Search

The stylization of 3D scenes is an increasingly attractive topic in 3D vision. Although image style transfer has been extensively researched with promising results, directly applying 2D style transfer methods to 3D scenes often fails to preserve the structural and multi-view properties of 3D environments, resulting in unpleasant distortions in images from different viewpoints. To address these issues, we leverage the remarkable generative prior of diffusion-based models and propose a novel style transfer method, OSDiffST, based on a pre-trained one-step diffusion model (i.e., SD-Turbo) for rendering diverse styles in multi-view images of 3D scenes. To efficiently adapt the pre-trained model for multi-view style transfer on small datasets, we introduce a vision condition module to extract style information from the reference style image to serve as conditional input for the diffusion model and employ LoRA in diffusion model for adaptation. Additionally, we consider color distribution alignment and structural similarity between the stylized and content images using two specific loss functions. As a result, our method effectively preserves the structural information and multi-view consistency in stylized images without any 3D information. Experiments show that our method surpasses other promising style transfer methods in synthesizing various styles for multi-view images of 3D scenes. Stylized images from different viewpoints generated by our method achieve superior visual quality, with better structural integrity and less distortion. The source code is available at https://github.com/YushenZuo/OSDiffST., Comment: Accepted by ECCV 2024 AI for Visual Arts Workshop and Challenges, 18 pages, 7 figures

In this paper, we investigate the strong gravitational lensing effect around a spherically symmetric regular black hole, whose metric is derived from a non-singular collapsing dust ball model in asymptotically safe gravity. In this regular black hole spacetime, we obtain the analytical expression of the light deflection angle via calculating the strong field limit coefficients, and then evaluate the lensing observables in strong field regime by supposing the regular black holes as the candidate of $M87*$ and $SgrA*$ supermassive black holes, respectively. In addition, we also in detail analyze the effects of the scale parameter $\xi$ on the strong deflection angle and the lensing observables. We expect our results will be useful in the future to distinguish these non-singular black holes from their classical singular counterparts., Comment: 13 pages, 20 figures, Comments are welcome

Superluminal propagation is an intrinsic problem in the diffusion equation and has not been effectively addressed for a long time. In this work, a rigorous solution to this issue is obtained under the assumption that particles undergo a random flight process, where they move isotropically at a constant speed while experiencing random scatterings. We validate this solution by comparing it with comprehensive simulations of the random flight process and find that it significantly deviates from the solution derived from the J\"{u}ttner propagator. This solution is broadly applicable to various diffusion phenomena, such as cosmic-ray propagation. We emphasize that our rigorous solution is particularly crucial in scenarios involving burst-like particle injection, where previous phenomenological approaches to the superluminal diffusion problem may not yield accurate results., Comment: 8 pages, 4 figures

Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. More importantly, text can describe implicit abstract styles, like styles of specific artists or art movements. In this paper, we propose a Contrastive Learning for Artistic Style Transfer (CLAST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a supervised contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel and efficient adaLN based state space models that explore style-content fusion. Finally, we achieve a text-driven image style transfer. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods in artistic style transfer. More importantly, it does not require online fine-tuning and can render a 512x512 image in 0.03s., Comment: 18 pages, 8 figures

Customized Image Generation, generating customized images with user-specified concepts, has raised significant attention due to its creativity and novelty. With impressive progress achieved in subject customization, some pioneer works further explored the customization of action and interaction beyond entity (i.e., human, animal, and object) appearance. However, these approaches only focus on basic actions and interactions between two entities, and their effects are limited by insufficient ''exactly same'' reference images. To extend customized image generation to more complex scenes for general real-world applications, we propose a new task: event-customized image generation. Given a single reference image, we define the ''event'' as all specific actions, poses, relations, or interactions between different entities in the scene. This task aims at accurately capturing the complex event and generating customized images with various target entities. To solve this task, we proposed a novel training-free event customization method: FreeEvent. Specifically, FreeEvent introduces two extra paths alongside the general diffusion denoising process: 1) Entity switching path: it applies cross-attention guidance and regulation for target entity generation. 2) Event transferring path: it injects the spatial feature and self-attention maps from the reference image to the target image for event generation. To further facilitate this new task, we collected two evaluation benchmarks: SWiG-Event and Real-Event. Extensive experiments and ablations have demonstrated the effectiveness of FreeEvent.

Multimodal Industrial Anomaly Detection (MIAD), utilizing 3D point clouds and 2D RGB images to identify the abnormal region of products, plays a crucial role in industrial quality inspection. However, the conventional MIAD setting presupposes that all 2D and 3D modalities are paired, overlooking the fact that multimodal data collected from the real world is often imperfect due to missing modalities. Consequently, MIAD models that demonstrate robustness against modal-incomplete data are highly desirable in practice. To address this practical challenge, we introduce a first-of-its-kind study that comprehensively investigates Modality-Incomplete Industrial Anomaly Detection (MIIAD), to consider the imperfect learning environment in which the multimodal information may be incomplete. Not surprisingly, we discovered that most existing MIAD approaches are inadequate for addressing MIIAD challenges, leading to significant performance degradation on the MIIAD benchmark we developed. In this paper, we propose a novel two-stage Robust modAlity-imcomplete fusing and Detecting frAmewoRk, abbreviated as RADAR. Our bootstrapping philosophy is to enhance two stages in MIIAD, improving the robustness of the Multimodal Transformer: i) In feature fusion, we first explore learning modality-incomplete instruction, guiding the pre-trained Multimodal Transformer to robustly adapt to various modality-incomplete scenarios, and implement adaptive parameter learning based on a HyperNetwork; ii) In anomaly detection, we construct a real-pseudo hybrid module to highlight the distinctiveness of modality combinations, further enhancing the robustness of the MIIAD model. Our experimental results demonstrate that the proposed RADAR significantly surpasses conventional MIAD methods in terms of effectiveness and robustness on our newly created MIIAD dataset, underscoring its practical application value.

Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated multi-modal data construction pipeline that organizes the final generation output into a Python code format. The pipeline leverages the VLM itself to extract cross-modal information via different prompts and filter the generated outputs again via a consistency filtering strategy. Experiments have demonstrated the high quality of W2C by improving various existing visual question answering and visual grounding benchmarks across different VLMs. Further analysis also demonstrates that the new code parsing ability of VLMs presents better cross-modal equivalence than the commonly used detail caption ability. Our code is available at https://github.com/foundation-multimodal-models/World2Code., Comment: Accepted at EMNLP 2024 Main Conference, 16pages

This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This manuscript focuses on the competition set-up, the proposed methods and their respective results. The challenge aims at producing novel camera view synthesis of diverse scenes from sparse image observations. It is composed of two tracks, with differing levels of sparsity; 3 views in Track 1 (very sparse) and 9 views in Track 2 (sparse). Participants are asked to optimise objective fidelity to the ground-truth images as measured via the Peak Signal-to-Noise Ratio (PSNR) metric. For both tracks, we use the newly introduced Sparse Rendering (SpaRe) dataset and the popular DTU MVS dataset. In this challenge, 5 teams submitted final results to Track 1 and 4 teams submitted final results to Track 2. The submitted models are varied and push the boundaries of the current state-of-the-art in sparse neural rendering. A detailed description of all models developed in the challenge is provided in this paper., Comment: Part of Advances in Image Manipulation workshop at ECCV 2024

In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial prerequisite for effortlessly deriving a consistent representation. Nevertheless, this premise is frequently compromised in certain applications, where each view is organized and transmitted independently, resulting in the view-unaligned problem (VuP). Restoring CVC of unaligned multi-view data is a challenging and highly demanding task that has received limited attention from the research community. To tackle this practical challenge, we propose to integrate the permutation derivation procedure into the bipartite graph paradigm for view-unaligned clustering, termed Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection (PAVuC-ATS). Specifically, we learn consistent anchors and view-specific graphs by the bipartite graph, and derive permutations applied to the unaligned graphs by reformulating the alignment between two latent representations as a 2-step transition of a Markov chain with adaptive template selection, thereby achieving the probabilistic alignment. The convergence of the resultant optimization problem is validated both experimentally and theoretically. Extensive experiments on six benchmark datasets demonstrate the superiority of the proposed PAVuC-ATS over the baseline methods., Comment: 12 pages, 6 figures

The rapid evolution of Multimodal Large Language Models (MLLMs) has brought substantial advancements in artificial intelligence, significantly enhancing the capability to understand and generate multimodal content. While prior studies have largely concentrated on model architectures and training methodologies, a thorough analysis of the benchmarks used for evaluating these models remains underexplored. This survey addresses this gap by systematically reviewing 211 benchmarks that assess MLLMs across four core domains: understanding, reasoning, generation, and application. We provide a detailed analysis of task designs, evaluation metrics, and dataset constructions, across diverse modalities. We hope that this survey will contribute to the ongoing advancement of MLLM research by offering a comprehensive overview of benchmarking practices and identifying promising directions for future work. An associated GitHub repository collecting the latest papers is available., Comment: Ongoing project

In this paper, we investigate the gravitational lensing effect and the shadow around a Schwarzschild-like black hole in metric-affine bumblebee gravity, which leads to the Lorentz symmetry breaking. We first present a generalized formalism for calculating higher-order corrections to light weak bending angle in a static, spherically symmetric and not asymptotically flat spacetime, and then applying this general formalism to the metric-affine bumblebee gravity. Moreover, we derive the light deflection angle and the size of the Einstein ring within the weak field in this scenario. In addition, we analyze the black hole shadow in this theory framework. By using observational data from the Einstein's ring of the galaxy ESO325-G004 and the black hole shadow of the ${\rm M}87$ galaxy, we estimate the upper bounds of the Lorentz symmetry breaking coefficient $\ell$, respectively., Comment: 12 pages, 4 figures, Accepted for publication in European Physical Journal C

The recently discovered stellar system, Ursa Major III/UNIONS 1, may be the faintest and densest dwarf spheroidal satellite galaxy of the Milky Way. Owing to its close proximity and substantial dark matter (DM) component, Ursa Major III emerges as a highly promising target for DM indirect detection. It is known that electrons and positrons originating from DM annihilation can generate a broad radio spectrum through the processes of synchrotron radiation and inverse Compton scattering within galaxies. In this study, we investigate the potential of the Square Kilometre Array (SKA) in detecting radio signatures arising from DM annihilation in Ursa Major III over a 100 hour observation period. Our analysis indicates that the SKA has strong capabilities in detecting these signatures. For instance, the SKA sensitivity to the DM annihilation cross section is estimated to reach $\mathcal{O}(10^{-30})-\mathcal{O}(10^{-28})\; \rm cm^{3} s^{-1}$ in the DM mass range from several GeV to $\sim100$ GeV for the $e^+e^-$ and $\mu^+\mu^-$ annihilation channels. The precise results are significantly influenced by various astrophysical factors, such as the strength of magnetic field, the diffusion coefficient, and the DM density profile in the dwarf galaxy. We discuss the impact of the uncertainties associated with these factors, and find that the SKA sensitivities have the potential to surpass the current constraints, even when considering these uncertainties., Comment: 20 pages, 6 figures

Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization with the help of salient information identified by the extractive model. Previous works that adopt this paradigm train the extractor and abstractor separately and introduce extra parameters to highlight the extracted salients to the abstractor, which results in error accumulation and additional training costs. In this paper, we first introduce a parameter-free highlight method into the encoder-decoder framework: replacing the encoder attention mask with a saliency mask in the cross-attention module to force the decoder to focus only on salient parts of the input. A preliminary analysis compares different highlight methods, demonstrating the effectiveness of our saliency mask. We further propose the novel extract-and-abstract paradigm, ExtAbs, which jointly and seamlessly performs Extractive and Abstractive summarization tasks within single encoder-decoder model to reduce error accumulation. In ExtAbs, the vanilla encoder is augmented to extract salients, and the vanilla decoder is modified with the proposed saliency mask to generate summaries. Built upon BART and PEGASUS, experiments on three datasets show that ExtAbs can achieve superior performance than baselines on the extractive task and performs comparable, or even better than the vanilla models on the abstractive task.

The recent AMS-02 measurements of cosmic-ray (CR) deuteron fluxes suggest the presence of primary deuterons in quantities far exceeding predictions from Big Bang nucleosynthesis. This poses a significant challenge to modern astrophysics, as no known processes can account for such large amounts of deuterons without violating existing constraints~\cite{Epstein:1976hq}. In contrast, it is recently proposed that the AMS-02 measurements can be explained by a purely secondary origin when contributions from heavier nuclei are considered. In this study, we recalculate the secondary deuteron flux using production cross sections updated with the latest collider data. We find that some of the deuteron production cross sections are overestimated in the widely-used calculation tools for CR propagation, and a primary deuteron component is still necessary. We then propose a novel process for generating primary deuterons at CR sources through a fusion mechanism, which is naturally unique to deuterons. This model could explain the observed deuteron excess while maintaining consistency with other CR measurements., Comment: 8 pages, 8 figures

In recent years, Multi-Modality Image Fusion (MMIF) has been applied to many fields, which has attracted many scholars to endeavour to improve the fusion performance. However, the prevailing focus has predominantly been on the architecture design, rather than the training strategies. As a low-level vision task, image fusion is supposed to quickly deliver output images for observation and supporting downstream tasks. Thus, superfluous computational and storage overheads should be avoided. In this work, a lightweight Distilled Mini-Model with a Dynamic Refresh strategy (MMDRFuse) is proposed to achieve this objective. To pursue model parsimony, an extremely small convolutional network with a total of 113 trainable parameters (0.44 KB) is obtained by three carefully designed supervisions. First, digestible distillation is constructed by emphasising external spatial feature consistency, delivering soft supervision with balanced details and saliency for the target network. Second, we develop a comprehensive loss to balance the pixel, gradient, and perception clues from the source images. Third, an innovative dynamic refresh training strategy is used to collaborate history parameters and current supervision during training, together with an adaptive adjust function to optimise the fusion network. Extensive experiments on several public datasets demonstrate that our method exhibits promising advantages in terms of model efficiency and complexity, with superior performance in multiple image fusion tasks and downstream pedestrian detection application. The code of this work is publicly available at https://github.com/yanglinDeng/MMDRFuse., Comment: 10 pages, 8 figures, accpeted by ACM International Conference on Multimedia 2024(Oral)

Recent advancements in the collection and analysis of sequential educational data have brought time series analysis to a pivotal position in educational research, highlighting its essential role in facilitating data-driven decision-making. However, there is a lack of comprehensive summaries that consolidate these advancements. To the best of our knowledge, this paper is the first to provide a comprehensive review of time series analysis techniques specifically within the educational context. We begin by exploring the landscape of educational data analytics, categorizing various data sources and types relevant to education. We then review four prominent time series methods-forecasting, classification, clustering, and anomaly detection-illustrating their specific application points in educational settings. Subsequently, we present a range of educational scenarios and applications, focusing on how these methods are employed to address diverse educational tasks, which highlights the practical integration of multiple time series methods to solve complex educational problems. Finally, we conclude with a discussion on future directions, including personalized learning analytics, multimodal data fusion, and the role of large language models (LLMs) in educational time series. The contributions of this paper include a detailed taxonomy of educational data, a synthesis of time series techniques with specific educational applications, and a forward-looking perspective on emerging trends and future research opportunities in educational analysis. The related papers and resources are available and regularly updated at the project page., Comment: 24 pages, 3 figures, 6 tables, project page: see https://github.com/ai-for-edu/time-series-analysis-for-education

Observations of the velocity dispersion indicate a severe dark matter (DM) deficit in the ultra-diffuse galaxy, NGC1052-DF4 (DF4). The ultra-deep images obtained with the Gemini telescope, which has the deepest imaging data till now, confirm the presence of tidal tails in DF4, suggesting its tidal formation. To enhance tidal effects, we consider the self-interaction among DM particles. Using an N-body simulation in the scenario of self-interacting dark matter (SIDM), we reproduce a DM-deficient galaxy that is consistent with all observational data of DF4. Specifically, our simulation result yields an extremely low DM-to-star mass ratio and a radial surface brightness profile very similar to that from deep images, showing accurate tidal features. By performing simulations with similar tidal effects and various cross-sections of SIDM, we show a significant impact of SIDM on the DM-to-star mass ratio in the central region of the galaxy. Our work confirms the tidal formation of DF4 in theory., Comment: 9 pages, 6 figures

