Search

Talking Head Generation (THG), typically driven by audio, is an important and challenging task with broad application prospects in various fields such as digital humans, film production, and virtual reality. While diffusion model-based THG methods present high quality and stable content generation, they often overlook the intrinsic style which encompasses personalized features such as speaking habits and facial expressions of a video. As consequence, the generated video content lacks diversity and vividness, thus being limited in real life scenarios. To address these issues, we propose a novel framework named Style-Enhanced Vivid Portrait (SVP) which fully leverages style-related information in THG. Specifically, we first introduce the novel probabilistic style prior learning to model the intrinsic style as a Gaussian distribution using facial expressions and audio embedding. The distribution is learned through the 'bespoked' contrastive objective, effectively capturing the dynamic style information in each video. Then we finetune a pretrained Stable Diffusion (SD) model to inject the learned intrinsic style as a controlling signal via cross attention. Experiments show that our model generates diverse, vivid, and high-quality videos with flexible control over intrinsic styles, outperforming existing state-of-the-art methods.

The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 106 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.

Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings., Comment: There is an error. In Sec 4.1, the number of images in some dataset is incorrect and needs to be revised

Despite significant anecdotal evidence regarding the vulnerability of the U.S. power infrastructure, there is a dearth of longitudinal and nation-level characterization of the spatial and temporal patterns in the frequency and extent of power outages. A data-driven national-level characterization of power outage vulnerability is particularly essential for understanding the urgency and formulating policies to promote the resilience of power infrastructure systems. Recognizing this, we retrieved 179,053,397 county-level power outage records with a 15-minute interval across 3,022 US counties during 2014-2023 to capture power outage characteristics. We focus on three dimensions--power outage intensity, frequency, and duration--and develop multiple metrics to quantify each dimension of power outage vulnerability. The results show that in the past ten years, the vulnerability of U.S. power system has consistently been increasing. Counties experienced an average of 999.4 outages over the decade, affecting an average of more than 540,000 customers per county, with disruptions occurring approximately every week. Coastal areas, particularly in California, Florida and New Jersey, faced more frequent and prolonged outages, while inland regions showed higher outage rates. A concerning increase in outage frequency and intensity was noted, especially after 2017, with a sharp rise in prolonged outages since 2019. The research also found positive association between social vulnerability and outage metrics, with the association becoming stronger over the years under study. Areas with higher social vulnerability experienced more severe and frequent outages, exacerbating challenges in these regions. These findings reveal the much-needed empirical evidence for stakeholders to inform policy formulation and program development for enhancing the resilience of the U.S. power infrastructure.

In 1948, Fritz John proposed a theorem stating that every convex body has a unique maximal volume inscribed ellipsoid, known as the John ellipsoid. The John ellipsoid has become fundamental in mathematics, with extensive applications in high-dimensional sampling, linear programming, and machine learning. Designing faster algorithms to compute the John ellipsoid is therefore an important and emerging problem. In [Cohen, Cousins, Lee, Yang COLT 2019], they established an algorithm for approximating the John ellipsoid for a symmetric convex polytope defined by a matrix $A \in \mathbb{R}^{n \times d}$ with a time complexity of $O(nd^2)$. This was later improved to $O(\text{nnz}(A) + d^\omega)$ by [Song, Yang, Yang, Zhou 2022], where $\text{nnz}(A)$ is the number of nonzero entries of $A$ and $\omega$ is the matrix multiplication exponent. Currently $\omega \approx 2.371$ [Alman, Duan, Williams, Xu, Xu, Zhou 2024]. In this work, we present the first quantum algorithm that computes the John ellipsoid utilizing recent advances in quantum algorithms for spectral approximation and leverage score approximation, running in $O(\sqrt{n}d^{1.5} + d^\omega)$ time. In the tall matrix regime, our algorithm achieves quadratic speedup, resulting in a sublinear running time and significantly outperforming the current best classical algorithms.

Given a character triple $(G,N,\theta)$, which means that $G$ is a finite group with $N \vartriangleleft G$ and $\theta\in{\rm Irr}(N)$ is $G$-invariant, we introduce the notion of a $\pi$-quasi extension of $\theta$ to $G$ where $\pi$ is the set of primes dividing the order of the cohomology element $[\theta]_{G/N}\in H^2(G/N,\mathbb{C}^\times)$ associated with the character triple, and then establish the uniqueness of such an extension in the normalized case. As an application, we use the $\pi$-quasi extension of $\theta$ to construct a bijection from the set of $\pi$-defect zero characters of $G/N$ onto the set of relative $\pi$-defect zero characters of $G$ over $\theta$. Our results generalize the related theorems of M. Murai and of G. Navarro.

Multi-behavior recommendation systems enhance effectiveness by leveraging auxiliary behaviors (such as page views and favorites) to address the limitations of traditional models that depend solely on sparse target behaviors like purchases. Existing approaches to multi-behavior recommendations typically follow one of two strategies: some derive initial node representations from individual behavior subgraphs before integrating them for a comprehensive profile, while others interpret multi-behavior data as a heterogeneous graph, applying graph neural networks to achieve a unified node representation. However, these methods do not adequately explore the intricate patterns of behavior among users and items. To bridge this gap, we introduce a novel algorithm called Behavior Pattern mining-based Multi-behavior Recommendation (BPMR). Our method extensively investigates the diverse interaction patterns between users and items, utilizing these patterns as features for making recommendations. We employ a Bayesian approach to streamline the recommendation process, effectively circumventing the challenges posed by graph neural network algorithms, such as the inability to accurately capture user preferences due to over-smoothing. Our experimental evaluation on three real-world datasets demonstrates that BPMR significantly outperforms existing state-of-the-art algorithms, showing an average improvement of 268.29% in Recall@10 and 248.02% in NDCG@10 metrics. The code of our BPMR is openly accessible for use and further research at https://github.com/rookitkitlee/BPMR.

