GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
机构 * School of EIC, Huazhong University of Science & Technology（华中科技大学电子信息学院） ； vivo AI Lab（vivo人工智能实验室）
Comments To appear at ICCV 2025. Code: https://github.com/hustvl/GroundingSuite
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA
机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院） ； Department of Electrical and Electronic Engineering, Yonsei University, Korea（延世大学电子与电气工程系）
Comments Accepted by ICCV 2025, 17 pages, 9 figures, 5 tables
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
机构 * Institute of Trustworthy Embodied AI, Fudan University, China（可信具身人工智能研究院，复旦大学） ； School of Information Science and Technology, USTC, China（信息科学与技术学院，中国科学技术大学） ； School of Computer Science and Technology, Beijing Jiaotong University, China（计算机科学与技术学院，北京交通大学）
Comments Accepted by ICCV 2025
PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models
Comments Accepted by ICCV 2025
Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching
机构 * National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室） ； National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心） ； Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院） ； Xi’an Jiaotong University（西安交通大学）
Comments Accepted by ICCV 2025
DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
机构 * University of Chinese Academy of Sciences（中国科学院大学） ； The University of Hong Kong（香港大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） ； Fudan University（复旦大学）
Comments ICCV 2025
FaceLLM: A Multimodal Large Language Model for Face Understanding
Comments Accepted in ICCV 2025 workshops
Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures
机构 * University of Science and Technology Beijing（北京科技大学） ； Tsinghua University（清华大学）
Comments Accepted at ICCV 2025. Project page is available at https://wakuwu.github.io/KBA
ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
机构 * University of Pittsburgh（匹兹堡大学）
Comments Accepted by ICCV'25
Straighten Viscous Rectified Flow via Noise Optimization
机构 * PCA Lab, Nanjing University of Science and Technology（南京理工大学科学与工程学院实验室） ； Xidian University（西安电子科技大学）
Journal ref International Conference on Computer Vision 2025
Taming Modern Point Tracking for Speckle Tracking Echocardiography via Impartial Motion
机构 * Norwegian University of Science and Technology（挪威科学与技术大学） ； Clinic of Cardiology, St. Olavs Hospital（圣奥拉夫医院心内科） ； SINTEF Digital（SINTEF数字）
Comments Accepted to CVAMD workshop at ICCV 2025
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
机构 * Faculty of Electrical Engineering and Computing（电子工程与计算学院） ； Faculty of Computer and Information Science（计算机与信息科学学院）
Comments ICCV 2025 Findings Workshop
IGD: Instructional Graphic Design with Multimodal Layer Generation
机构 * University of Science and Technology of China（中国科学技术大学） ； YuanShi Technology（元世科技） ； Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）
Comments ICCV 2025
Measuring the Impact of Rotation Equivariance on Aerial Object Detection
机构 * Xidian University（西电大学） ； National University of Defense Technology（国防科技大学）
Comments Accepted by ICCV 2025
Resolution Revolution: A Physics-Guided Deep Learning Framework for Spatiotemporal Temperature Reconstruction
机构 * University of Southern California（南加州大学）
Comments ICCV 2025 Workshop SEA -- International Conference on Computer Vision 2025 Workshop on Sustainability with Earth Observation and AI
Democratizing High-Fidelity Co-Speech Gesture Video Generation
机构 * South China University of Technology（华南理工大学） ； Tencent AI Lab（腾讯AI实验室）
Comments ICCV 2025
Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation
机构 * Wuhan University（武汉大学）
Comments Accepted by ICCV 2025 Workshop LSVOS
RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction
机构 * Fraunhofer Heinrich-Hertz-Institut, HHI（弗劳恩霍夫海因里希-赫兹研究所）
Comments ICCV 2025
Information-Bottleneck Driven Binary Neural Network for Change Detection
机构 * University of Macau（澳门大学） ； Singapore Management University（新加坡管理大学） ； Nanjing University of Science and Technology（南京理工大学）
Comments ICCV 2025 Accepted
On the Robustness Tradeoff in Fine-Tuning
机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Comments Accepted to International Conference on Computer Vision, ICCV 2025
One-shot recognition of any material anywhere using contrastive learning with physics-based rendering
Comments for associated code and dataset, see https://zenodo.org/record/7390166#.Y5ku6mHMJH4 or https://e1.pcloud.link/publink/show?code=kZIiSQZCYU5M4HOvnQykql9jxF4h0KiC5MX and https://icedrive.net/s/A13FWzZ8V2aP9T4ufGQ1N3fBZxDF
Journal ref Proc. IEEE/CVF Int. Conf. on Computer Vision (ICCV), 2023, pp. 23524-23533
Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
机构 * Shanghai Jiao Tong University（上海交通大学） ； OPPO AI Center（OPPO人工智能中心）
Comments Accepted by ICCV 2025
Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive
机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（多媒体可信感知与高效计算重点实验室，教育部，厦门大学）
Comments Accepted by ICCV 2025
Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions
机构 * Shandong University（山东大学） ； Xi’an Jiaotong University（西安交通大学） ； Peking University（北京大学） ； Pazhou Laboratory (Huangpu)（黄埔实验室）
Comments ICCV 2025
Free-running vs. Synchronous: Single-Photon Lidar for High-flux 3D Imaging
Comments 20 pages, 15 figures, to be presented at the International Conference on Computer Vision (ICCV) 2025
Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves
机构 * California Institute of Technology（加州理工学院）
Comments ICCV 2025
Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning
机构 * VCIP, CS, Nankai University（VCIP、计算机科学系、南开大学） ； NKIARI, Shenzhen Futian（NKIARI、深圳福田）
Comments Accepted at ICCV 2025
Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
机构 * South China University of Technology（华南理工大学） ； Alibaba International Digital Commerce Group（阿里巴巴国际数字商务集团） ； Pazhou Lab（琶洲实验室） ； Nanyang Technological University（南洋理工大学）
Comments Accepted by ICCV 2025
PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection
机构 * Queen’s University（皇后大学）
Comments Accepted to ICCV 2025
LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching
机构 * Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China（北京智能信息技术重点实验室，计算机科学与技术学院，北京理工大学，中国） ； Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China（广东机器感知与智能计算实验室，深圳MSU-BIT大学，中国） ； Beijing Research Center of Intelligent Equipment for Agriculture, China（北京智能农业设备研究中心，中国）
Comments accepted by ICCV 2025