The interaction between axion-like particles (ALPs) and photons induces ALP-photon oscillations in astrophysical magnetic fields, leading to spectral distortions in the $\gamma$-ray spectrum of blazars. The primary uncertainty of this phenomenon may originate from the magnetic field within the jet of the blazar. While many studies have explored the effects of ALP-photon oscillations using typical values for jet magnetic field parameters, it is important to recognize that these parameters can be constrained by multi-wavelength observations. In this study, we utilize the high energy $\gamma$-ray spectrum of Mrk 421 obtained from MAGIC and Fermi-LAT observations. By employing multi-wavelength fitting with a one-zone synchrotron self-Compton model, we derive the parameters characterizing the magnetic field model within the jet, and investigate their impacts on the ALP constraints., Comment: 9 pages, 7 figures

Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification of the covariance matrices by applying matrix function normalization, such as matrix logarithm or power, followed by a Euclidean classifier. However, covariance matrices inherently lie in a Riemannian manifold, known as the Symmetric Positive Definite (SPD) manifold. The current literature does not provide a satisfactory explanation of why Euclidean classifiers can be applied directly to Riemannian features after the normalization of the matrix power. To mitigate this gap, this paper provides a comprehensive and unified understanding of the matrix logarithm and power from a Riemannian geometry perspective. The underlying mechanism of matrix functions in GCP is interpreted from two perspectives: one based on tangent classifiers (Euclidean classifiers on the tangent space) and the other based on Riemannian classifiers. Via theoretical analysis and empirical validation through extensive experiments on fine-grained and large-scale visual classification datasets, we conclude that the working mechanism of the matrix functions should be attributed to the Riemannian classifiers they implicitly respect., Comment: 24 pages, 3 figures

Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-structure representation based on panoptic segmentation masks. Despite remarkable progress in PSG, almost all existing methods neglect the importance of shape-aware features, which inherently focus on the contours and boundaries of objects. To bridge this gap, we propose a model-agnostic Curricular shApe-aware FEature (CAFE) learning strategy for PSG. Specifically, we incorporate shape-aware features (i.e., mask features and boundary features) into PSG, moving beyond reliance solely on bbox features. Furthermore, drawing inspiration from human cognition, we propose to integrate shape-aware features in an easy-to-hard manner. To achieve this, we categorize the predicates into three groups based on cognition learning difficulty and correspondingly divide the training process into three stages. Each stage utilizes a specialized relation classifier to distinguish specific groups of predicates. As the learning difficulty of predicates increases, these classifiers are equipped with features of ascending complexity. We also incorporate knowledge distillation to retain knowledge acquired in earlier stages. Due to its model-agnostic nature, CAFE can be seamlessly incorporated into any PSG model. Extensive experiments and ablations on two PSG tasks under both robust and zero-shot PSG have attested to the superiority and robustness of our proposed CAFE, which outperforms existing state-of-the-art methods by a large margin., Comment: Accepted by IJCV

Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions composed of previously observed verbs and objects, thus requiring so-called compositional generalization ability. To facilitate this research, we propose a novel Zero-Shot Compositional Action Recognition (ZS-CAR) task. For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset. We also propose a novel Component-to-Composition (C2C) learning method to solve the new ZS-CAR task. C2C includes an independent component learning module and a composition inference module. Last, we devise an enhanced training strategy to address the challenges of component variations between seen and unseen compositions and to handle the subtle balance between learning seen and unseen actions. The experimental results demonstrate that the proposed framework significantly surpasses the existing compositional generalization methods and sets a new state-of-the-art. The new Sth-com benchmark and code are available at https://github.com/RongchangLi/ZSCAR_C2C., Comment: Accepted by ECCV2024

The waveguide-integrated metasurface introduces a novel photonic chip capable of converting guided modes into free-space light. This enables functions such as off-chip beam focusing, steering, and imaging. The challenge lies in achieving hypermultiplexing across diverse parameters, including guided-wave mode type, direction, polarization, and notably, multiple wavelengths. Here, we introduce a comprehensive end-to-end inverse design framework, rooted in a physical model, for the multifunctional design of on-chip metasurfaces. This framework allows for metasurface optimization through a target-field-driven iteration process. We demonstrate a hypermultiplexed on-chip metasurface capable of generating red-green-blue holograms at multiple target planes, with both independent and cooperative control over guided-wave direction. Significantly, the proposed method streamlines the design process utilizing only the positions of meta-atoms as the design variable. We demonstrate 9 independent holographic channels through a combination of wavelength and distance multiplexing. Moreover, by incorporating the excitation direction into the design, the metasurface produces a total of 36 distinct holograms. The robustness of these results against fabrication discrepancies is validated through 3D full-wave electromagnetic simulations, aligning well with advanced manufacturing techniques. Our research presents a universal design framework for the development of multifunctional on-chip metasurfaces, opening up new avenues for a wide range of applications.

This paper presents two new metrics on the Symmetric Positive Definite (SPD) manifold via the Cholesky manifold, i.e., the space of lower triangular matrices with positive diagonal elements. We first unveil that the existing popular Riemannian metric on the Cholesky manifold can be generally characterized as the product metric of a Euclidean metric and a Riemannian metric on the space of n-dimensional positive vectors. Based on this analysis, we propose two novel metrics on the Cholesky manifolds, i.e., Diagonal Power Euclidean Metric and Diagonal Generalized Bures-Wasserstein Metric, which are numerically stabler than the existing Cholesky metric. We also discuss the gyro structures and deformed metrics associated with our metrics. The gyro structures connect the linear and geometric properties, while the deformed metrics interpolate between our proposed metrics and the existing metric. Further, by Cholesky decomposition, the proposed deformed metrics and gyro structures are pulled back to SPD manifolds. Compared with existing Riemannian metrics on SPD manifolds, our metrics are easy to use, computationally efficient, and numerically stable., Comment: 25 pages, 1 figures

