Search

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a novel training framework aimed at UNifying Image and Text recognition within a single model. Starting with a vision encoder pre-trained with image recognition tasks, UNIT introduces a lightweight language decoder for predicting text outputs and a lightweight vision decoder to prevent catastrophic forgetting of the original image encoding capabilities. The training process comprises two stages: intra-scale pretraining and inter-scale finetuning. During intra-scale pretraining, UNIT learns unified representations from multi-scale inputs, where images and documents are at their commonly used resolution, to enable fundamental recognition capability. In the inter-scale finetuning stage, the model introduces scale-exchanged data, featuring images and documents at resolutions different from the most commonly used ones, to enhance its scale robustness. Notably, UNIT retains the original vision encoder architecture, making it cost-free in terms of inference and deployment. Experiments across multiple benchmarks confirm that our method significantly outperforms existing methods on document-related tasks (e.g., OCR and DocQA) while maintaining the performances on natural images, demonstrating its ability to substantially enhance text recognition without compromising its core image recognition capabilities.

The rapid advancement in large language models (LLMs) comes with a significant increase in their parameter size, presenting challenges for adaptation and fine-tuning. Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt LLMs for downstream tasks efficiently. In this paper, we propose Singular Values and Orthonormal Regularized Singular Vectors Adaptation, or SORSA, a novel PEFT method. We introduce a method to analyze the variation of the parameters by performing singular value decomposition (SVD) on weights and discuss SORSA's superiority in minimizing the deviation from the pre-trained weight. Each SORSA layer consists of two main parts: trainable principle singular weights $W_p = U_p \Sigma_p V^\top_p$, and frozen residual weights $W_r = U_r \Sigma_r V^\top_r$. These parts are initialized by performing SVD on pre-trained weights. Moreover, we implement an orthonormal regularizer and analyze its importance by performing gradient analysis. The analysis shows that the regularizer could effectively transfer the scaling information into $\Sigma_p$, which ensures the parameter updating of SORSA layers is evenly and minimized on $U_p$ and $V^\top_p$. SORSA layers could be merged during inference, thus eliminating inference latency. After all, SORSA shows a faster convergence speed than PiSSA and LoRA in our experiments. On the MATH benchmark, Llama 2 7B adapted using SORSA achieved 10.36% accuracy, outperforming LoRA (5.50%), Full FT (7.22%), and PiSSA (7.44%). On the GSM-8K benchmark, SORSA achieved 56.03% accuracy, surpassing LoRA (42.30%), Full FT (49.05%), and PiSSA (53.07%) We conclude that SORSA offers a new perspective on parameter-efficient fine-tuning, demonstrating remarkable performance. The code is available at https://github.com/Gunale0926/SORSA., Comment: 12 pages, 5 figures, 3 tables

Terahertz (THz) fiber that provides high-speed connections is an essential component in THz communication systems. The emerging space-division-multiplexing technology is expected to increase the transmission capacity of THz communications. A promising candidate to achieve that is integrating multiple channels in a compact THz multi-core fiber system. Here, we propose and experimentally demonstrate a THz subwavelength rectangular dielectric dual-core fiber structure, where two identical cores can be densely integrated, thanks to the polarization-maintaining feature of the rectangular fiber. Different configurations, including the placements, core-spacings, and polarization states of two fiber cores, are comprehensively investigated to improve channel isolation. Numerical simulations show that the fractional power in core of fiber mode has a dominant effect on inter-core coupling performance. Moreover, we design the core size (1 mm x 0.5 mm) slightly less than the WR5.1 waveguide (1.295 mm x 0.6475 mm) so that the fiber can be conveniently connected with the WR5.1 flange port with mode excitation efficiencies up to 62.8%. A cost-efficient dielectric 3D printing technique is employed for rapid fabrications of dual-core fibers and corresponding polymer flange structures that offer solid integration between the fiber samples and the WR5.1 port. Experimental measurements demonstrate that a 4-mm core-spacing (less than three times the operation wavelengths over 0.17-0.21 THz) supports robust dual-channel propagation with channel isolation values more than 15 dB, which are consistent with theoretical and numerical results. This work provides a densely integrated dual-core fiber system with low fabrication cost and practical connection to the WR5.1 flange, holding exciting potential for high-capacity THz space-division-multiplexing communication systems., Comment: 10 pages, 9 figures, 3 tables

Burst super-resolution aims to reconstruct high-resolution images with higher quality and richer details by fusing the sub-pixel information from multiple burst low-resolution frames. In BusrtSR, the key challenge lies in extracting the base frame's content complementary sub-pixel details while simultaneously suppressing high-frequency noise disturbance. Existing methods attempt to extract sub-pixels by modeling inter-frame relationships frame by frame while overlooking the mutual correlations among multi-current frames and neglecting the intra-frame interactions, leading to inaccurate and noisy sub-pixels for base frame super-resolution. Further, existing methods mainly employ static upsampling with fixed parameters to improve spatial resolution for all scenes, failing to perceive the sub-pixel distribution difference across multiple frames and cannot balance the fusion weights of different frames, resulting in over-smoothed details and artifacts. To address these limitations, we introduce a novel Query Mamba Burst Super-Resolution (QMambaBSR) network, which incorporates a Query State Space Model (QSSM) and Adaptive Up-sampling module (AdaUp). Specifically, based on the observation that sub-pixels have consistent spatial distribution while random noise is inconsistently distributed, a novel QSSM is proposed to efficiently extract sub-pixels through inter-frame querying and intra-frame scanning while mitigating noise interference in a single step. Moreover, AdaUp is designed to dynamically adjust the upsampling kernel based on the spatial distribution of multi-frame sub-pixel information in the different burst scenes, thereby facilitating the reconstruction of the spatial arrangement of high-resolution details. Extensive experiments on four popular synthetic and real-world benchmarks demonstrate that our method achieves a new state-of-the-art performance.