Heterogeneous Graph Neural Networks (HGNNs) leverage diverse semantic relationships in Heterogeneous Graphs (HetGs) and have demonstrated remarkable learning performance in various applications. However, current distributed GNN training systems often overlook unique characteristics of HetGs, such as varying feature dimensions and the prevalence of missing features among nodes, leading to suboptimal performance or even incompatibility with distributed HGNN training. We introduce Heta, a framework designed to address the communication bottleneck in distributed HGNN training. Heta leverages the inherent structure of HGNNs - independent relation-specific aggregations for each relation, followed by a cross-relation aggregation - and advocates for a novel Relation-Aggregation-First computation paradigm. It performs relation-specific aggregations within graph partitions and then exchanges partial aggregations. This design, coupled with a new graph partitioning method that divides a HetG based on its graph schema and HGNN computation dependency, substantially reduces communication overhead. Heta further incorporates an innovative GPU feature caching strategy that accounts for the different cache miss-penalties associated with diverse node types. Comprehensive evaluations of various HGNN models and large heterogeneous graph datasets demonstrate that Heta outperforms state-of-the-art systems like DGL and GraphLearn by up to 5.8x and 2.3x in end-to-end epoch time, respectively.

Advancements in autonomous driving have increasingly focused on end-to-end (E2E) systems that manage the full spectrum of driving tasks, from environmental perception to vehicle navigation and control. This paper introduces V2X-VLM, an innovative E2E vehicle-infrastructure cooperative autonomous driving (VICAD) framework with large vision-language models (VLMs). V2X-VLM is designed to enhance situational awareness, decision-making, and ultimate trajectory planning by integrating data from vehicle-mounted cameras, infrastructure sensors, and textual information. The strength of the comprehensive multimodel data fusion of the VLM enables precise and safe E2E trajectory planning in complex and dynamic driving scenarios. Validation on the DAIR-V2X dataset demonstrates that V2X-VLM outperforms existing state-of-the-art methods in cooperative autonomous driving.

The perception of physical objects and miniatures enhances the realism and immersion in VR. This work explores the relationship between haptic feedback from real objects and their visual representations in VR. The study examines how users confirm and adjust the sizes of different virtual objects. The results show that as the size of the virtual cubes increases, users are less likely to perceive the size correctly and need more adjustments. This research provides insights into how haptic sensations and visual inputs interact, contributing to the understanding of visual-haptic illusions in VR environments., Comment: 8 pages, 6 figures, VINCI 2024

Determining the John ellipsoid - the largest volume ellipsoid contained within a convex polytope - is a fundamental problem with applications in machine learning, optimization, and data analytics. Recent work has developed fast algorithms for approximating the John ellipsoid using sketching and leverage score sampling techniques. However, these algorithms do not provide privacy guarantees for sensitive input data. In this paper, we present the first differentially private algorithm for fast John ellipsoid computation. Our method integrates noise perturbation with sketching and leverage score sampling to achieve both efficiency and privacy. We prove that (1) our algorithm provides $(\epsilon,\delta)$-differential privacy, and the privacy guarantee holds for neighboring datasets that are $\epsilon_0$-close, allowing flexibility in the privacy definition; (2) our algorithm still converges to a $(1+\xi)$-approximation of the optimal John ellipsoid in $O(\xi^{-2}(\log(n/\delta_0) + (L\epsilon_0)^{-2}))$ iterations where $n$ is the number of data point, $L$ is the Lipschitz constant, $\delta_0$ is the failure probability, and $\epsilon_0$ is the closeness of neighboring input datasets. Our theoretical analysis demonstrates the algorithm's convergence and privacy properties, providing a robust approach for balancing utility and privacy in John ellipsoid computation. This is the first differentially private algorithm for fast John ellipsoid computation, opening avenues for future research in privacy-preserving optimization techniques.

This study explores text-to-SQL parsing by leveraging the powerful reasoning capabilities of large language models (LLMs). Despite recent advancements, existing LLM-based methods have not adequately addressed scalability, leading to inefficiencies when processing wide tables. Furthermore, current interaction-based approaches either lack a step-by-step, interpretable SQL generation process or fail to provide an efficient and universally applicable interaction design. To address these challenges, we introduce Interactive-T2S, a framework that generates SQL queries through direct interactions with databases. This framework includes four general tools that facilitate proactive and efficient information retrieval by the LLM. Additionally, we have developed detailed exemplars to demonstrate the step-wise reasoning processes within our framework. Our experiments on the BIRD-Dev dataset, employing a setting without oracle knowledge, reveal that our method achieves state-of-the-art results with only two exemplars, underscoring the effectiveness and robustness of our framework., Comment: 15 pages, 7 figures

Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often tie pruning techniques to specific model architectures or vision tasks. To address this limitation, we propose a novel unified pruning framework Comb, Prune, Distill (CPD), which addresses both model-agnostic and task-agnostic concerns simultaneously. Our framework employs a combing step to resolve hierarchical layer-wise dependency issues, enabling architecture independence. Additionally, the pruning pipeline adaptively remove parameters based on the importance scoring metrics regardless of vision tasks. To support the model in retaining its learned information, we introduce knowledge distillation during the pruning step. Extensive experiments demonstrate the generalizability of our framework, encompassing both convolutional neural network (CNN) and transformer models, as well as image classification and segmentation tasks. In image classification we achieve a speedup of up to x4.3 with a accuracy loss of 1.8% and in semantic segmentation up to x1.89 with a 5.1% loss in mIoU., Comment: Accepted by ITSC 2024. Code is publicly available at: https://github.com/Cranken/CPD

With the progressive advancements in deep graph learning, out-of-distribution (OOD) detection for graph data has emerged as a critical challenge. While the efficacy of auxiliary datasets in enhancing OOD detection has been extensively studied for image and text data, such approaches have not yet been explored for graph data. Unlike Euclidean data, graph data exhibits greater diversity but lower robustness to perturbations, complicating the integration of outliers. To tackle these challenges, we propose the introduction of \textbf{H}ybrid External and Internal \textbf{G}raph \textbf{O}utlier \textbf{E}xposure (HGOE) to improve graph OOD detection performance. Our framework involves using realistic external graph data from various domains and synthesizing internal outliers within ID subgroups to address the poor robustness and presence of OOD samples within the ID class. Furthermore, we develop a boundary-aware OE loss that adaptively assigns weights to outliers, maximizing the use of high-quality OOD samples while minimizing the impact of low-quality ones. Our proposed HGOE framework is model-agnostic and designed to enhance the effectiveness of existing graph OOD detection models. Experimental results demonstrate that our HGOE framework can significantly improve the performance of existing OOD detection models across all 8 real datasets., Comment: Proceedings of the 32nd ACM International Conference on Multimedia

