Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
机构 * The University of Sydney（悉尼大学） ； Macquarie University（麦觉瑞大学）
Comments Accepted to ICCV 2025
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
机构 * Simon Fraser University（西蒙弗雷泽大学） ； National Research Council Canada（加拿大国家研究理事会）
Comments Accepted to ICCV 2025
Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning
机构 * School of Computer Science and Technology, Huazhong University of Science and Technology（计算机科学与技术学院，华中科技大学）
Comments Accepted to ICCV 2025, 11 pages
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Comments Accepted to ICCV 2025
EgoM2P: Egocentric Multimodal Multitask Pretraining
机构 * ETH Zürich（苏黎世联邦理工学院） ； Zhejiang University（浙江大学） ； Microsoft（微软公司）
Comments Accepted by ICCV 2025
Controllable Weather Synthesis and Removal with Video Diffusion Models
机构 * NVIDIA ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Toronto（多伦多大学） ； Vector Institute（向量研究所）
Comments International Conference on Computer Vision (ICCV) 2025, Project Website: https://research.nvidia.com/labs/toronto-ai/WeatherWeaver/
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
机构 * Samsung Research（三星研究）
Comments Camera ready version for ICCV 2025, 30 pages, 20 figures, project page : https://cubeyoung.github.io/pladis-proejct/
Advancing Textual Prompt Learning with Anchored Attributes
机构 * PCA Lab, VCIP, College of Computer Science, Nankai University（PCA实验室、VCIP、计算机科学学院、南开大学） ； DAMO Academy, Alibaba Group（达摩院、阿里巴巴集团）
Comments ICCV 2025. Code: https://github.com/zhengli97/ATPrompt. Project Page: https://zhengli97.github.io/ATPrompt/
CABLD: Contrast-Agnostic Brain Landmark Detection with Consistency-Based Regularization
机构 * Department of Computer Science and Software Engineering, Concordia University（计算机科学与软件工程系，康科迪亚大学） ； Department of Electrical and Computer Engineering, Concordia University（电气与计算机工程系，康科迪亚大学）
Comments Accepted to ICCV 2025
Fourier Domain Adaptation for Traffic Light Detection in Adverse Weather
Comments Accepted at the 2COOOL Workshop, ICCV 2025
Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics
机构 * National University of Defense Technology（国防科技大学）
Comments Accepted by ICCV 2025. Code: https://github.com/zhirui-gao/PartGS
UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomography
机构 * Vellore Institute of Technology（沃洛雷理工学院） ； Shiv Nadar University（施瓦尔纳大学）
Comments 18 pages, 10 figures, 5 tables, 2025 ICCV Workshops
Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Dataset
机构 * Eindhoven University of Technology（埃因霍温理工大学）
Comments accepted at ICCV'25 workshop CV4BIOM
Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning
机构 * UNIST（全南国立科学技术大学） ； DeepBrain AI ； NVIDIA Foundation Models LAB, MODULABS（NVIDIA基础模型实验室，MODULABS）
Comments 6th CLVISION ICCV Workshop accepted
FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning
机构 * School of Computing and Information Technology, University of Wollongong, Wollongong, Australia（新南威尔士大学计算机与信息科技学院） ； School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia（悉尼大学电子与计算机工程学院） ； QLD Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, Australia（昆士兰大学昆士兰农业与食品创新联盟）
Comments 11 Pages, ICCV 2025
SIC: Similarity-Based Interpretable Image Classification with Neural Networks
机构 * Lab for Artificial Intelligence in Medical Imaging, Technical University of Munich, Germany（医学影像中人工智能实验室，慕尼黑技术大学，德国） ； Munich Center for Machine Learning (MCML), Germany（慕尼黑机器学习中心（MCML），德国）
Comments Accepted at ICCV 2025
Smart Routing for Multimodal Video Retrieval: When to Search What
机构 * Cloudglue
Comments Accepted to ICCV 2025 Multimodal Representation and Retrieval Workshop
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
机构 * College of Computer Science and Technology, Harbin Engineering University（哈尔滨工程大学计算机科学与技术学院） ； Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院） ； School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院） ； State Key Laboratory of Space-Ground Integrated Information Technology（空间地面一体化信息技术创新实验室）
Comments ICCV 2025 Accept, Project page: https://danceba.github.io/
Accelerating Diffusion Transformer via Gradient-Optimized Cache
机构 * University of Science and Technology of China（中国科学技术大学） ； Hefei University of Technology（合肥工业大学）
Journal ref ICCV 2025
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy
机构 * Xi’an University of Architecture and Technology（西安建筑科技大学） ； University of Electronic Science and Technology of China（电子科技大学） ； Northwestern Polytechnical University（西北工业大学） ； TongJi University（同济大学）
Comments This paper is accepted by ICCV 2025
GLAD: Generalizable Tuning for Vision-Language Models
机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） ； Northeastern University（东北大学） ； The Hong Kong Polytechnic University（香港理工大学） ； Shenzhen University of Advanced Technology（深圳先进技术大学）
Comments ICCV 2025 workshop
Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
机构 * Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院） ； School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
Comments Accepted by ICCV 2025
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
机构 * KAIST（韩国科学技术院）
Comments Accepted by ICCV 2025
CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling
机构 * University of Arkansas（亚拉巴马大学） ； University of Houston（休斯顿大学） ； University of Science VNU-HCM（越南国家大学VNU-HCM） ； FPT Software（FPT软件公司） ； Auburn University（阿伯丁大学） ； University of Liverpool（利物浦大学） ； MD Anderson Cancer Center（MD安德森癌症中心）
Comments ICCV 2025
MMOne: Representing Multiple Modalities in One Scene
机构 * Spatial Intelligence Group, The Hong Kong Polytechnic University（香港理工大学空间智能组）
Comments Accepted to ICCV 2025
Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
机构 * The University of Tokyo（东京大学） ； University of Toronto（多伦多大学）
Comments Accepted by The ICCV 2025 Workshop on Curated Data for Efficient Learning
EchoNet-Quality: Denoising Echocardiograms via Deep Generative Modeling of Ultrasound Noise
Comments Accepted to ICCV 2025 Workshop CVAMD
MRGen: Segmentation Data Engine for Underrepresented MRI Modalities
机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Comments Accepted by ICCV 2025; Project Page: https://haoningwu3639.github.io/MRGen/
PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning
机构 * STEM University of South Australia（南澳大利亚STEM大学） ； Institute for Infocomm Research, A*STAR & IPAL（信息与通信研究所，A*STAR及IPAL） ； Systems Research Institute, Polish Academy of Sciences（波兰科学院系统研究所）
Comments ICCV 2025
Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement
机构 * University of Electronic Science and Technology of China（电子科技大学）
Comments Accepted to ICCV 2025