Aerosol interactions with clouds represent a significant uncertainty in our understanding of the Earth system. Deep convective clouds may respond to aerosol perturbations in several ways that have proven difficult to elucidate with observations. Here, we leverage the two busiest maritime shipping lanes in the world, which emit aerosol particles and their precursors into an otherwise relatively clean tropical marine boundary layer, to make headway on the influence of aerosol on deep convective clouds. The recent seven-fold change in allowable fuel sulfur by the International Maritime Organization allows us to test the sensitivity of the lightning to changes in ship plume aerosol size distributions. We find that, across a range of atmospheric thermodynamic conditions, the previously documented enhancement of lightning over the shipping lanes has fallen by over 40\%. The enhancement is therefore at least partially aerosol-mediated, a conclusion that is supported by observations of droplet number at cloud base, which show a similar decline over the shipping lane. These results have fundamental implications for our understanding of aerosol-cloud interactions, suggesting that deep convective clouds are impacted by the aerosol number distribution in the remote marine environment.

Differentially private graph analysis is a powerful tool for deriving insights from diverse graph data while protecting individual information. Designing private analytic algorithms for different graph queries often requires starting from scratch. In contrast, differentially private synthetic graph generation offers a general paradigm that supports one-time generation for multiple queries. Although a rich set of differentially private graph generation algorithms has been proposed, comparing them effectively remains challenging due to various factors, including differing privacy definitions, diverse graph datasets, varied privacy requirements, and multiple utility metrics. To this end, we propose PGB (Private Graph Benchmark), a comprehensive benchmark designed to enable researchers to compare differentially private graph generation algorithms fairly. We begin by identifying four essential elements of existing works as a 4-tuple: mechanisms, graph datasets, privacy requirements, and utility metrics. We discuss principles regarding these elements to ensure the comprehensiveness of a benchmark. Next, we present a benchmark instantiation that adheres to all principles, establishing a new method to evaluate existing and newly proposed graph generation algorithms. Through extensive theoretical and empirical analysis, we gain valuable insights into the strengths and weaknesses of prior algorithms. Our results indicate that there is no universal solution for all possible cases. Finally, we provide guidelines to help researchers select appropriate mechanisms for various scenarios., Comment: 12 pages

First-person hand-object interaction anticipation aims to predict the interaction process over a forthcoming period based on current scenes and prompts. This capability is crucial for embodied intelligence and human-robot collaboration. The complete interaction process involves both pre-contact interaction intention (i.e., hand motion trends and interaction hotspots) and post-contact interaction manipulation (i.e., manipulation trajectories and hand poses with contact). Existing research typically anticipates only interaction intention while neglecting manipulation, resulting in incomplete predictions and an increased likelihood of intention errors due to the lack of manipulation constraints. To address this, we propose a novel model, PEAR (Phrase-Based Hand-Object Interaction Anticipation), which jointly anticipates interaction intention and manipulation. To handle uncertainties in the interaction process, we employ a twofold approach. Firstly, we perform cross-alignment of verbs, nouns, and images to reduce the diversity of hand movement patterns and object functional attributes, thereby mitigating intention uncertainty. Secondly, we establish bidirectional constraints between intention and manipulation using dynamic integration and residual connections, ensuring consistency among elements and thus overcoming manipulation uncertainty. To rigorously evaluate the performance of the proposed model, we collect a new task-relevant dataset, EGO-HOIP, with comprehensive annotations. Extensive experimental results demonstrate the superiority of our method., Comment: 22 pages, 10 figures, 4 tables

Spatiotemporal federated learning has recently raised intensive studies due to its ability to train valuable models with only shared gradients in various location-based services. On the other hand, recent studies have shown that shared gradients may be subject to gradient inversion attacks (GIA) on images or texts. However, so far there has not been any systematic study of the gradient inversion attacks in spatiotemporal federated learning. In this paper, we explore the gradient attack problem in spatiotemporal federated learning from attack and defense perspectives. To understand privacy risks in spatiotemporal federated learning, we first propose Spatiotemporal Gradient Inversion Attack (ST-GIA), a gradient attack algorithm tailored to spatiotemporal data that successfully reconstructs the original location from gradients. Furthermore, we design an adaptive defense strategy to mitigate gradient inversion attacks in spatiotemporal federated learning. By dynamically adjusting the perturbation levels, we can offer tailored protection for varying rounds of training data, thereby achieving a better trade-off between privacy and utility than current state-of-the-art methods. Through intensive experimental analysis on three real-world datasets, we reveal that the proposed defense strategy can well preserve the utility of spatiotemporal federated learning with effective security protection., Comment: Accepted by DASFAA 2024, 16 pages