SAR image simulation has attracted much attention due to its great potential to supplement the scarce training data for deep learning algorithms. Consequently, evaluating the quality of the simulated SAR image is crucial for practical applications. The current literature primarily uses image quality assessment techniques for evaluation that rely on human observers' perceptions. However, because of the unique imaging mechanism of SAR, these techniques may produce evaluation results that are not entirely valid. The distribution inconsistency between real and simulated data is the main obstacle that influences the utility of simulated SAR images. To this end, we propose a novel trustworthy utility evaluation framework with a counterfactual explanation for simulated SAR images for the first time, denoted as X-Fake. It unifies a probabilistic evaluator and a causal explainer to achieve a trustworthy utility assessment. We construct the evaluator using a probabilistic Bayesian deep model to learn the posterior distribution, conditioned on real data. Quantitatively, the predicted uncertainty of simulated data can reflect the distribution discrepancy. We build the causal explainer with an introspective variational auto-encoder to generate high-resolution counterfactuals. The latent code of IntroVAE is finally optimized with evaluation indicators and prior information to generate the counterfactual explanation, thus revealing the inauthentic details of simulated data explicitly. The proposed framework is validated on four simulated SAR image datasets obtained from electromagnetic models and generative artificial intelligence approaches. The results demonstrate the proposed X-Fake framework outperforms other IQA methods in terms of utility. Furthermore, the results illustrate that the generated counterfactual explanations are trustworthy, and can further improve the data utility in applications.

Recent theoretical efforts predicted a type of unconventional antiferromagnet characterized by the crystal symmetry C (rotation or mirror), which connects antiferromagnetic sublattices in real space and simultaneously couples spin and momentum in reciprocal space. This results in a unique C-paired spin-valley locking (SVL) and corresponding novel properties such as piezomagnetism and noncollinear spin current even without spin-orbit coupling. However, the unconventional antiferromagnets reported thus far are not layered materials, limiting their potential in spintronic applications. Additionally, they do not meet the necessary symmetry requirements for nonrelativistic spin current. Here, we report the realization of C-paired SVL in a layered room-temperature antiferromagnetic compound, Rb1-{\delta}V2Te2O. Spin resolved photoemission measurements directly demonstrate the opposite spin splitting between C-paired valleys. Quasi-particle interference patterns reveal the suppression of inter-valley scattering due to the spin selection rules, as a direct consequence of C-paired SVL. All these experiments are well consistent with the results obtained from first-principles calculations. Our observations represent the first realization of layered antiferromagnets with C-paired SVL, enabling both the advantages of layered materials and possible control through crystal symmetry manipulation. These results hold significant promise and broad implications for advancements in magnetism, electronics, and information technology., Comment: 22 pages, 5 figures

In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research papers often operate under diverse settings and tasks, incorporating potential training strategies. This heterogeneity poses challenges in establishing a fair comparison among these attention module variants. In this paper, we address this issue by rethinking and exploring attention module design within a consistent base framework and settings. Both global-based and local-based attention methods are studied, with a focus on the selection basis and scales of neighbors for local-based attention. Different combinations of aggregated local features and computation methods for attention scores are evaluated, ranging from the initial addition/concatenation-based approach to the widely adopted dot product-based method and the recently proposed vector attention technique. Various position encoding methods are also investigated. Our extensive experimental analysis reveals that there is no universally optimal design across diverse point cloud tasks. Instead, drawing from best practices, we propose tailored attention modules for specific tasks, leading to superior performance on point cloud classification and segmentation benchmarks.

As a special type of collinear antiferromagnetism (AFM), altermagnetism has garnered significant research interest recently. Altermagnets exhibit broken parity-time symmetry and zero net magnetization in real space, leading to substantial band splitting in momentum space even in the absence of spin-orbit coupling. Meanwhile, parity-time symmetry breaking always induce nontrivial band topology such as Weyl nodes. While Weyl semimetal states and nodal lines have been theoretically proposed in altermagnets, rare reports of experimental observation have been made up to this point. Using ARPES and first-principles calculations, we systematically studied the electronic structure of the room-temperature altermagnet candidate CrSb. At generic locations in momentum space, we clearly observed band spin splitting. Furthermore, we identified discrete surface Fermi arcs on the (100) cleaved side surface close to the Fermi level originating from bulk band topology. Our results imply that CrSb contains interesting nontrivial topological Weyl physics, in addition to being an excellent room temperature altermagnet., Comment: 10 pages, 4 figures

We aim to evaluate the efficacy of traditional machine learning and large language models (LLMs) in classifying anxiety and depression from long conversational transcripts. We fine-tune both established transformer models (BERT, RoBERTa, Longformer) and more recent large models (Mistral-7B), trained a Support Vector Machine with feature engineering, and assessed GPT models through prompting. We observe that state-of-the-art models fail to enhance classification outcomes compared to traditional machine learning methods.

