arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 433 records · Page 24Linked to original sources

arXiv2024

SoccerNet 2024 Challenges Results

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

cs.CV↗

arXiv2024

One Shot is Enough for Sequential Infrared Small Target Segmentation

Infrared small target sequences exhibit strong similarities between frames and contain rich contextual information, which motivates us to achieve sequential infrared small target segmentation (IRSTS) with minimal data. Inspired by the success of Segment Anything Model (SAM) across various downstream tasks, we propose a one-shot and training-free method that perfectly adapts SAM's zero-shot generalization capability to sequential IRSTS. Specifically, we first obtain a confidence map through local feature matching (LFM). The highest point in the confidence map is used as the prompt to replace the manual prompt. Then, to address the over-segmentation issue caused by the domain gap, we design the point prompt-centric focusing (PPCF) module. Subsequently, to prevent miss and false detections, we introduce the triple-level ensemble (TLE) module to produce the final mask. Experiments demonstrate that our method requires only one shot to achieve comparable performance to state-of-the-art IRSTS methods and significantly outperforms other one-shot segmentation methods. Moreover, ablation studies confirm the robustness of our method in the type of annotations and the selection of reference images.

cs.CV↗

arXiv2024

Contact-aware Human Motion Generation from Textual Descriptions

This paper addresses the problem of generating 3D interactive human motion from text. Given a textual description depicting the actions of different body parts in contact with static objects, we synthesize sequences of 3D body poses that are visually natural and physically plausible. Yet, this task poses a significant challenge due to the inadequate consideration of interactions by physical contacts in both motion and textual descriptions, leading to unnatural and implausible sequences. To tackle this challenge, we create a novel dataset named RICH-CAT, representing "Contact-Aware Texts" constructed from the RICH dataset. RICH-CAT comprises high-quality motion, accurate human-object contact labels, and detailed textual descriptions, encompassing over 8,500 motion-text pairs across 26 indoor/outdoor actions. Leveraging RICH-CAT, we propose a novel approach named CATMO for text-driven interactive human motion synthesis that explicitly integrates human body contacts as evidence. We employ two VQ-VAE models to encode motion and body contact sequences into distinct yet complementary latent spaces and an intertwined GPT for generating human motions and contacts in a mutually conditioned manner. Additionally, we introduce a pre-trained text encoder to learn textual embeddings that better discriminate among various contact types, allowing for more precise control over synthesized motions and contacts. Our experiments demonstrate the superior performance of our approach compared to existing text-to-motion methods, producing stable, contact-aware motion sequences. Code and data will be available for research purposes at https://xymsh.github.io/RICH-CAT/

cs.CV↗

arXiv2024

PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions

Pose estimation aims to accurately identify anatomical keypoints in humans and animals using monocular images, which is crucial for various applications such as human-machine interaction, embodied AI, and autonomous driving. While current models show promising results, they are typically trained and tested on clean data, potentially overlooking the corruption during real-world deployment and thus posing safety risks in practical scenarios. To address this issue, we introduce PoseBench, a comprehensive benchmark designed to evaluate the robustness of pose estimation models against real-world corruption. We evaluated 60 representative models, including top-down, bottom-up, heatmap-based, regression-based, and classification-based methods, across three datasets for human and animal pose estimation. Our evaluation involves 10 types of corruption in four categories: 1) blur and noise, 2) compression and color loss, 3) severe lighting, and 4) masks. Our findings reveal that state-of-the-art models are vulnerable to common real-world corruptions and exhibit distinct behaviors when tackling human and animal pose estimation tasks. To improve model robustness, we delve into various design considerations, including input resolution, pre-training datasets, backbone capacity, post-processing, and data augmentations. We hope that our benchmark will serve as a foundation for advancing research in robust pose estimation. The benchmark and source code will be released at https://xymsh.github.io/PoseBench

cs.CV↗

arXiv2024

Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare

The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers new opportunities to alleviate this issue. Segment Anything Model (SAM), which excels in intelligent image segmentation, has demonstrated exceptional performance in medical monitoring and assisted diagnosis. Unfortunately, the huge computational and storage overhead of SAM poses significant challenges for deployment on resource-limited edge devices. Quantization is an effective solution for model compression; however, traditional methods rely heavily on original data for calibration, which raises widespread concerns about medical data privacy and security. In this paper, we propose a data-free quantization framework for SAM, called DFQ-SAM, which learns and calibrates quantization parameters without any original data, thus effectively preserving data privacy during model compression. Specifically, we propose pseudo-positive label evolution for segmentation, combined with patch similarity, to fully leverage the semantic and distribution priors in pre-trained models, which facilitates high-quality data synthesis as a substitute for real data. Furthermore, we introduce scale reparameterization to ensure the accuracy of low-bit quantization. We perform extensive segmentation experiments on various datasets, and DFQ-SAM consistently provides significant performance on low-bit quantization. DFQ-SAM eliminates the need for data transfer in cloud-edge collaboration, thereby protecting sensitive data from potential attacks. It enables secure, fast, and personalized healthcare services at the edge, which enhances system efficiency and optimizes resource allocation, and thus facilitating the pervasive application of artificial intelligence in worldwide healthcare.