The recently discovered satellite dwarf galaxy Ursa Major III provides a promising opportunity to explore the signatures resulting from dark matter (DM) annihilation, due to its proximity and large J-factor. Owing to the absence of an excess of $\gamma$-ray signatures originating from Ursa Major III, observations of $\gamma$-rays, such as those from Fermi-LAT, can be utilized to set constraints on the DM annihilation cross section. In this study, we determine the DM density profile, and consider the relationship between DM density and velocity dispersion at different locations within Ursa Major III through Jeans analysis. We calculate the J-factor of Ursa Major III for s-wave annihilation, along with the effective J-factors for p-wave and Sommerfeld enhanced annihilation scenarios. Utilizing these derived J-factors, we set stringent constraints on DM annihilation cross sections in three scenarios. Given the substantial impact of member star identification on the J-factor of Ursa Major III, we further calculate J-factors with the condition of excluding the largest velocity outlier. Our analysis reveals a notable reduction in the median value and an increase in the deviation of J-factors, thereby leading to considerably weaker constraints.

With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of video diffusion models (VDMs) generate long videos in an autoregressive manner, i.e., generating subsequent clips conditioned on last frames of previous clip. However, existing approaches all involve bidirectional computations, which restricts the receptive context of each autoregression step, and results in the model lacking long-term dependencies. Inspired from the huge success of large language models (LLMs) and following GPT (generative pre-trained transformer), we bring causal (i.e., unidirectional) generation into VDMs, and use past frames as prompt to generate future frames. For Causal Generation, we introduce causal temporal attention into VDM, which forces each generated frame to depend on its previous frames. For Frame as Prompt, we inject the conditional frames by concatenating them with noisy frames (frames to be generated) along the temporal axis. Consequently, we present Video Diffusion GPT (ViD-GPT). Based on the two key designs, in each autoregression step, it is able to acquire long-term context from prompting frames concatenated by all previously generated frames. Additionally, we bring the kv-cache mechanism to VDMs, which eliminates the redundant computation from overlapped frames, significantly boosting the inference speed. Extensive experiments demonstrate that our ViD-GPT achieves state-of-the-art performance both quantitatively and qualitatively on long video generation. Code will be available at https://github.com/Dawn-LX/Causal-VideoGen., Comment: Code will be available at https://github.com/Dawn-LX/Causal-VideoGen

As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous deep-learning-based methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature., Comment: 13 pages, 12 figures, journal

Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially for infrared and visible images which contain big similarity gap between these two modalities. The common cross attention modules only consider the correlation, on the contrary, image fusion tasks need focus on complementarity (uncorrelation). Hence, in this paper, a novel cross attention mechanism (CAM) is proposed to enhance the complementary information. Furthermore, a two-stage training strategy based fusion scheme is presented to generate the fused images. For the first stage, two auto-encoder networks with same architecture are trained for each modality. Then, with the fixed encoders, the CAM and a decoder are trained in the second stage. With the trained CAM, features extracted from two modalities are integrated into one fused feature in which the complementary information is enhanced and the redundant features are reduced. Finally, the fused image can be generated by the trained decoder. The experimental results illustrate that our proposed fusion method obtains the SOTA fusion performance compared with the existing fusion networks. The codes are available at https://github.com/hli1221/CrossFuse, Comment: 11 pages, 16 fuigures

Continuous diffusion models have demonstrated their effectiveness in addressing the inherent uncertainty and indeterminacy in monocular 3D human pose estimation (HPE). Despite their strengths, the need for large search spaces and the corresponding demand for substantial training data make these models prone to generating biomechanically unrealistic poses. This challenge is particularly noticeable in occlusion scenarios, where the complexity of inferring 3D structures from 2D images intensifies. In response to these limitations, we introduce the Discrete Diffusion Pose ($\text{Di}^2\text{Pose}$), a novel framework designed for occluded 3D HPE that capitalizes on the benefits of a discrete diffusion model. Specifically, $\text{Di}^2\text{Pose}$ employs a two-stage process: it first converts 3D poses into a discrete representation through a \emph{pose quantization step}, which is subsequently modeled in latent space through a \emph{discrete diffusion process}. This methodological innovation restrictively confines the search space towards physically viable configurations and enhances the model's capability to comprehend how occlusions affect human pose within the latent space. Extensive evaluations conducted on various benchmarks (e.g., Human3.6M, 3DPW, and 3DPW-Occ) have demonstrated its effectiveness.

Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.

With the advance of diffusion models, various personalized image generation methods have been proposed. However, almost all existing work only focuses on either subject-driven or style-driven personalization. Meanwhile, state-of-the-art methods face several challenges in realizing compositional personalization, i.e., composing different subject and style concepts, such as concept disentanglement, unified reconstruction paradigm, and insufficient training data. To address these issues, we introduce FreeTuner, a flexible and training-free method for compositional personalization that can generate any user-provided subject in any user-provided style (see Figure 1). Our approach employs a disentanglement strategy that separates the generation process into two stages to effectively mitigate concept entanglement. FreeTuner leverages the intermediate features within the diffusion model for subject concept representation and introduces style guidance to align the synthesized images with the style concept, ensuring the preservation of both the subject's structure and the style's aesthetic features. Extensive experiments have demonstrated the generation ability of FreeTuner across various personalization settings.