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen representations from text-image generative models, along with salient-aware and geometric-aware masks, for open-vocabulary 3D semantic segmentation and visual grounding tasks. Diff2Scene gets rid of any labeled 3D data and effectively identifies objects, appearances, materials, locations and their compositions in 3D scenes. We show that it outperforms competitive baselines and achieves significant improvements over state-of-the-art methods. In particular, Diff2Scene improves the state-of-the-art method on ScanNet200 by 12%., Comment: ECCV 2024

We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first presented to facilitate the unsupervised cross-modal homography estimation. The correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework. SCPNet is the first to achieve effective unsupervised homography estimation on the satellite-map image pair cross-modal dataset, GoogleMap, under [-32,+32] offset on a 128x128 image, leading the supervised approach MHN by 14.0% of mean average corner error (MACE). We further conduct extensive experiments on several cross-modal/spectral and manually-made inconsistent datasets, on which SCPNet achieves the state-of-the-art (SOTA) performance among unsupervised approaches, and owns 49.0%, 25.2%, 36.4%, and 10.7% lower MACEs than the supervised approach MHN. Source code is available at https://github.com/RM-Zhang/SCPNet., Comment: Accepted by ECCV 2024

Antiferromagnetic materials (AFMs) have been gaining lots of attentions due to its great potential in spintronics devices and the recently discovered novel spin structure in the momentum space, i.e., $C$-paired spin-valley or spin-momentum locking (CSVL), where spins and valleys/momenta are locked to each other due to the crystal symmetry guaranteeing zero magnetization. Here, we systematically studied CSVLs and proposed a general theory and algorithm using little co-group and coset representatives, which reveals that 12 elementary kinds of CSVLs, determined by the geometric relation of spins and valleys and the essential symmetry guaranteeing zero magnetization, are sufficient to fully represent all possible CSVLs. By combining the proposed algorithm and high-throughput first-principles calculations, we predicted 38 magnetic point groups and identified 140 experimentally verified AFMs that can realize CSVL. Besides predicting new materials, our theory can naturally reveal underlying mechanisms of CSVLs' responses to external fields. As an example, two qualitatively different types of piezomagnetism via occupation imbalance or spin tilting were predicted in RuO$_2$. The algorithm and conclusions can be directly extended to the locking between valley/momentum and any other pseudo-vector degree of freedom, e.g. Berry curvature, as exemplified in RuO$_2$, and the proposed concept and methodology can be straightforwardly applied to other symmetry groups such as spin space group., Comment: Main text: 9 pages, 4 figures

Panoramic images, capturing a 360{\deg} field of view (FoV), encompass omnidirectional spatial information crucial for scene understanding. However, it is not only costly to obtain training-sufficient dense-annotated panoramas but also application-restricted when training models in a close-vocabulary setting. To tackle this problem, in this work, we define a new task termed Open Panoramic Segmentation (OPS), where models are trained with FoV-restricted pinhole images in the source domain in an open-vocabulary setting while evaluated with FoV-open panoramic images in the target domain, enabling the zero-shot open panoramic semantic segmentation ability of models. Moreover, we propose a model named OOOPS with a Deformable Adapter Network (DAN), which significantly improves zero-shot panoramic semantic segmentation performance. To further enhance the distortion-aware modeling ability from the pinhole source domain, we propose a novel data augmentation method called Random Equirectangular Projection (RERP) which is specifically designed to address object deformations in advance. Surpassing other state-of-the-art open-vocabulary semantic segmentation approaches, a remarkable performance boost on three panoramic datasets, WildPASS, Stanford2D3D, and Matterport3D, proves the effectiveness of our proposed OOOPS model with RERP on the OPS task, especially +2.2% on outdoor WildPASS and +2.4% mIoU on indoor Stanford2D3D. The source code is publicly available at https://junweizheng93.github.io/publications/OPS/OPS.html., Comment: Accepted by ECCV 2024. Project page: https://junweizheng93.github.io/publications/OPS/OPS.html

We introduce a new task called Referring Atomic Video Action Recognition (RAVAR), aimed at identifying atomic actions of a particular person based on a textual description and the video data of this person. This task differs from traditional action recognition and localization, where predictions are delivered for all present individuals. In contrast, we focus on recognizing the correct atomic action of a specific individual, guided by text. To explore this task, we present the RefAVA dataset, containing 36,630 instances with manually annotated textual descriptions of the individuals. To establish a strong initial benchmark, we implement and validate baselines from various domains, e.g., atomic action localization, video question answering, and text-video retrieval. Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person. The key ingredients are: (1) a multi-stream architecture that connects video, text, and a new location-semantic stream, and (2) cross-stream agent attention fusion and agent token fusion which amplify the most relevant information across these streams and consistently surpasses standard attention-based fusion on RAVAR. Extensive experiments demonstrate the effectiveness of RefAtomNet and its building blocks for recognizing the action of the described individual. The dataset and code will be made publicly available at https://github.com/KPeng9510/RAVAR., Comment: Accepted to ECCV 2024. The dataset and code will be made publicly available at https://github.com/KPeng9510/RAVAR

Polyp segmentation plays a pivotal role in colorectal cancer diagnosis. Recently, the emergence of the Segment Anything Model (SAM) has introduced unprecedented potential for polyp segmentation, leveraging its powerful pre-training capability on large-scale datasets. However, due to the domain gap between natural and endoscopy images, SAM encounters two limitations in achieving effective performance in polyp segmentation. Firstly, its Transformer-based structure prioritizes global and low-frequency information, potentially overlooking local details, and introducing bias into the learned features. Secondly, when applied to endoscopy images, its poor out-of-distribution (OOD) performance results in substandard predictions and biased confidence output. To tackle these challenges, we introduce a novel approach named Augmented SAM for Polyp Segmentation (ASPS), equipped with two modules: Cross-branch Feature Augmentation (CFA) and Uncertainty-guided Prediction Regularization (UPR). CFA integrates a trainable CNN encoder branch with a frozen ViT encoder, enabling the integration of domain-specific knowledge while enhancing local features and high-frequency details. Moreover, UPR ingeniously leverages SAM's IoU score to mitigate uncertainty during the training procedure, thereby improving OOD performance and domain generalization. Extensive experimental results demonstrate the effectiveness and utility of the proposed method in improving SAM's performance in polyp segmentation. Our code is available at https://github.com/HuiqianLi/ASPS., Comment: Accepted by MICCAI2024

Graph learning models have been widely deployed in collaborative filtering (CF) based recommendation systems. Due to the issue of data sparsity, the graph structure of the original input lacks potential positive preference edges, which significantly reduces the performance of recommendations. In this paper, we study how to enhance the graph structure for CF more effectively, thereby optimizing the representation of graph nodes. Previous works introduced matrix completion techniques into CF, proposing the use of either stochastic completion methods or superficial structure completion to address this issue. However, most of these approaches employ random numerical filling that lack control over noise perturbations and limit the in-depth exploration of higher-order interaction features of nodes, resulting in biased graph representations. In this paper, we propose an Amplify Graph Learning framework based on Sparsity Completion (called AGL-SC). First, we utilize graph neural network to mine direct interaction features between user and item nodes, which are used as the inputs of the encoder. Second, we design a factorization-based method to mine higher-order interaction features. These features serve as perturbation factors in the latent space of the hidden layer to facilitate generative enhancement. Finally, by employing the variational inference, the above multi-order features are integrated to implement the completion and enhancement of missing graph structures. We conducted benchmark and strategy experiments on four real-world datasets related to recommendation tasks. The experimental results demonstrate that AGL-SC significantly outperforms the state-of-the-art methods.

Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity expression-to-face renderer. In the first component, we consider both identity and intra-personal variation features related to speaking lip movements. By incorporating cross-modal attention on the enriched facial priors, we can effectively align lip movements with audio, thus attaining greater precision in expression prediction. In the second component, we design a lightweight facial identity alignment (FIA) module which includes a lip-shape control structure and a face texture reference structure. This novel design allows us to generate fine details in real-time, without depending on sophisticated and inefficient feature alignment modules. Our experimental results, both quantitative and qualitative, on public datasets demonstrate the clear advantages of our method in terms of lip-speech synchronization and generation quality. Furthermore, our method is efficient and requires fewer computational resources, making it well-suited to meet the needs of practical applications.

Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views. Existing methods, however, heavily rely on pre-computed poses and Gaussian initialization by Structure from Motion (SfM) algorithms or expensive sensors. For the first time, this paper addresses this issue by integrating self-supervised VO into our pose-free dynamic Gaussian method (VDG) to boost pose and depth initialization and static-dynamic decomposition. Moreover, VDG can work with only RGB image input and construct dynamic scenes at a faster speed and larger scenes compared with the pose-free dynamic view-synthesis method. We demonstrate the robustness of our approach via extensive quantitative and qualitative experiments. Our results show favorable performance over the state-of-the-art dynamic view synthesis methods. Additional video and source code will be posted on our project page at https://3d-aigc.github.io/VDG.

With the rapid development of multimodal large language models (MLLMs), especially their capabilities in visual chat through refer and ground functionalities, their significance is increasingly recognized. However, the biomedical field currently exhibits a substantial gap in this area, primarily due to the absence of a dedicated refer and ground dataset for biomedical images. To address this challenge, we devised the Med-GRIT-270k dataset. It comprises 270k question-and-answer pairs and spans eight distinct medical imaging modalities. Most importantly, it is the first dedicated to the biomedical domain and integrating refer and ground conversations. The key idea is to sample large-scale biomedical image-mask pairs from medical segmentation datasets and generate instruction datasets from text using chatGPT. Additionally, we introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning. Extensive experiments have corroborated the efficacy of the Med-GRIT-270k dataset and the multi-modal, fine-grained interactive capabilities of the BiRD model. This holds significant reference value for the exploration and development of intelligent biomedical assistants., Comment: Accepted by MICCAI2024

Open-Vocabulary Mobile Manipulation (OVMM) is a crucial capability for autonomous robots, especially when faced with the challenges posed by unknown and dynamic environments. This task requires robots to explore and build a semantic understanding of their surroundings, generate feasible plans to achieve manipulation goals, adapt to environmental changes, and comprehend natural language instructions from humans. To address these challenges, we propose a novel framework that leverages the zero-shot detection and grounded recognition capabilities of pretraining visual-language models (VLMs) combined with dense 3D entity reconstruction to build 3D semantic maps. Additionally, we utilize large language models (LLMs) for spatial region abstraction and online planning, incorporating human instructions and spatial semantic context. We have built a 10-DoF mobile manipulation robotic platform JSR-1 and demonstrated in real-world robot experiments that our proposed framework can effectively capture spatial semantics and process natural language user instructions for zero-shot OVMM tasks under dynamic environment settings, with an overall navigation and task success rate of 80.95% and 73.33% over 105 episodes, and better SFT and SPL by 157.18% and 19.53% respectively compared to the baseline. Furthermore, the framework is capable of replanning towards the next most probable candidate location based on the spatial semantic context derived from the 3D semantic map when initial plans fail, keeping an average success rate of 76.67%., Comment: Open-vocabulary, Mobile Manipulation, Dynamic Environments, 3D Semantic Maps, Zero-shot, LLMs, VLMs, 18 pages, 2 figures

High-fidelity 3D garment synthesis from text is desirable yet challenging for digital avatar creation. Recent diffusion-based approaches via Score Distillation Sampling (SDS) have enabled new possibilities but either intricately couple with human body or struggle to reuse. We introduce ClotheDreamer, a 3D Gaussian-based method for generating wearable, production-ready 3D garment assets from text prompts. We propose a novel representation Disentangled Clothe Gaussian Splatting (DCGS) to enable separate optimization. DCGS represents clothed avatar as one Gaussian model but freezes body Gaussian splats. To enhance quality and completeness, we incorporate bidirectional SDS to supervise clothed avatar and garment RGBD renderings respectively with pose conditions and propose a new pruning strategy for loose clothing. Our approach can also support custom clothing templates as input. Benefiting from our design, the synthetic 3D garment can be easily applied to virtual try-on and support physically accurate animation. Extensive experiments showcase our method's superior and competitive performance. Our project page is at https://ggxxii.github.io/clothedreamer., Comment: Project Page: https://ggxxii.github.io/clothedreamer

We report on an ultrafast terahertz free-carrier dynamic study of a photo-excited WTe2 thin film. In the photo-excited state, we observe a metastable electronic state featuring negative differential terahertz photoconductivity and reduced scattering rate. Detailed electrodynamics analysis and first-principal calculation attribute it to light-induced topological phase transition, reducing density of states near the Fermi level. Furthermore, the emergence of an unconventional temporal isosbestic point marks a dynamic universality, strongly suggesting a percolative interaction between the two topologically distinct phases.