Moir\'e patterns are commonly seen when taking photos of screens. Camera devices usually have limited hardware performance but take high-resolution photos. However, users are sensitive to the photo processing time, which presents a hardly considered challenge of efficiency for demoir\'eing methods. To balance the network speed and quality of results, we propose a \textbf{F}ully \textbf{C}onnected en\textbf{C}oder-de\textbf{C}oder based \textbf{D}emoir\'eing \textbf{Net}work (FC3DNet). FC3DNet utilizes features with multiple scales in each stage of the decoder for comprehensive information, which contains long-range patterns as well as various local moir\'e styles that both are crucial aspects in demoir\'eing. Besides, to make full use of multiple features, we design a Multi-Feature Multi-Attention Fusion (MFMAF) module to weigh the importance of each feature and compress them for efficiency. These designs enable our network to achieve performance comparable to state-of-the-art (SOTA) methods in real-world datasets while utilizing only a fraction of parameters, FLOPs, and runtime., Comment: Accepted by ICIP2024

Watermarking is broadly utilized to protect ownership of shared data while preserving data utility. However, existing watermarking methods for tabular datasets fall short on the desired properties (detectability, non-intrusiveness, and robustness) and only preserve data utility from the perspective of data statistics, ignoring the performance of downstream ML models trained on the datasets. Can we watermark tabular datasets without significantly compromising their utility for training ML models while preventing attackers from training usable ML models on attacked datasets? In this paper, we propose a hypothesis testing-based watermarking scheme, TabularMark. Data noise partitioning is utilized for data perturbation during embedding, which is adaptable for numerical and categorical attributes while preserving the data utility. For detection, a custom-threshold one proportion z-test is employed, which can reliably determine the presence of the watermark. Experiments on real-world and synthetic datasets demonstrate the superiority of TabularMark in detectability, non-intrusiveness, and robustness.

Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts have either manually simulated intricate physical-based degradations or utilized learning-based techniques, yet these approaches remain inadequate for producing large-scale, realistic, and diverse data simultaneously. In this paper, we introduce a novel Realistic Decoupled Data Generator (RealDGen), an unsupervised learning data generation framework designed for real-world super-resolution. We meticulously develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model to create realistic low-resolution images from unpaired real LR and HR images. Extensive experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations, significantly advancing the performance of popular SR models on various real-world benchmarks.

Wireless devices can be easily attacked by jammers during transmission, which is a potential security threat for wireless communications. Active reconfigurable intelligent surface (RIS) attracts considerable attention and is expected to be employed in anti-jamming systems for secure transmission to significantly enhance the anti-jamming performance. However, active RIS introduces external power load, which increases the complexity of hardware and restricts the flexible deployment of active RIS. To overcome these drawbacks, we design a innovative self-sustainable structure in this paper, where the active RIS is energized by harvesting energy from base station (BS) signals through the time dividing based simultaneous wireless information and power transfer (TD-SWIPT) scheme. Based on the above structure, we develop the BS harvesting scheme based on joint transmit and reflecting beamforming with the aim of maximizing the achievable rate of active RIS-assisted system, where the alternating optimization (AO) algorithm based on stochastic successive convex approximation (SSCA) tackles the nonconvex optimization problem in the scheme. Simulation results verified the effectiveness of our developed BS harvesting scheme, which can attain higher anti-jamming performance than other schemes when given the same maximum transmit power., Comment: submitted to IEEE systems journal

Although the emerging reconfigurable intelligent surface (RIS) paves a new way for next-generation wireless communications, it suffers from inherent flaws, i.e., double-fading attenuation effects and half-space coverage limitations. The state-of-the-art double-face active (DFA)-RIS architecture is proposed for significantly amplifying and transmitting incident signals in full-space. Despite the efficacy of DFA-RIS in mitigating the aforementioned flaws, its potential drawback is that the complex active hardware also incurs intolerable energy consumption. To overcome this drawback, in this paper we propose a novel dynamic energy-saving design for the DFA-RIS, called the sub-array based DFA-RIS architecture. This architecture divides the DFA-RIS into multiple sub-arrays, where the signal amplification function in each sub-array can be activated/deactivated dynamically and flexibly. Utilizing the above architecture, we develop the joint optimization scheme based on transmit beamforming, DFA-RIS configuration, and reflection amplifier (RA) operating pattern to maximize the energy efficiency (EE) of the DFA-RIS assisted multiuser MISO system considering the perfect/imperfect channel state information (CSI) case. Then, the penalty dual decomposition (PDD) based alternating optimization (AO) algorithm and the constrained stochastic majorization-minimization (CSMM) based AO algorithm address non-convex problems in the perfect/imperfect CSI case, respectively. Simulation results verified that our proposed sub-array based DFA-RIS architecture can benefit the EE of the system more than other RIS architectures., Comment: submitted to IEEE TWC

