arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Computer Vision · 会议 · Computer Vision

共收录 4770
2509.02969 2025-09-04 cs.CV cs.MM cs.SI

VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results

Dasong Li, Sizhuo Ma, Hang Hua, Wenjie Li, Jian Wang, Chris Wei Zhou, Fengbin Guan, Xin Li, Zihao Yu, Yiting Lu, Ru-Ling Liao, Yan Ye, Zhibo Chen, Wei Sun, Linhan Cao, Yuqin Cao, Weixia Zhang, Wen Wen, Kaiwei Zhang, Zijian Chen, Fangfang Lu, Xiongkuo Min, Guangtao Zhai, Erjia Xiao, Lingfeng Zhang, Zhenjie Su, Hao Cheng, Yu Liu, Renjing Xu, Long Chen, Xiaoshuai Hao, Zhenpeng Zeng, Jianqin Wu, Xuxu Wang, Qian Yu, Bo Hu, Weiwei Wang, Pinxin Liu, Yunlong Tang, Luchuan Song, Jinxi He, Jiaru Wu, Hanjia Lyu

机构 * Sizhuo Ma(* 作者单位) Hang Hua(* 作者单位) Wenjie Li(* 作者单位) Jian Wang(* 作者单位) Chris Wei Zhou(* 作者单位) Fengbin Guan(* 作者单位) Xin Li(* 作者单位) Zihao Yu(* 作者单位) Yiting Lu(* 作者单位) Ru-Ling Liao(* 作者单位) Yan Ye(* 作者单位) Zhibo Chen(* 作者单位) Wei Sun(* 作者单位) Linhan Cao(* 作者单位) Yuqin Cao(* 作者单位) Weixia Zhang(* 作者单位) Wen Wen(* 作者单位) Kaiwei Zhang(* 作者单位) Zijian Chen(* 作者单位) Fangfang Lu(* 作者单位) Xiongkuo Min(* 作者单位) Guangtao Zhai(* 作者单位) Erjia Xiao(* 作者单位) Lingfeng Zhang(* 作者单位) Zhenjie Su(* 作者单位) Hao Cheng(* 作者单位) Yu Liu(* 作者单位) Renjing Xu(* 作者单位) Long Chen(* 作者单位) Xiaoshuai Hao(* 作者单位) Zhenpeng Zeng(* 作者单位) Jianqin Wu(* 作者单位) Xuxu Wang(* 作者单位) Qian Yu(* 作者单位) Bo Hu(* 作者单位) Weiwei Wang(* 作者单位) Pinxin Liu(* 作者单位) Yunlong Tang(* 作者单位) Luchuan Song(* 作者单位) Jinxi He(* 作者单位) Jiaru Wu(* 作者单位) Hanjia Lyu(* 作者单位)

Comments ICCV 2025 VQualA workshop EVQA track

Journal ref ICCV 2025 Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01028 2025-09-04 cs.CV

CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation

Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan

机构 * University at Buffalo(布法罗大学) Adobe Inc. (ASML)(Adobe公司)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10578 2025-09-04 cs.CR cs.AI

When and Where do Data Poisons Attack Textual Inversion?

Jeremy Styborski, Mingzhi Lyu, Jiayou Lu, Nupur Kapur, Adams Kong

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore(计算与数据科学学院,南洋理工大学,新加坡) Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University, Singapore(快速丰富对象搜索(ROSE)实验室,南洋理工大学,新加坡)

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18368 2025-09-04 cs.CV

Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection

Anja Delić, Matej Grcić, Siniša Šegvić

机构 * University of Zagreb, Faculty of Electrical Engineering and Computing(Zagreb大学,电子工程与计算学院)

Comments ICCV 2025 Highlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14494 2025-09-04 cs.CV

Deeply Supervised Flow-Based Generative Models

Inkyu Shin, Chenglin Yang, Liang-Chieh Chen

机构 * ByteDance Seed(字节跳动种子)

Comments Accepted to ICCV 2025. Project website at https://deepflow-project.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12615 2025-09-04 cs.CV cs.LG

LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization

Alessio Spagnoletti, Jean Prost, Andrés Almansa, Nicolas Papadakis, Marcelo Pereyra

Comments 27 pages, 24 figures, International Conference on Computer Vision, ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02512 2025-09-03 cs.LG

MoPEQ: Mixture of Mixed Precision Quantized Experts

Krishna Teja Chitty-Venkata, Jie Ye, Murali Emani

机构 * Argonne National Laboratory(阿贡国家实验室) Illinois Institute of Technology(伊利诺伊理工学院)

Comments Accepted by ICCV Bivision Workshop 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02101 2025-09-03 cs.CV cs.AI

SALAD -- Semantics-Aware Logical Anomaly Detection

Matic Fučka, Vitjan Zavrtanik, Danijel Skočaj

机构 * University of Ljubljana, Faculty of Computer and Information Science(卢布尔雅那大学计算机与信息科学学院)