cs.CV↗

arXiv2024

Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark

Visual Language Tracking (VLT) enhances tracking by mitigating the limitations of relying solely on the visual modality, utilizing high-level semantic information through language. This integration of the language enables more advanced human-machine interaction. The essence of interaction is cognitive alignment, which typically requires multiple information exchanges, especially in the sequential decision-making process of VLT. However, current VLT benchmarks do not account for multi-round interactions during tracking. They provide only an initial text and bounding box (bbox) in the first frame, with no further interaction as tracking progresses, deviating from the original motivation of the VLT task. To address these limitations, we propose a novel and robust benchmark, VLT-MI (Visual Language Tracking with Multi-modal Interaction), which introduces multi-round interaction into the VLT task for the first time. (1) We generate diverse, multi-granularity texts for multi-round, multi-modal interaction based on existing mainstream VLT benchmarks using DTLLM-VLT, leveraging the world knowledge of LLMs. (2) We propose a new VLT interaction paradigm that achieves multi-round interaction through text updates and object recovery. When multiple tracking failures occur, we provide the tracker with more aligned texts and corrected bboxes through interaction, thereby expanding the scope of VLT downstream tasks. (3) We conduct comparative experiments on both traditional VLT benchmarks and VLT-MI, evaluating and analyzing the accuracy and robustness of trackers under the interactive paradigm. This work offers new insights and paradigms for the VLT task, enabling a fine-grained evaluation of multi-modal trackers. We believe this approach can be extended to additional datasets in the future, supporting broader evaluations and comparisons of video-language model capabilities.

cs.CV↗

arXiv2024

Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding

Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous discriminative methods achieve only weak or coarse-grained alignment by panoptic segmentation pretraining or CLIP model adaptation. Given the recent progress of text-to-image Diffusion models, several works have shown their capability to achieve fine-grained image-text alignment through cross-attention maps and improved general segmentation performance. However, the direct use of phrase features as static prompts to apply frozen Diffusion models to the PNG task still suffers from a large task gap and insufficient vision-language interaction, yielding inferior performance. Therefore, we propose an Extractive-Injective Phrase Adapter (EIPA) bypass within the Diffusion UNet to dynamically update phrase prompts with image features and inject the multimodal cues back, which leverages the fine-grained image-text alignment capability of Diffusion models more sufficiently. In addition, we also design a Multi-Level Mutual Aggregation (MLMA) module to reciprocally fuse multi-level image and phrase features for segmentation refinement. Extensive experiments on the PNG benchmark show that our method achieves new state-of-the-art performance.

cs.CV↗

arXiv2024

Band representation, band connectivity and irreducibility

The BR, formulated by Zak in the 80s, is widely used in studies of topological phase of material. EBR are considered the building block of TQC. However, there were debate on whether they admit split bands, or if they contain band invariant subspaces. This manuscript presents a clear definition of the basis and illustrate that the band transformation properties are dependent on the band connectivity. Two different Fourier transform conventions in defining the BR induced from the same set of localised Wannier functions are discussed and identified as related by a simple gauge transformation. The TB BR are used to derive the form of TB Hamiltonian using group theoretical technique. The transformation properties of EBR allow explicit decomposition in terms of irreps of space group, and use of projection operators in determining symmetry permitted band connectivity. It is shown that EBRs arising from Wyckoff positions with multiplicity can have multiple atomic limits and identifies explicitly what occurs at HSPs on the surface of BZ as what determines the band connectivity and the irreducible nature of the connected band. Such multiple configurations arise from multiple ways to block-diagonalising representation matrix at these HSPs. The symmetry permitted connectivity allows the existence of dynamic band invariant subspaces known as irreducible band representations. Such IBR, induced from Wannier functions centred on linear combination of orbits of Wyckoff positions, can also arise from interaction among composite EBRs. They are rooted in the permutation symmetry of crystallographic orbits of Wyckoff positions with multiplicity and can occur even if the parental EBR is classified as indecomposable. When symmetry permitted split EBR occurs, which does not correspond to division between connected IBRs, the topologies of the bands are potentially non-trivial on both sides of the gap.