On-chip integrated metasurface driven by in-plane guided waves is of great interests in various light field manipulation applications such as colorful augmented reality and holographic display. However, it remains a challenge to design colorful multichannel holography by a single on-chip metasurface. Here we present metasurfaces integrated on top of guided-wave photonic slab that achieves multi-channel colorful holographic light display. An end-to-end scheme is used to inverse design the metasurface for projecting off-chip preset multiple patterns. Particular examples are presented for customized patterns that were encoded into the metasurface with a single-cell meta-atom, working simultaneously at RGB color channels and for several different diffractive distance, with polarization dependence. Holographic images are generated at 18 independent channels with such a single-cell metasurface. The proposed design scheme is easy to implement and the resulting device is viable to fabrication, promising a plenty of applications in nanophotonics., Comment: 18 pages and 11 figures

There is currently strong interest in improving visual object tracking by augmenting the RGB modality with the output of a visual event camera that is particularly informative about the scene motion. However, existing approaches perform event feature extraction for RGB-E tracking using traditional appearance models, which have been optimised for RGB only tracking, without adapting it for the intrinsic characteristics of the event data. To address this problem, we propose an Event backbone (Pooler), designed to obtain a high-quality feature representation that is cognisant of the innate characteristics of the event data, namely its sparsity. In particular, Multi-Scale Pooling is introduced to capture all the motion feature trends within event data through the utilisation of diverse pooling kernel sizes. The association between the derived RGB and event representations is established by an innovative module performing adaptive Mutually Guided Fusion (MGF). Extensive experimental results show that our method significantly outperforms state-of-the-art trackers on two widely used RGB-E tracking datasets, including VisEvent and COESOT, where the precision and success rates on COESOT are improved by 4.9% and 5.2%, respectively. Our code will be available at https://github.com/SSSpc333/TENet.

The significance of network structures in promoting group cooperation within social dilemmas has been widely recognized. Prior studies attribute this facilitation to the assortment of strategies driven by spatial interactions. Although reinforcement learning has been employed to investigate the impact of dynamic interaction on the evolution of cooperation, there remains a lack of understanding about how agents develop neighbour selection behaviours and the formation of strategic assortment within an explicit interaction structure. To address this, our study introduces a computational framework based on multi-agent reinforcement learning in the spatial Prisoner's Dilemma game. This framework allows agents to select dilemma strategies and interacting neighbours based on their long-term experiences, differing from existing research that relies on preset social norms or external incentives. By modelling each agent using two distinct Q-networks, we disentangle the coevolutionary dynamics between cooperation and interaction. The results indicate that long-term experience enables agents to develop the ability to identify non-cooperative neighbours and exhibit a preference for interaction with cooperative ones. This emergent self-organizing behaviour leads to the clustering of agents with similar strategies, thereby increasing network reciprocity and enhancing group cooperation., Comment: Accepted at IJCAI 2024 (33rd International Joint Conference on Artificial Intelligence - Jeju)

Second-order topological insulators can be characterized by their bulk polarization, which is believed to be intrinsically connected to the center of the Wannier function. In this study, we demonstrate the existence of second-order topological insulators that feature a pair of partially degenerate photonic bands. These arise from the nonsymmorphic glide symmetry in an all-dielectric photonic crystal. The center of the maximally localized Wannier function (MLWF) is consistently located at the origin but is not equivalent with respect to the sum of constituent polarizations. As a result, topological corner modes can be identified by the distinctly hybridized MLWFs that truncate at the sample boundary. Through full-wave numerical simulations paired with microwave experiments, the second-order topology is clearly confirmed and characterized. These topological corner states exhibit notably unique modal symmetries, which are made possible by the inversion of the Wannier bands. Our results provide an alternative approach to explore higher-order topological physics with significant potential for applications in integrated and quantum photonics.

RGBT tracking draws increasing attention due to its robustness in multi-modality warranting (MMW) scenarios, such as nighttime and bad weather, where relying on a single sensing modality fails to ensure stable tracking results. However, the existing benchmarks predominantly consist of videos collected in common scenarios where both RGB and thermal infrared (TIR) information are of sufficient quality. This makes the data unrepresentative of severe imaging conditions, leading to tracking failures in MMW scenarios. To bridge this gap, we present a new benchmark, MV-RGBT, captured specifically in MMW scenarios. In contrast with the existing datasets, MV-RGBT comprises more object categories and scenes, providing a diverse and challenging benchmark. Furthermore, for severe imaging conditions of MMW scenarios, a new problem is posed, namely \textit{when to fuse}, to stimulate the development of fusion strategies for such data. We propose a new method based on a mixture of experts, namely MoETrack, as a baseline fusion strategy. In MoETrack, each expert generates independent tracking results along with the corresponding confidence score, which is used to control the fusion process. Extensive experimental results demonstrate the significant potential of MV-RGBT in advancing RGBT tracking and elicit the conclusion that fusion is not always beneficial, especially in MMW scenarios. Significantly, the proposed MoETrack method achieves new state-of-the-art results not only on MV-RGBT, but also on standard benchmarks, such as RGBT234, LasHeR, and the short-term split of VTUAV (VTUAV-ST). More information of MV-RGBT and the source code of MoETrack will be released at https://github.com/Zhangyong-Tang/MoETrack.

Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network, referred to as IGPN. The main innovations include: Our method incorporates a region-awareness pooling strategy based on structural partitioning. The correlation matrix of the original feature is used to adaptively adjust the weight of information in different regions of the newly generated features, resulting in more flexible and effective processing. To prevent the irreversible loss of discriminative information, we propose a cross fusion module and an information supplement module to provide block-level and input-level information respectively. As a plug-and-play structure, the proposed operation can be seamlessly combined with existing GCN-based models. We conducted extensive evaluations on several challenging benchmarks, and the experimental results indicate the effectiveness of our proposed solutions. For example, in the cross-subject evaluation of the NTU-RGB+D 60 dataset, IGPN achieves a significant improvement in accuracy compared to the baseline while reducing Flops by nearly 70%; a heavier version has also been introduced to further boost accuracy.