Learning generalizable visual dynamic representation across different embodied environments is crucial for real-world robotic manipulation. As the scale and diversity of robot demonstration data are limited, recent works have turned to large-scale pre-training using human data. However, the morphological differences between humans and robots introduce a significant human-robot domain discrepancy, challenging the generalization of these human-data pre-trained models to downstream manipulation tasks. To address this, we propose a novel adaptation paradigm that utilizes readily available paired human-robot video data to bridge the discrepancy. Following this paradigm, our method exploits a human-robot contrastive alignment loss to align the semantics of human and robot videos, adapting pre-trained models to the robotic domain in a parameter-efficient manner. The experiments demonstrate significant improvements on 25 tasks across three different benchmarks, where the single-task, language-conditioned multi-task settings are covered, and two different pre-trained models are evaluated. On the large RLBench benchmark, our adaptation method achieves an average improvement of $8.9\%$ in success rate over the pre-trained R3M model across multiple tasks. We will release the code and models upon acceptance.

We propose a new comprehensive benchmark to revolutionize the current deepfake detection field to the next generation. Predominantly, existing works identify top-notch detection algorithms and models by adhering to the common practice: training detectors on one specific dataset (e.g., FF++) and testing them on other prevalent deepfake datasets. This protocol is often regarded as a "golden compass" for navigating SoTA detectors. But can these stand-out "winners" be truly applied to tackle the myriad of realistic and diverse deepfakes lurking in the real world? If not, what underlying factors contribute to this gap? In this work, we found the dataset (both train and test) can be the "primary culprit" due to: (1) forgery diversity: Deepfake techniques are commonly referred to as both face forgery (face-swapping and face-reenactment) and entire image synthesis (AIGC). Most existing datasets only contain partial types, with limited forgery methods implemented; (2) forgery realism: The dominant training dataset, FF++, contains old forgery techniques from the past five years. "Honing skills" on these forgeries makes it difficult to guarantee effective detection of nowadays' SoTA deepfakes; (3) evaluation protocol: Most detection works perform evaluations on one type, e.g., train and test on face-swapping only, which hinders the development of universal deepfake detectors. To address this dilemma, we construct a highly diverse and large-scale deepfake dataset called DF40, which comprises 40 distinct deepfake techniques. We then conduct comprehensive evaluations using 4 standard evaluation protocols and 7 representative detectors, resulting in over 2,000 evaluations. Through these evaluations, we analyze from various perspectives, leading to 12 new insightful findings contributing to the field. We also open up 5 valuable yet previously underexplored research questions to inspire future works.

Vehicle trajectory prediction is crucial for advancing autonomous driving and advanced driver assistance systems (ADAS), enhancing road safety and traffic efficiency. While traditional methods have laid foundational work, modern deep learning techniques, particularly transformer-based models and generative approaches, have significantly improved prediction accuracy by capturing complex and non-linear patterns in vehicle motion and traffic interactions. However, these models often overlook the detailed car-following behaviors and inter-vehicle interactions essential for real-world driving scenarios. This study introduces a Cross-Attention Transformer Enhanced Conditional Diffusion Model (Crossfusor) specifically designed for car-following trajectory prediction. Crossfusor integrates detailed inter-vehicular interactions and car-following dynamics into a robust diffusion framework, improving both the accuracy and realism of predicted trajectories. The model leverages a novel temporal feature encoding framework combining GRU, location-based attention mechanisms, and Fourier embedding to capture historical vehicle dynamics. It employs noise scaled by these encoded historical features in the forward diffusion process, and uses a cross-attention transformer to model intricate inter-vehicle dependencies in the reverse denoising process. Experimental results on the NGSIM dataset demonstrate that Crossfusor outperforms state-of-the-art models, particularly in long-term predictions, showcasing its potential for enhancing the predictive capabilities of autonomous driving systems.

The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space and lead to incorrect predictions. Recent studies have attempted to calibrate contaminated features by either suppressing or over-activating particular channels. Despite these efforts, we claim that adversarial attacks exhibit varying disruption levels across individual channels. Furthermore, we argue that harmonizing feature maps via graph and employing graph convolution can calibrate contaminated features. To this end, we introduce an innovative plug-and-play module called Feature Map-based Reconstructed Graph Convolution (FMR-GC). FMR-GC harmonizes feature maps in the channel dimension to reconstruct the graph, then employs graph convolution to capture neighborhood information, effectively calibrating contaminated features. Extensive experiments have demonstrated the superior performance and scalability of FMR-GC. Moreover, our model can be combined with advanced adversarial training methods to considerably enhance robustness without compromising the model's clean accuracy.

Developing robots capable of executing various manipulation tasks, guided by natural language instructions and visual observations of intricate real-world environments, remains a significant challenge in robotics. Such robot agents need to understand linguistic commands and distinguish between the requirements of different tasks. In this work, we present Sigma-Agent, an end-to-end imitation learning agent for multi-task robotic manipulation. Sigma-Agent incorporates contrastive Imitation Learning (contrastive IL) modules to strengthen vision-language and current-future representations. An effective and efficient multi-view querying Transformer (MVQ-Former) for aggregating representative semantic information is introduced. Sigma-Agent shows substantial improvement over state-of-the-art methods under diverse settings in 18 RLBench tasks, surpassing RVT by an average of 5.2% and 5.9% in 10 and 100 demonstration training, respectively. Sigma-Agent also achieves 62% success rate with a single policy in 5 real-world manipulation tasks. The code will be released upon acceptance.

Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension. However, due to the limitations of existing datasets, RSLMMs have shortcomings in understanding the rich semantic relations among objects in complex remote sensing scenes. To unlock RSLMMs' complex comprehension ability, we propose a large-scale instruction tuning dataset FIT-RS, containing 1,800,851 instruction samples. FIT-RS covers common interpretation tasks and innovatively introduces several complex comprehension tasks of escalating difficulty, ranging from relation reasoning to image-level scene graph generation. Based on FIT-RS, we build the FIT-RSFG benchmark. Furthermore, we establish a new benchmark to evaluate the fine-grained relation comprehension capabilities of LMMs, named FIT-RSRC. Based on combined instruction data, we propose SkySenseGPT, which achieves outstanding performance on both public datasets and FIT-RSFG, surpassing existing RSLMMs. We hope the FIT-RS dataset can enhance the relation comprehension capability of RSLMMs and provide a large-scale fine-grained data source for the remote sensing community. The dataset will be available at https://github.com/Luo-Z13/SkySenseGPT, Comment: 30 pages, 5 figures, 19 tables, dataset and code see https://github.com/Luo-Z13/SkySenseGPT

Repository-level code completion is challenging as it involves complicated contexts from multiple files in the repository. To date, researchers have proposed two technical categories to enhance LLM-based repository-level code completion, i.e., retrieval-augmented generation (RAG) and static analysis integration. This work performs the first study on the static analysis integration in LLM-based repository-level code completion by investigating both the effectiveness and efficiency of static analysis integration strategies across different phases of code completion. We first implement a framework STALL+, which supports an extendable and customizable integration of multiple static analysis strategies into the complete pipeline of LLM-based repository-level code completion; and based on STALL+, we perform extensive experiments by including different code LLMs on the latest repository-level code completion benchmark CrossCodeEval. Our findings show that integrating file-level dependencies in prompting phase performs the best while the integration in post-processing phase performs the worse. Additionally, we observe different improvements from static analysis between dynamic languages and static languages, i.e., the best combination is prompting-phase with decoding-phase integration for Java while the best combination is prompting-phase with post-processing-phase integration for Python given the limitations of statically analyzing dynamic languages. Additionally, we find the complementarity between RAG and static analysis integration as well as their cost-effectiveness after combination., Comment: 12 pages, 5 figures

Real-time detection and prediction of extreme weather protect human lives and infrastructure. Traditional methods rely on numerical threshold setting and manual interpretation of weather heatmaps with Geographic Information Systems (GIS), which can be slow and error-prone. Our research redefines Extreme Weather Events Detection (EWED) by framing it as a Visual Question Answering (VQA) problem, thereby introducing a more precise and automated solution. Leveraging Vision-Language Models (VLM) to simultaneously process visual and textual data, we offer an effective aid to enhance the analysis process of weather heatmaps. Our initial assessment of general-purpose VLMs (e.g., GPT-4-Vision) on EWED revealed poor performance, characterized by low accuracy and frequent hallucinations due to inadequate color differentiation and insufficient meteorological knowledge. To address these challenges, we introduce ClimateIQA, the first meteorological VQA dataset, which includes 8,760 wind gust heatmaps and 254,040 question-answer pairs covering four question types, both generated from the latest climate reanalysis data. We also propose Sparse Position and Outline Tracking (SPOT), an innovative technique that leverages OpenCV and K-Means clustering to capture and depict color contours in heatmaps, providing ClimateIQA with more accurate color spatial location information. Finally, we present Climate-Zoo, the first meteorological VLM collection, which adapts VLMs to meteorological applications using the ClimateIQA dataset. Experiment results demonstrate that models from Climate-Zoo substantially outperform state-of-the-art general VLMs, achieving an accuracy increase from 0% to over 90% in EWED verification. The datasets and models in this study are publicly available for future climate science research: https://github.com/AlexJJJChen/Climate-Zoo.

Scene graph generation (SGG) in satellite imagery (SAI) benefits promoting understanding of geospatial scenarios from perception to cognition. In SAI, objects exhibit great variations in scales and aspect ratios, and there exist rich relationships between objects (even between spatially disjoint objects), which makes it attractive to holistically conduct SGG in large-size very-high-resolution (VHR) SAI. However, there lack such SGG datasets. Due to the complexity of large-size SAI, mining triplets heavily relies on long-range contextual reasoning. Consequently, SGG models designed for small-size natural imagery are not directly applicable to large-size SAI. This paper constructs a large-scale dataset for SGG in large-size VHR SAI with image sizes ranging from 512 x 768 to 27,860 x 31,096 pixels, named STAR (Scene graph generaTion in lArge-size satellite imageRy), encompassing over 210K objects and over 400K triplets. To realize SGG in large-size SAI, we propose a context-aware cascade cognition (CAC) framework to understand SAI regarding object detection (OBD), pair pruning and relationship prediction for SGG. We also release a SAI-oriented SGG toolkit with about 30 OBD and 10 SGG methods which need further adaptation by our devised modules on our challenging STAR dataset. The dataset and toolkit are available at: https://linlin-dev.github.io/project/STAR., Comment: 18 pages, 11 figures

To facilitate the evolution of edge intelligence in ever-changing environments, we study on-device incremental learning constrained in limited computation resource in this paper. Current on-device training methods just focus on efficient training without considering the catastrophic forgetting, preventing the model getting stronger when continually exploring the world. To solve this problem, a direct solution is to involve the existing incremental learning mechanisms into the on-device training framework. Unfortunately, such a manner cannot work well as those mechanisms usually introduce large additional computational cost to the network optimization process, which would inevitably exceed the memory capacity of the edge devices. To address this issue, this paper makes an early effort to propose a simple but effective edge-friendly incremental learning framework. Based on an empirical study on the knowledge intensity of the kernel elements of the neural network, we find that the center kernel is the key for maximizing the knowledge intensity for learning new data, while freezing the other kernel elements would get a good balance on the model's capacity for overcoming catastrophic forgetting. Upon this finding, we further design a center-sensitive kernel optimization framework to largely alleviate the cost of the gradient computation and back-propagation. Besides, a dynamic channel element selection strategy is also proposed to facilitate a sparse orthogonal gradient projection for further reducing the optimization complexity, upon the knowledge explored from the new task data. Extensive experiments validate our method is efficient and effective, e.g., our method achieves average accuracy boost of 38.08% with even less memory and approximate computation compared to existing on-device training methods, indicating its significant potential for on-device incremental learning.

Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus devise a technique to turn TabPFN -- a highly performant transformer initially designed for in-context discriminative tabular tasks -- into an energy-based generative model, which we dub TabPFGen. This novel framework leverages the pre-trained TabPFN as part of the energy function and does not require any additional training or hyperparameter tuning, thus inheriting TabPFN's in-context learning capability. We can sample from TabPFGen analogously to other energy-based models. We demonstrate strong results on standard generative modelling tasks, including data augmentation, class-balancing, and imputation, unlocking a new frontier of tabular data generation.