cond-mat.mes-hall↗

arXiv2024

SiamMo: Siamese Motion-Centric 3D Object Tracking

Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for motion-centric tracking. This decouples feature extraction from temporal fusion, significantly enhancing tracking performance. Additionally, we design a Spatio-Temporal Feature Aggregation module to integrate Siamese features at multiple scales, capturing motion information effectively. We also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation. SiamMo is a purely motion-centric tracker that eliminates the need for additional processes like segmentation and box refinement. Without whistles and bells, SiamMo not only surpasses state-of-the-art methods across multiple benchmarks but also demonstrates exceptional robustness in challenging scenarios. SiamMo sets a new record on the KITTI tracking benchmark with 90.1\% precision while maintaining a high inference speed of 108 FPS. The code will be released at https://github.com/HDU-VRLab/SiamMo.

cs.CV↗

arXiv2024

LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation

Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in conjunction with ECCV 2024 workshop. This year's challenge includes two tasks: Video Object Segmentation (VOS) and Referring Video Object Segmentation (RVOS). In this year, we replace the classic YouTube-VOS and YouTube-RVOS benchmark with latest datasets MOSE, LVOS, and MeViS to assess VOS under more challenging complex environments. This year's challenge attracted 129 registered teams from more than 20 institutes across over 8 countries. This report include the challenge and dataset introduction, and the methods used by top 7 teams in two tracks. More details can be found in our homepage https://lsvos.github.io/.

cs.CV↗

arXiv2024

Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection

Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD). Despite their remarkable success, a notable gap persists between these IRSTD methods and generic segmentation approaches in natural image domains. This gap primarily arises from the significant modality differences and the limited availability of infrared data. In this study, we aim to bridge this divergence by investigating the adaptation of generic segmentation models, such as the Segment Anything Model (SAM), to IRSTD tasks. Our investigation reveals that many generic segmentation models can achieve comparable performance to state-of-the-art IRSTD methods. However, their full potential in IRSTD remains untapped. To address this, we propose a simple, lightweight, yet effective baseline model for segmenting small infrared objects. Through appropriate distillation strategies, we empower smaller student models to outperform state-of-the-art methods, even surpassing fine-tuned teacher results. Furthermore, we enhance the model's performance by introducing a novel query design comprising dense and sparse queries to effectively encode multi-scale features. Through extensive experimentation across four popular IRSTD datasets, our model demonstrates significantly improved performance in both accuracy and throughput compared to existing approaches, surpassing SAM and Semantic-SAM by over 14 IoU on NUDT and 4 IoU on IRSTD1k. The source code and models will be released at https://github.com/O937-blip/SimIR.

cs.CV↗

arXiv2024

RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation

The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive prompts and a limited understanding of different modalities, such as language and vision. This paper presents the RefSAM model, which explores the potential of SAM for RVOS by incorporating multi-view information from diverse modalities and successive frames at different timestamps in an online manner. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-Modal MLP that projects the text embedding of the referring expression into sparse and dense embeddings, serving as user-interactive prompts. Additionally, we have introduced the hierarchical dense attention module to fuse hierarchical visual semantic information with sparse embeddings to obtain fine-grained dense embeddings, and an implicit tracking module to generate a tracking token and provide historical information for the mask decoder. Furthermore, we employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively. Through comprehensive ablation studies, we demonstrate our model's practical and effective design choices. Extensive experiments conducted on Refer-Youtube-VOS, Ref-DAVIS17, and three referring image segmentation datasets validate the superiority and effectiveness of our RefSAM model over existing methods.

cs.CV↗

arXiv2024

BEVNav: Robot Autonomous Navigation Via Spatial-Temporal Contrastive Learning in Bird's-Eye View

Goal-driven mobile robot navigation in map-less environments requires effective state representations for reliable decision-making. Inspired by the favorable properties of Bird's-Eye View (BEV) in point clouds for visual perception, this paper introduces a novel navigation approach named BEVNav. It employs deep reinforcement learning to learn BEV representations and enhance decision-making reliability. First, we propose a self-supervised spatial-temporal contrastive learning approach to learn BEV representations. Spatially, two randomly augmented views from a point cloud predict each other, enhancing spatial features. Temporally, we combine the current observation with consecutive frames' actions to predict future features, establishing the relationship between observation transitions and actions to capture temporal cues. Then, incorporating this spatial-temporal contrastive learning in the Soft Actor-Critic reinforcement learning framework, our BEVNav offers a superior navigation policy. Extensive experiments demonstrate BEVNav's robustness in environments with dense pedestrians, outperforming state-of-the-art methods across multiple benchmarks. \rev{The code will be made publicly available at https://github.com/LanrenzzzZ/BEVNav.