Audio-driven visual scene editing endeavors to manipulate the visual background while leaving the foreground content unchanged, according to the given audio signals. Unlike current efforts focusing primarily on image editing, audio-driven video scene editing has not been extensively addressed. In this paper, we introduce AudioScenic, an audio-driven framework designed for video scene editing. AudioScenic integrates audio semantics into the visual scene through a temporal-aware audio semantic injection process. As our focus is on background editing, we further introduce a SceneMasker module, which maintains the integrity of the foreground content during the editing process. AudioScenic exploits the inherent properties of audio, namely, audio magnitude and frequency, to guide the editing process, aiming to control the temporal dynamics and enhance the temporal consistency. First, we present an audio Magnitude Modulator module that adjusts the temporal dynamics of the scene in response to changes in audio magnitude, enhancing the visual dynamics. Second, the audio Frequency Fuser module is designed to ensure temporal consistency by aligning the frequency of the audio with the dynamics of the video scenes, thus improving the overall temporal coherence of the edited videos. These integrated features enable AudioScenic to not only enhance visual diversity but also maintain temporal consistency throughout the video. We present a new metric named temporal score for more comprehensive validation of temporal consistency. We demonstrate substantial advancements of AudioScenic over competing methods on DAVIS and Audioset datasets.

Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this stability often results in fluctuations in kinematic states, leading to inconsistent predictions and the amplification of errors. In this study, we introduce a framework called Multi-Agent Trajectory prediction via neural interaction Energy (MATE). This framework assesses the interactive motion of agents by employing neural interaction energy, which captures the dynamics of interactions and illustrates their influence on the future trajectories of agents. To bolster temporal stability, we introduce two constraints: inter-agent interaction constraint and intra-agent motion constraint. These constraints work together to ensure temporal stability at both the system and agent levels, effectively mitigating prediction fluctuations inherent in multi-agent systems. Comparative evaluations against previous methods on four diverse datasets highlight the superior prediction accuracy and generalization capabilities of our model.

Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires the model not only to classify salient activity (verb) in the image, but also to detect all semantic roles that participate in the action. This complex task usually involves three steps: verb recognition, semantic role grounding, and noun recognition. Directly employing class-based prompts with VLMs and grounding models for this task suffers from several limitations, e.g., it struggles to distinguish ambiguous verb concepts, accurately localize roles with fixed verb-centric template1 input, and achieve context-aware noun predictions. In this paper, we argue that these limitations stem from the mode's poor understanding of verb/noun classes. To this end, we introduce a new approach for zero-shot GSR via Language EXplainer (LEX), which significantly boosts the model's comprehensive capabilities through three explainers: 1) verb explainer, which generates general verb-centric descriptions to enhance the discriminability of different verb classes; 2) grounding explainer, which rephrases verb-centric templates for clearer understanding, thereby enhancing precise semantic role localization; and 3) noun explainer, which creates scene-specific noun descriptions to ensure context-aware noun recognition. By equipping each step of the GSR process with an auxiliary explainer, LEX facilitates complex scene understanding in real-world scenarios. Our extensive validations on the SWiG dataset demonstrate LEX's effectiveness and interoperability in zero-shot GSR.

Leveraging generative retrieval (GR) techniques to enhance search systems is an emerging methodology that has shown promising results in recent years. In GR, a text-to-text model maps string queries directly to relevant document identifiers (docIDs), dramatically simplifying the retrieval process. However, when applying most GR models in large-scale E-commerce for personalized item search, we must face two key problems in encoding and decoding. (1) Existing docID generation methods ignore the encoding of efficiency information, which is critical in E-commerce. (2) The positional information is important in decoding docIDs, while prior studies have not adequately discriminated the significance of positional information or well exploited the inherent interrelation among these positions. To overcome these problems, we introduce an efficient Hierarchical encoding-decoding Generative retrieval method (Hi-Gen) for large-scale personalized E-commerce search systems. Specifically, we first design a representation learning model using metric learning to learn discriminative feature representations of items to capture semantic relevance and efficiency information. Then, we propose a category-guided hierarchical clustering scheme that makes full use of the semantic and efficiency information of items to facilitate docID generation. Finally, we design a position-aware loss to discriminate the importance of positions and mine the inherent interrelation between different tokens at the same position. This loss boosts the performance of the language model used in the decoding stage. Besides, we propose two variants of Hi-Gen (Hi-Gen-I2I and Hi-Gen-Cluster) to support online real-time large-scale recall in the online serving process. Hi-Gen gets 3.30% and 4.62% improvements over SOTA for Recall@1 on the public and industry datasets, respectively., Comment: Accepted by ICDM 2024

Spin-mechanical coupling is vital in diverse fields including spintronics, sensing and quantum transduction. Two-dimensional (2D) magnetic materials provide a unique platform for investigating spin-mechanical coupling, attributed to their mechanical flexibility and novel spin orderings. However, studying spin-mechanical coupling in 2D magnets presents challenges in probing mechanical deformation and thermodynamic properties change at nanoscale. Here we use nano opto-electro-mechanical interferometry to mechanically detect the phase transition and magnetostriction effect in multilayer CrSBr, an air-stable antiferromagnets with large magnon-exciton coupling. The transitions among antiferromagnetism, spin-canted ferromagnetism and paramagnetism are visualized by optomechanical frequency anomalies. Nontrivial magnetostriction coefficient 2.3x10^(-5) and magnetoelastic coupling strength on the order of 10^6 J/m^3 have been found. Moreover, we demonstrate the substantial tunability of the magnetoelastic constant by nearly 50% via gate-induced strain. Our findings demonstrate the strong spin-mechanical coupling in CrSBr and paves the way for developing sensitive magnetic sensing and efficient quantum transduction at atomically thin limit.