Tabular data is a pervasive modality spanning a wide range of domains, and the inherent diversity poses a considerable challenge for deep learning. Recent advancements using transformer-based in-context learning have shown promise on smaller and less complex datasets, but have struggled to scale to larger and more complex ones. To address this limitation, we propose a combination of retrieval and fine-tuning: we can adapt the transformer to a local subset of the data by collecting nearest neighbours, and then perform task-specific fine-tuning with this retrieved set of neighbours in context. Using TabPFN as the base model -- currently the best tabular in-context learner -- and applying our retrieval and fine-tuning scheme on top results in what we call a locally-calibrated PFN, or LoCalPFN. We conduct extensive evaluation on 95 datasets curated by TabZilla from OpenML, upon which we establish a new state-of-the-art with LoCalPFN -- even with respect to tuned tree-based models. Notably, we show a significant boost in performance compared to the base in-context model, demonstrating the efficacy of our approach and advancing the frontier of deep learning in tabular data.

Individualized treatment rules tailor treatments to patients based on clinical, demographic, and other characteristics. Estimation of individualized treatment rules requires the identification of individuals who benefit most from the particular treatments and thus the detection of variability in treatment effects. To develop an effective individualized treatment rule, data from multisite studies may be required due to the low power provided by smaller datasets for detecting the often small treatment-covariate interactions. However, sharing of individual-level data is sometimes constrained. Furthermore, sparsity may arise in two senses: different data sites may recruit from different populations, making it infeasible to estimate identical models or all parameters of interest at all sites, and the number of non-zero parameters in the model for the treatment rule may be small. To address these issues, we adopt a two-stage Bayesian meta-analysis approach to estimate individualized treatment rules which optimize expected patient outcomes using multisite data without disclosing individual-level data beyond the sites. Simulation results demonstrate that our approach can provide consistent estimates of the parameters which fully characterize the optimal individualized treatment rule. We estimate the optimal Warfarin dose strategy using data from the International Warfarin Pharmacogenetics Consortium, where data sparsity and small treatment-covariate interaction effects pose additional statistical challenges.

Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training session, it introduces a supervisory mechanism to guide network expansion whose growth size is compactly commensurate with the intrinsic complexity of a newly arriving task. This constructs a near-minimal network while allowing the model to expand its capacity when cannot sufficiently hold new classes. At inference time, it automatically reactivates the required neural units to retrieve knowledge and leaves the remaining inactivated to prevent interference. We name our model AutoActivator, which is effective and scalable. To gain insights into the neural unit dynamics, we theoretically analyze the model's convergence property via a universal approximation theorem on learning sequential mappings, which is under-explored in the CIL community. Experiments show that our method achieves strong CIL performance in rehearsal-free and minimal-expansion settings with different backbones., Comment: Accepted to ICML 2024

Cardinality estimation (CardEst) is essential for optimizing query execution plans. Recent ML-based CardEst methods achieve high accuracy but face deployment challenges due to high preparation costs and lack of transferability across databases. In this paper, we propose PRICE, a PRetrained multI-table CardEst model, which addresses these limitations. PRICE takes low-level but transferable features w.r.t. data distributions and query information and elegantly applies self-attention models to learn meta-knowledge to compute cardinality in any database. It is generally applicable to any unseen new database to attain high estimation accuracy, while its preparation cost is as little as the basic one-dimensional histogram-based CardEst methods. Moreover, PRICE can be finetuned to further enhance its performance on any specific database. We pretrained PRICE using 30 diverse datasets, completing the process in about 5 hours with a resulting model size of only about 40MB. Evaluations show that PRICE consistently outperforms existing methods, achieving the highest estimation accuracy on several unseen databases and generating faster execution plans with lower overhead. After finetuning with a small volume of databasespecific queries, PRICE could even find plans very close to the optimal ones. Meanwhile, PRICE is generally applicable to different settings such as data updates, data scaling, and query workload shifts. We have made all of our data and codes publicly available at https://github.com/StCarmen/PRICE.

Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information. Learning shape priors is crucial for effective amodal completion, but traditional methods often rely on two-stage processes or additional information, leading to inefficiencies and potential error accumulation. To address these shortcomings, we introduce a novel framework named the Hyper-Transformer Amodal Network (H-TAN). This framework utilizes a hyper transformer equipped with a dynamic convolution head to directly learn shape priors and accurately predict amodal masks. Specifically, H-TAN uses a dual-branch structure to extract multi-scale features from both images and masks. The multi-scale features from the image branch guide the hyper transformer in learning shape priors and in generating the weights for dynamic convolution tailored to each instance. The dynamic convolution head then uses the features from the mask branch to predict precise amodal masks. We extensively evaluate our model on three benchmark datasets: KINS, COCOA-cls, and D2SA, where H-TAN demonstrated superior performance compared to existing methods. Additional experiments validate the effectiveness and stability of the novel hyper transformer in our framework.

Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of previous ones. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting since they try to cram diverse knowledge into one fixed model. To overcome this limitation, we introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning. Concretely, we incrementally build distinct adapters to learn domain-specific knowledge at each step, which can effectively learn and preserve knowledge across different datasets. Meanwhile, the proposed auto-selection strategy adaptively calculates the knowledge similarity between the input set and the adapters. On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model. Extensive experiments are conducted to demonstrate the superiority of our AdalReID, which significantly outperforms SOTAs by about 10$\sim$20\% mAP on both seen and unseen domains.

Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a novel approach for compositional 3D asset generation from single images. REPARO employs a two-step process: first, it extracts individual objects from the scene and reconstructs their 3D meshes using off-the-shelf image-to-3D models; then, it optimizes the layout of these meshes through differentiable rendering techniques, ensuring coherent scene composition. By integrating optimal transport-based long-range appearance loss term and high-level semantic loss term in the differentiable rendering, REPARO can effectively recover the layout of 3D assets. The proposed method can significantly enhance object independence, detail accuracy, and overall scene coherence. Extensive evaluation of multi-object scenes demonstrates that our REPARO offers a comprehensive approach to address the complexities of multi-object 3D scene generation from single images.