cs.RO↗

arXiv2024

Neutron-proton pairing correlations described on quantum computers

The ADAPT-VQE approach is used to solve the neutron-proton pairing problem in atomic nuclei. This variational approach is considered today as one of the most powerful methods to iteratively find the ground state of a many-body problem, provided a performing set of operators, called the pool of operators, is used to explore the Hilbert space of many-body wave-functions. Three different pools of operators, which might eventually break one or several symmetries of the Hamiltonian during the descent to the ground state, are tested for the neutron-proton pairing problem. We observe that the breaking of some symmetries during the optimization of the trial wave-function might, in general, help to speed up the convergence towards the ground state. Still, we rejected the pool of operators that might explicitly break the total particle number because they become uncontrollable during the optimization process. Overall, we observed that the iterative optimization process rapidly becomes a delicate problem when the number of parameters to build the ansatz increases, and the energy might get stuck at energies higher than the ground state energy. To improve the convergence in this case, several techniques have been proposed, with some better controlling the symmetries during the energy minimization. Among the proposed methods, two have proven effective: one based on an embedding technique and the other on a randomized preparation of the initial state. We conclude that the ADAPT-VQE, complemented by these techniques, can provide a very accurate description of the neutron-proton pairing problem, and can outperform other standardly used techniques that break the particle number symmetry and restore afterwards.

nucl-th↗

arXiv2024

AlignBench: Benchmarking Chinese Alignment of Large Language Models

Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap, we introduce AlignBench, a comprehensive multi-dimensional benchmark for evaluating LLMs' alignment in Chinese. We design a human-in-the-loop data curation pipeline, containing eight main categories, 683 real-scenario rooted queries and corresponding human verified references. To ensure the correctness of references, each knowledge-intensive query is accompanied with evidences collected from reliable web sources (including URLs and quotations) by our annotators. For automatic evaluation, our benchmark employs a rule-calibrated multi-dimensional LLM-as-Judge~\cite{zheng2023judging} approach with Chain-of-Thought to generate explanations and final ratings, ensuring high reliability and interpretability. All evaluation code, data, and LLM generations are available at \url{https://github.com/THUDM/AlignBench}. Since its release, AlignBench has been adopted by top (Chinese) LLMs for evaluating their alignment capabilities in Chinese, including ChatGLM, Qwen, DeepSeek, Yi, Baichuan, and Abab.

cs.CL↗

arXiv2024

Purely flavored leptogenesis from a sudden mass gain of right-handed neutrinos

In this paper, we would like to point out that in the scenario that the right-handed neutrinos suddenly gain some masses much larger than the temperature of the Universe at that time so that the washout effects for the lepton asymmetry generated from their decays can be neglected safely, the purely flavored leptogenesis scenario (in which the total CP asymmetries for the decays of the right-handed neutrinos are vanishing and the successful leptogenesis is realized by virtue of the flavor non-universality of the washout effects) cannot work in the usual way any more. For this problem, we put forward that the flavor non-universality of the conversion efficiencies from the flavored lepton asymmetries to the baryon asymmetry via the sphaleron processes may play a crucial role. And we will study if the requisite baryon asymmetry can be successfully reproduced from such a mechanism in the scenarios that the right-handed neutrino masses are hierarchical and nearly degenerate, respectively. A detailed study shows that this mechanism can be viable in both these two scenarios.

hep-ph↗

arXiv2024

LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS

Video Object Segmentation (VOS) presents several challenges, including object occlusion and fragmentation, the dis-appearance and re-appearance of objects, and tracking specific objects within crowded scenes. In this work, we combine the strengths of the state-of-the-art (SOTA) models SAM2 and Cutie to address these challenges. Additionally, we explore the impact of various hyperparameters on video instance segmentation performance. Our approach achieves a J\&F score of 0.7952 in the testing phase of LSVOS challenge VOS track, ranking third overall.

cs.CV↗

arXiv2024

$\rm SP^3$: Enhancing Structured Pruning via PCA Projection

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection (SP3), targeting the effective reduction of d by projecting features into a space defined by principal components before masking. Extensive experiments on benchmarks (GLUE and SQuAD) show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, maintain over 96% accuracy, and outperform other methods that compress d by 6% in accuracy at the same compression ratio. SP3 has also proven effective with other models, including OPT and Llama. Our data and code are available at an anonymous repo.

cs.CL↗