This paper introduces a novel competitive mechanism into differential evolution (DE), presenting an effective DE variant named competitive DE (CDE). CDE features a simple yet efficient mutation strategy: DE/winner-to-best/1. Essentially, the proposed DE/winner-to-best/1 strategy can be recognized as an intelligent integration of the existing mutation strategies of DE/rand-to-best/1 and DE/cur-to-best/1. The incorporation of DE/winner-to-best/1 and the competitive mechanism provide new avenues for advancing DE techniques. Moreover, in CDE, the scaling factor $F$ and mutation rate $Cr$ are determined by a random number generator following a normal distribution, as suggested by previous research. To investigate the performance of the proposed CDE, comprehensive numerical experiments are conducted on CEC2017 and engineering simulation optimization tasks, with CMA-ES, JADE, and other state-of-the-art optimizers and DE variants employed as competitor algorithms. The experimental results and statistical analyses highlight the promising potential of CDE as an alternative optimizer for addressing diverse optimization challenges., Comment: Accepted by The 30th Int'l Conf on Parallel and Distributed Processing Techniques and Applications (PDPTA'24)

Motivated by the potential of large language models (LLMs) as optimizers for solving combinatorial optimization problems, this paper proposes a novel LLM-assisted optimizer (LLMO) to address adversarial robustness neural architecture search (ARNAS), a specific application of combinatorial optimization. We design the prompt using the standard CRISPE framework (i.e., Capacity and Role, Insight, Statement, Personality, and Experiment). In this study, we employ Gemini, a powerful LLM developed by Google. We iteratively refine the prompt, and the responses from Gemini are adapted as solutions to ARNAS instances. Numerical experiments are conducted on NAS-Bench-201-based ARNAS tasks with CIFAR-10 and CIFAR-100 datasets. Six well-known meta-heuristic algorithms (MHAs) including genetic algorithm (GA), particle swarm optimization (PSO), differential evolution (DE), and its variants serve as baselines. The experimental results confirm the competitiveness of the proposed LLMO and highlight the potential of LLMs as effective combinatorial optimizers. The source code of this research can be downloaded from \url{https://github.com/RuiZhong961230/LLMO}., Comment: Accepted by The 6th International Conference on Data-driven Optimization of Complex Systems (DOCS)

High utility and rigorous data privacy are of the main goals of a federated learning (FL) system, which learns a model from the data distributed among some clients. The latter has been tried to achieve by using differential privacy in FL (DPFL). There is often heterogeneity in clients privacy requirements, and existing DPFL works either assume uniform privacy requirements for clients or are not applicable when server is not fully trusted (our setting). Furthermore, there is often heterogeneity in batch and/or dataset size of clients, which as shown, results in extra variation in the DP noise level across clients model updates. With these sources of heterogeneity, straightforward aggregation strategies, e.g., assigning clients aggregation weights proportional to their privacy parameters will lead to lower utility. We propose Robust-HDP, which efficiently estimates the true noise level in clients model updates and reduces the noise-level in the aggregated model updates considerably. Robust-HDP improves utility and convergence speed, while being safe to the clients that may maliciously send falsified privacy parameter to server. Extensive experimental results on multiple datasets and our theoretical analysis confirm the effectiveness of Robust-HDP. Our code can be found here., Comment: Proceedings of the 41 st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024

Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories. For localization, the proposed 3D Novel Object Discovery (3D-NOD) strategy utilizes 3D geometries and 2D open-vocabulary semantic priors to discover pseudo labels for novel objects during training. 3D-NOD is further extended with an Enrichment strategy that significantly enriches the novel object distribution in the training scenes, and then enhances the model's ability to localize more novel objects. The 3D-NOD with Enrichment is termed 3D-NODE. For classification, the Discovery-driven Cross-modal Alignment (DCMA) module aligns features from 3D point clouds and 2D/textual modalities, employing both class-agnostic and class-specific alignments that are iteratively refined to handle the expanding vocabulary of objects. Besides, 2D box guidance boosts the classification accuracy against complex background noises, which is coined as Box-DCMA. Extensive evaluation demonstrates the superiority of CoDAv2. CoDAv2 outperforms the best-performing method by a large margin (AP_Novel of 9.17 vs. 3.61 on SUN-RGBD and 9.12 vs. 3.74 on ScanNetv2). Source code and pre-trained models are available at the GitHub project page., Comment: Code Page: https://github.com/yangcaoai/CoDA_NeurIPS2023 This paper has been submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) for possible publication

Collaborative graph analysis across multiple institutions is becoming increasingly popular. Realistic examples include social network analysis across various social platforms, financial transaction analysis across multiple banks, and analyzing the transmission of infectious diseases across multiple hospitals. We define the federated graph analytics, a new problem for collaborative graph analytics under differential privacy. Although differentially private graph analysis has been widely studied, it fails to achieve a good tradeoff between utility and privacy in federated scenarios, due to the limited view of local clients and overlapping information across multiple subgraphs. Motivated by this, we first propose a federated graph analytic framework, named FEAT, which enables arbitrary downstream common graph statistics while preserving individual privacy. Furthermore, we introduce an optimized framework based on our proposed degree-based partition algorithm, called FEAT+, which improves the overall utility by leveraging the true local subgraphs. Finally, extensive experiments demonstrate that our FEAT and FEAT+ significantly outperform the baseline approach by approximately one and four orders of magnitude, respectively., Comment: 13 pages