In recent astronomical observations, an almost dark galaxy, designated as Nube, has unveiled an intriguing anomaly in its stellar distribution. Specifically, Nube exhibits an exceptionally low central brightness, with the 2D half-light radius of its stars far exceeding the typical values found in dwarf galaxies, and even surpassing those observed in ultra-diffuse galaxies (UDGs). This phenomenon is difficult to explain within the framework of cold dark matter (CDM). Meanwhile, due to its ultralight particle mass, fuzzy dark matter (FDM) exhibits a de Broglie wavelength on the order of kiloparsecs under the typical velocities of galaxies. The interference between different modes of the FDM wave gives rise to fluctuations in the gravitational field, which can lead to the dynamical heating of stars within galaxies, resulting in an expansion of their spatial distribution. In this paper, we aim to interpret the anomalous stellar distribution observed in Nube as a consequence of the dynamical heating effect induced by FDM. Our findings suggest that a FDM particle mass around $1-2\times 10^{-23}$ eV can effectively account for this anomaly. And we propose that the FDM dynamical heating effect provides a new insight into understanding the formation of field UDGs., Comment: 13 pages, 4 figures

Human motion prediction is consisting in forecasting future body poses from historically observed sequences. It is a longstanding challenge due to motion's complex dynamics and uncertainty. Existing methods focus on building up complicated neural networks to model the motion dynamics. The predicted results are required to be strictly similar to the training samples with L2 loss in current training pipeline. However, little attention has been paid to the uncertainty property which is crucial to the prediction task. We argue that the recorded motion in training data could be an observation of possible future, rather than a predetermined result. In addition, existing works calculate the predicted error on each future frame equally during training, while recent work indicated that different frames could play different roles. In this work, a novel computationally efficient encoder-decoder model with uncertainty consideration is proposed, which could learn proper characteristics for future frames by a dynamic function. Experimental results on benchmark datasets demonstrate that our uncertainty consideration approach has obvious advantages both in quantity and quality. Moreover, the proposed method could produce motion sequences with much better quality that avoids the intractable shaking artefacts. We believe our work could provide a novel perspective to consider the uncertainty quality for the general motion prediction task and encourage the studies in this field. The code will be available in https://github.com/Motionpre/Adaptive-Salient-Loss-SAGGB., Comment: Accepted by AAAI2024

Recently LHAASO Collaboration gives precise measurements of cosmic rays (CR) all particle energy spectrum and mean logarithmic mass $\left \langle \ln A \right \rangle$ from 0.3 PeV to 30 PeV. Combining the CR measurements by AMS-02 and DAMPE in space and that by LHAASO and Auger on the ground we construct a model to recover all these measurements from tens of GeV to tens of EeV. We find the LHAASO measurement is crucial in the model construction by connecting the Galactic component to the extragalactic component. The precise measurements of CR spectra for individual species by AMS-02 and DAMPE together with the newest LHAASO results clearly indicates three Galactic CR components, that is, a soft low energy background, a hard high energy component, and a local source contribution. However, the LHAASO data show that above $\sim 10^{16}$ eV a nonnegligible extragalactic component must be included. Combining the Auger results and the LHAASO results we figure out the extragalactic CRs which need at least two components at lower and higher energies. Thanks to the precise measurements by LHAASO the constraints on the model parameters are quite stringent. The spectra features and mass measurements in all energy range are all well reproduced in the model., Comment: 11 pages, 2 figures, 4 tables

Observations have revealed a significant dark matter deficit in the ultra-diffuse galaxy NGC1052-DF2 (DF2). It is widely accepted that the formation of this unique galaxy can be attributed to the tidal stripping of its host galaxy, NGC1052. In this study, we simulate the evolution of a satellite system containing globular clusters (GCs) within an accreting host halo in the framework of self-interacting dark matter (SIDM). Our simulation results suggest that the heightened tidal stripping resulting from DM self-interactions can give rise to the transformation of a conventional dwarf galaxy into a dark matter deficit galaxy resembling DF2. By comparing the simulation results with identical initial conditions in both the standard cold dark matter (CDM) and SIDM models, we find that the latter is more likely to replicate the properties of DF2. Furthermore, we demonstrate that a DF2 analog can also be produced on an orbit with a greater pericenter distance by increasing the strength of DM self-interactions. This suggests that the issue of extreme orbital parameters can be mitigated by implementing the SIDM model. The distributions of the GC population derived in our SIDM simulation are consistent with the observed characteristics of DF2. For comparison, we also explored the potential for achieving GC distributions in the context of CDM., Comment: 12 pages, 7 figures

Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting accuracy inconsistencies across varied data subpopulations. This unfairness is largely attributed to bias in data, where some spurious attributes (e.g., Male) statistically correlate with the target attribute (e.g., Smiling). Most of existing fairness-aware methods rely on the labels of spurious attributes, which may be unavailable in practice. This work proposes a novel, generation-based two-stage framework to train a fair FAC model on biased data without additional annotation. Initially, we identify the potential spurious attributes based on generative models. Notably, it enhances interpretability by explicitly showing the spurious attributes in image space. Following this, for each image, we first edit the spurious attributes with a random degree sampled from a uniform distribution, while keeping target attribute unchanged. Then we train a fair FAC model by fostering model invariance to these augmentation. Extensive experiments on three common datasets demonstrate the effectiveness of our method in promoting fairness in FAC without compromising accuracy. Codes are in https://github.com/heqianpei/DiGA., Comment: CVPR 2024