In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques. In this paper, we study extending ICL to address a broader range of tasks with an extended learning horizon and higher improvement potential, namely General-Purpose In-Context Learning (GPICL). To this end, we introduce two lightweight benchmarks specifically crafted to train and evaluate GPICL functionalities. Each benchmark encompasses a vast number of tasks characterized by significant task variance, facilitating meta-training that minimizes inductive bias. These tasks are also crafted to promote long-horizon in-context learning through continuous generation and interaction. These characteristics necessitate the models to leverage contexts and history interactions to enhance their capabilities, across domains such as language modeling, decision-making, and world modeling. Our experiments on the baseline models demonstrate that meta-training with minimal inductive bias and ICL from the ground up is feasible across all the domains we've discussed. Additionally, our findings indicate that the scale of parameters alone may not be crucial for ICL or GPICL, suggesting alternative approaches such as increasing the scale of contexts and memory states.

Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined norm and then injects calibrated noise into the training procedure. Existing DPSGD works typically assume the gradients follow sub-Gaussian distributions and design various clipping mechanisms to optimize training performance. However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms. To address this problem, we propose a novel approach, Discriminative Clipping~(DC)-DPSGD, with two key designs. First, we introduce a subspace identification technique to distinguish between body and tail gradients. Second, we present a discriminative clipping mechanism that applies different clipping thresholds for body and tail gradients to reduce the clipping loss. Under the non-convex condition, \ourtech{} reduces the empirical gradient norm from {${\mathbb{O}\left(\log^{\max(0,\theta-1)}(T/\delta)\log^{2\theta}(\sqrt{T})\right)}$} to {${\mathbb{O}\left(\log(\sqrt{T})\right)}$} with heavy-tailed index $\theta\geq 1/2$, iterations $T$, and arbitrary probability $\delta$. Extensive experiments on four real-world datasets demonstrate that our approach outperforms three baselines by up to 9.72\% in terms of accuracy.

Knowledge tracing (KT) enhances student learning by leveraging past performance to predict future performance. Current research utilizes models based on attention mechanisms and recurrent neural network structures to capture long-term dependencies and correlations between exercises, aiming to improve model accuracy. Due to the growing amount of data in smart education scenarios, this poses a challenge in terms of time and space consumption for knowledge tracing models. However, existing research often overlooks the efficiency of model training and inference and the constraints of training resources. Recognizing the significance of prioritizing model efficiency and resource usage in knowledge tracing, we introduce Mamba4KT. This novel model is the first to explore enhanced efficiency and resource utilization in knowledge tracing. We also examine the interpretability of the Mamba structure both sequence-level and exercise-level to enhance model interpretability. Experimental findings across three public datasets demonstrate that Mamba4KT achieves comparable prediction accuracy to state-of-the-art models while significantly improving training and inference efficiency and resource utilization. As educational data continues to grow, our work suggests a promising research direction for knowledge tracing that improves model prediction accuracy, model efficiency, resource utilization, and interpretability simultaneously.

The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about \textit{What}, \textit{Why}, and \textit{How}. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (\textit{CNN/DailyMail}, \textit{XSum}, \textit{NYT}, \textit{RA-MDS}); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction., Comment: IJCNN 2024

Understanding egocentric human-object interaction (HOI) is a fundamental aspect of human-centric perception, facilitating applications like AR/VR and embodied AI. For the egocentric HOI, in addition to perceiving semantics e.g., ''what'' interaction is occurring, capturing ''where'' the interaction specifically manifests in 3D space is also crucial, which links the perception and operation. Existing methods primarily leverage observations of HOI to capture interaction regions from an exocentric view. However, incomplete observations of interacting parties in the egocentric view introduce ambiguity between visual observations and interaction contents, impairing their efficacy. From the egocentric view, humans integrate the visual cortex, cerebellum, and brain to internalize their intentions and interaction concepts of objects, allowing for the pre-formulation of interactions and making behaviors even when interaction regions are out of sight. In light of this, we propose harmonizing the visual appearance, head motion, and 3D object to excavate the object interaction concept and subject intention, jointly inferring 3D human contact and object affordance from egocentric videos. To achieve this, we present EgoChoir, which links object structures with interaction contexts inherent in appearance and head motion to reveal object affordance, further utilizing it to model human contact. Additionally, a gradient modulation is employed to adopt appropriate clues for capturing interaction regions across various egocentric scenarios. Moreover, 3D contact and affordance are annotated for egocentric videos collected from Ego-Exo4D and GIMO to support the task. Extensive experiments on them demonstrate the effectiveness and superiority of EgoChoir. Code and data will be open., Comment: 23 pages,10 figures

Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.

Human mobility data offers valuable insights for many applications such as urban planning and pandemic response, but its use also raises privacy concerns. In this paper, we introduce the Hierarchical and Multi-Resolution Network (HRNet), a novel deep generative model specifically designed to synthesize realistic human mobility data while guaranteeing differential privacy. We first identify the key difficulties inherent in learning human mobility data under differential privacy. In response to these challenges, HRNet integrates three components: a hierarchical location encoding mechanism, multi-task learning across multiple resolutions, and private pre-training. These elements collectively enhance the model's ability under the constraints of differential privacy. Through extensive comparative experiments utilizing a real-world dataset, HRNet demonstrates a marked improvement over existing methods in balancing the utility-privacy trade-off.

In recent years, privacy and security concerns in machine learning have promoted trusted federated learning to the forefront of research. Differential privacy has emerged as the de facto standard for privacy protection in federated learning due to its rigorous mathematical foundation and provable guarantee. Despite extensive research on algorithms that incorporate differential privacy within federated learning, there remains an evident deficiency in systematic reviews that categorize and synthesize these studies. Our work presents a systematic overview of the differentially private federated learning. Existing taxonomies have not adequately considered objects and level of privacy protection provided by various differential privacy models in federated learning. To rectify this gap, we propose a new taxonomy of differentially private federated learning based on definition and guarantee of various differential privacy models and federated scenarios. Our classification allows for a clear delineation of the protected objects across various differential privacy models and their respective neighborhood levels within federated learning environments. Furthermore, we explore the applications of differential privacy in federated learning scenarios. Our work provide valuable insights into privacy-preserving federated learning and suggest practical directions for future research., Comment: 36pages

Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressive achievements in detail recovery, they still fall short when addressing regions with complex gradient arrangements due to the intensity-based linear weighting feature extraction manner. Moreover, the stochastic artifacts introduced by degradation cues during the imaging process in real LR increase the disorder of the overall image details, further complicating the perception of intrinsic gradient arrangement. To address these challenges, we innovatively introduce kernel-wise differential operations within the convolutional kernel and develop several learnable directional gradient convolutions. These convolutions are integrated in parallel with a novel linear weighting mechanism to form an Adaptive Directional Gradient Convolution (DGConv), which adaptively weights and fuses the basic directional gradients to improve the gradient arrangement perception capability for both regular and irregular textures. Coupled with DGConv, we further devise a novel equivalent parameter fusion method for DGConv that maintains its rich representational capabilities while keeping computational costs consistent with a single Vanilla Convolution (VConv), enabling DGConv to improve the performance of existing super-resolution networks without incurring additional computational expenses. To better leverage the superiority of DGConv, we further develop an Adaptive Information Interaction Block (AIIBlock) to adeptly balance the enhancement of texture and contrast while meticulously investigating the interdependencies, culminating in the creation of a DGPNet for Real-SR through simple stacking. Comparative results with 15 SOTA methods across three public datasets underscore the effectiveness and efficiency of our proposed approach.

Interaction intention anticipation aims to jointly predict future hand trajectories and interaction hotspots. Existing research often treated trajectory forecasting and interaction hotspots prediction as separate tasks or solely considered the impact of trajectories on interaction hotspots, which led to the accumulation of prediction errors over time. However, a deeper inherent connection exists between hand trajectories and interaction hotspots, which allows for continuous mutual correction between them. Building upon this relationship, a novel Bidirectional prOgressive Transformer (BOT), which introduces a Bidirectional Progressive mechanism into the anticipation of interaction intention is established. Initially, BOT maximizes the utilization of spatial information from the last observation frame through the Spatial-Temporal Reconstruction Module, mitigating conflicts arising from changes of view in first-person videos. Subsequently, based on two independent prediction branches, a Bidirectional Progressive Enhancement Module is introduced to mutually improve the prediction of hand trajectories and interaction hotspots over time to minimize error accumulation. Finally, acknowledging the intrinsic randomness in human natural behavior, we employ a Trajectory Stochastic Unit and a C-VAE to introduce appropriate uncertainty to trajectories and interaction hotspots, respectively. Our method achieves state-of-the-art results on three benchmark datasets Epic-Kitchens-100, EGO4D, and EGTEA Gaze+, demonstrating superior in complex scenarios.

This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images., Comment: CVPR 2024, AI for Streaming (AIS) Workshop

Event-based eye tracking has shown great promise with the high temporal resolution and low redundancy provided by the event camera. However, the diversity and abruptness of eye movement patterns, including blinking, fixating, saccades, and smooth pursuit, pose significant challenges for eye localization. To achieve a stable event-based eye-tracking system, this paper proposes a bidirectional long-term sequence modeling and time-varying state selection mechanism to fully utilize contextual temporal information in response to the variability of eye movements. Specifically, the MambaPupil network is proposed, which consists of the multi-layer convolutional encoder to extract features from the event representations, a bidirectional Gated Recurrent Unit (GRU), and a Linear Time-Varying State Space Module (LTV-SSM), to selectively capture contextual correlation from the forward and backward temporal relationship. Furthermore, the Bina-rep is utilized as a compact event representation, and the tailor-made data augmentation, called as Event-Cutout, is proposed to enhance the model's robustness by applying spatial random masking to the event image. The evaluation on the ThreeET-plus benchmark shows the superior performance of the MambaPupil, which secured the 1st place in CVPR'2024 AIS Event-based Eye Tracking challenge., Comment: Accepted by CVPR 2024 Workshop (AIS: Vision, Graphics and AI for Streaming), top solution of challenge Event-based Eye Tracking, see https://www.kaggle.com/competitions/event-based-eye-tracking-ais2024

This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge. The task of the challenge focuses on processing eye movement recorded with event cameras and predicting the pupil center of the eye. The challenge emphasizes efficient eye tracking with event cameras to achieve good task accuracy and efficiency trade-off. During the challenge period, 38 participants registered for the Kaggle competition, and 8 teams submitted a challenge factsheet. The novel and diverse methods from the submitted factsheets are reviewed and analyzed in this survey to advance future event-based eye tracking research., Comment: Qinyu Chen is the corresponding author

3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion., Comment: Project page: https://johanan528.github.io/Infusion

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/., Comment: The report paper of NTIRE2024 Efficient Super-resolution, accepted by CVPRW2024

The computation of the skyline provides a mechanism for utilizing multiple location-based criteria to identify optimal data points. However, the efficiency of these computations diminishes and becomes more challenging as the input data expands. This study presents a novel algorithm aimed at mitigating this challenge by harnessing the capabilities of Apache Spark, a distributed processing platform, for conducting area skyline computations. The proposed algorithm enhances processing speed and scalability. In particular, our algorithm encompasses three key phases: the computation of distances between data points, the generation of distance tuples, and the execution of the skyline operators. Notably, the second phase employs a local partial skyline extraction technique to minimize the volume of data transmitted from each executor (a parallel processing procedure) to the driver (a central processing procedure). Afterwards, the driver processes the received data to determine the final skyline and creates filters to exclude irrelevant points. Extensive experimentation on eight datasets reveals that our algorithm significantly reduces both data size and computation time required for area skyline computation.

Large language models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy prompts lead to sub-standard results in terms of readability and interpretability of the compressed prompt, with a detrimental impact on prompt utility. To address this, we propose PROMPT-SAW: Prompt compresSion via Relation AWare graphs, an effective strategy for prompt compression over task-agnostic and task-aware prompts. PROMPT-SAW uses the prompt's textual information to build a graph, later extracts key information elements in the graph to come up with the compressed prompt. We also propose GSM8K-AUG, i.e., an extended version of the existing GSM8k benchmark for task-agnostic prompts in order to provide a comprehensive evaluation platform. Experimental evaluation using benchmark datasets shows that prompts compressed by PROMPT-SAW are not only better in terms of readability, but they also outperform the best-performing baseline models by up to 14.3 and 13.7 respectively for task-aware and task-agnostic settings while compressing the original prompt text by 33.0 and 56.7.

Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to animate static image (i.e., image-to-video generation). The difficulty originates from the aspect that the diffusion process of subsequent animated frames should not only preserve the faithful alignment with the given image but also pursue temporal coherence among adjacent frames. To alleviate this, we present TRIP, a new recipe of image-to-video diffusion paradigm that pivots on image noise prior derived from static image to jointly trigger inter-frame relational reasoning and ease the coherent temporal modeling via temporal residual learning. Technically, the image noise prior is first attained through one-step backward diffusion process based on both static image and noised video latent codes. Next, TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning, thereby easing the learning of the residual noise for each frame. Furthermore, both reference and residual noise of each frame are dynamically merged via attention mechanism for final video generation. Extensive experiments on WebVid-10M, DTDB and MSR-VTT datasets demonstrate the effectiveness of our TRIP for image-to-video generation. Please see our project page at https://trip-i2v.github.io/TRIP/., Comment: CVPR 2024; Project page: https://trip-i2v.github.io/TRIP/

Anomaly detection is a longstanding and active research area that has many applications in domains such as finance, security, and manufacturing. However, the efficiency and performance of anomaly detection algorithms are challenged by the large-scale, high-dimensional, and heterogeneous data that are prevalent in the era of big data. Isolation-based unsupervised anomaly detection is a novel and effective approach for identifying anomalies in data. It relies on the idea that anomalies are few and different from normal instances, and thus can be easily isolated by random partitioning. Isolation-based methods have several advantages over existing methods, such as low computational complexity, low memory usage, high scalability, robustness to noise and irrelevant features, and no need for prior knowledge or heavy parameter tuning. In this survey, we review the state-of-the-art isolation-based anomaly detection methods, including their data partitioning strategies, anomaly score functions, and algorithmic details. We also discuss some extensions and applications of isolation-based methods in different scenarios, such as detecting anomalies in streaming data, time series, trajectory, and image datasets. Finally, we identify some open challenges and future directions for isolation-based anomaly detection research.

Dynamic Range (DR) is a pivotal characteristic of imaging systems. Current frame-based cameras struggle to achieve high dynamic range imaging due to the conflict between globally uniform exposure and spatially variant scene illumination. In this paper, we propose AsynHDR, a Pixel-Asynchronous HDR imaging system, based on key insights into the challenges in HDR imaging and the unique event-generating mechanism of Dynamic Vision Sensors (DVS). Our proposed AsynHDR system integrates the DVS with a set of LCD panels. The LCD panels modulate the irradiance incident upon the DVS by altering their transparency, thereby triggering the pixel-independent event streams. The HDR image is subsequently decoded from the event streams through our temporal-weighted algorithm. Experiments under standard test platform and several challenging scenes have verified the feasibility of the system in HDR imaging task.

Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages action intention consisting of human movement and action description as view-independent representation to guide video generation, preserving the consistency of content and motion. Specifically, the egocentric head trajectory is first estimated through multi-view stereo matching. Then, cross-view feature perception module is introduced to establish correspondences between exo- and ego- views, guiding the trajectory transformation module to infer human full-body movement from the head trajectory. Meanwhile, we present an action description unit that maps the action semantics into the feature space consistent with the exocentric image. Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i.e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video. We conduct extensive experiments on the relevant dataset with diverse exo-ego video pairs, and our IDE outperforms state-of-the-art models in both subjective and objective assessments, demonstrating its efficacy in ego-to-exo video generation.

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained models, as anyone can publish without strict validation processes. However, a released pre-trained model can be a privacy trap for fine-tuning datasets if it is carefully designed. In this work, we propose PreCurious framework to reveal the new attack surface where the attacker releases the pre-trained model and gets a black-box access to the final fine-tuned model. PreCurious aims to escalate the general privacy risk of both membership inference and data extraction on the fine-tuning dataset. The key intuition behind PreCurious is to manipulate the memorization stage of the pre-trained model and guide fine-tuning with a seemingly legitimate configuration. While empirical and theoretical evidence suggests that parameter-efficient and differentially private fine-tuning techniques can defend against privacy attacks on a fine-tuned model, PreCurious demonstrates the possibility of breaking up this invulnerability in a stealthy manner compared to fine-tuning on a benign pre-trained model. While DP provides some mitigation for membership inference attack, by further leveraging a sanitized dataset, PreCurious demonstrates potential vulnerabilities for targeted data extraction even under differentially private tuning with a strict privacy budget e.g. $\epsilon=0.05$. Thus, PreCurious raises warnings for users on the potential risks of downloading pre-trained models from unknown sources, relying solely on tutorials or common-sense defenses, and releasing sanitized datasets even after perfect scrubbing., Comment: 15 pages

This paper explores providing explainability for session-based recommendation (SR) by path reasoning. Current SR models emphasize accuracy but lack explainability, while traditional path reasoning prioritizes knowledge graph exploration, ignoring sequential patterns present in the session history. Therefore, we propose a generalized hierarchical reinforcement learning framework for SR, which improves the explainability of existing SR models via Path Reasoning, namely PR4SR. Considering the different importance of items to the session, we design the session-level agent to select the items in the session as the starting point for path reasoning and the path-level agent to perform path reasoning. In particular, we design a multi-target reward mechanism to adapt to the skip behaviors of sequential patterns in SR, and introduce path midpoint reward to enhance the exploration efficiency in knowledge graphs. To improve the completeness of the knowledge graph and to diversify the paths of explanation, we incorporate extracted feature information from images into the knowledge graph. We instantiate PR4SR in five state-of-the-art SR models (i.e., GRU4REC, NARM, GCSAN, SR-GNN, SASRec) and compare it with other explainable SR frameworks, to demonstrate the effectiveness of PR4SR for recommendation and explanation tasks through extensive experiments with these approaches on four datasets.

In this paper, we present a novel method for automatically generating sports news, which employs a unique algorithm that extracts pivotal moments from live text broadcasts and uses them to create an initial draft of the news. This draft is further refined by incorporating key details and background information from a specially designed sports knowledge graph. This graph contains 5,893 entities, which are classified into three distinct conceptual categories, interconnected through four relationship types, and characterized by 27 unique attributes. In addition, we create a multi-stage learning model by combining convolutional neural networks and a transformer encoder. This model expresses entity-task interactions using convolutional neural networks and enriches entity representations in the query set with the transformer encoder. It also includes a processor to compute matching scores for incomplete triples, addressing few-shot knowledge graph completion problem. The efficiency of this approach has been confirmed through both subjective and objective evaluations of 50 selected test cases, demonstrating its capability in revolutionizing the creation of sports news.

Constructing earth-fixed cells with low-earth orbit (LEO) satellites in non-terrestrial networks (NTNs) has been the most promising paradigm to enable global coverage. The limited computing capabilities on LEO satellites however render tackling resource optimization within a short duration a critical challenge. Although the sufficient computing capabilities of the ground infrastructures can be utilized to assist the LEO satellite, different time-scale control cycles and coupling decisions between the space- and ground-segments still obstruct the joint optimization design for computing agents at different segments. To address the above challenges, in this paper, a multi-time-scale deep reinforcement learning (DRL) scheme is developed for achieving the radio resource optimization in NTNs, in which the LEO satellite and user equipment (UE) collaborate with each other to perform individual decision-making tasks with different control cycles. Specifically, the UE updates its policy toward improving value functions of both the satellite and UE, while the LEO satellite only performs finite-step rollout for decision-makings based on the reference decision trajectory provided by the UE. Most importantly, rigorous analysis to guarantee the performance convergence of the proposed scheme is provided. Comprehensive simulations are conducted to justify the effectiveness of the proposed scheme in balancing the transmission performance and computational complexity.