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01864 2025-09-03 cs.CV

Latent Gene Diffusion for Spatial Transcriptomics Completion

Paula Cárdenas, Leonardo Manrique, Daniela Vega, Daniela Ruiz, Pablo Arbeláez

机构 * Center for Research and Formation in Artificial Intelligence(人工智能研究与培训中心) Universidad de los Andes(andes大学)

Comments 10 pages, 8 figures. Accepted to CVAMD Workshop, ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01610 2025-09-03 cs.CV

Improving Large Vision and Language Models by Learning from a Panel of Peers

Jefferson Hernandez, Jing Shi, Simon Jenni, Vicente Ordonez, Kushal Kafle

机构 * Rice University(里士大学) Adobe Research(Adobe研究)

Comments Accepted at ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01554 2025-09-03 cs.CV cs.AI cs.LG

Unified Supervision For Vision-Language Modeling in 3D Computed Tomography

Hao-Chih Lee, Zelong Liu, Hamza Ahmed, Spencer Kim, Sean Huver, Vishwesh Nath, Zahi A. Fayad, Timothy Deyer, Xueyan Mei

Comments ICCV 2025 VLM 3d Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01453 2025-09-03 cs.CV

Traces of Image Memorability in Vision Encoders: Activations, Attention Distributions and Autoencoder Losses

Ece Takmaz, Albert Gatt, Jakub Dotlacil

机构 * Institute for Language Sciences, Department of Languages, Literature and Communication, Utrecht University(乌特勒支大学语言科学研究所) Department of Information and Computing Sciences, Utrecht University(乌特勒支大学信息与计算科学系)

Comments Accepted to the ICCV 2025 workshop MemVis: The 1st Workshop on Memory and Vision (non-archival)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01250 2025-09-03 cs.CV

Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

Xiangdong Zhang, Shaofeng Zhang, Junchi Yan

机构 * School of AI, Shanghai Jiao Tong University(人工智能学院,上海交通大学)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01157 2025-09-03 cs.CV

MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost

Taiga Yamane, Ryo Masumura, Satoshi Suzuki, Shota Orihashi

机构 * NTT Human Informatics Laboratries, NTT Corporation(日本电报电话株式会社人机信息实验室)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01107 2025-09-03 cs.CV

FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation

Wenzhuang Wang, Yifan Zhao, Mingcan Ma, Ming Liu, Zhonglin Jiang, Yong Chen, Jia Li

机构 * State Key Laboratory of Virtual Reality Technology and Systems, SCSE&QRI, Beihang University(虚拟现实技术与系统国家重点实验室,北京航空航天大学) Geely Automobile Research Institute (Ningbo) Co., Ltd(吉利汽车研究院(宁波)有限公司)

Comments 21 pages, 19 figures, ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15439 2025-09-03 cs.CV

Aligning Moments in Time using Video Queries

Yogesh Kumar, Uday Agarwal, Manish Gupta, Anand Mishra

机构 * Indian Institute of Technology Jodhpur(印度理工学院贾尔普尔分校) Microsoft(微软公司)

Comments 11 pages, 4 figures, accepted at ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05254 2025-09-03 cs.CV cs.AI

CF3: Compact and Fast 3D Feature Fields

Hyunjoon Lee, Joonkyu Min, Jaesik Park

机构 * Seoul National University(首尔国立大学)

Comments ICCV 2025, Project Page: https://jjoonii.github.io/cf3-website/

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22459 2025-09-03 cs.CV

Exploiting Diffusion Prior for Task-driven Image Restoration

Jaeha Kim, Junghun Oh, Kyoung Mu Lee

机构 * Dept. of ECE&ASRI(电子工程与先进科学研究院部) IPAI(人工智能研究所)

Comments Accepted to ICCV 2025. Code is available at https://github.com/JaehaKim97/EDTR

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10029 2025-09-03 cs.CV cs.LG

Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies

Seokeon Choi, Sunghyun Park, Hyoungwoo Park, Jeongho Kim, Sungrack Yun

机构 * Qualcomm AI Research(高通人工智能研究)

Comments Accepted to ICCV 2025 LIMIT Workshop (4-page short paper). Extended version in preparation

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06075 2025-09-03 cs.CV

Discontinuity-aware Normal Integration for Generic Central Camera Models

Francesco Milano, Manuel López-Antequera, Naina Dhingra, Roland Siegwart, Robert Thiel

Comments Accepted by the IEEE/CVF International Conference on Computer Vision (ICCV) 2025, as highlight. 19 pages, 13 figures, 9 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.20860 2025-09-03 cs.CV

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci

机构 * University of Trento(特伦托大学) University of Bergamo(贝拉姆奥大学) Indian Institute of Technology Bombay(印度班加罗尔理工学院) LNMIIT Jaipur(斋普尔LNMIIT) The University of Queensland(昆士兰大学) Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)

Comments Accepted in ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00527 2025-09-03 cs.CV

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement

Ruitao Wu, Yifan Zhao, Jia Li

机构 * State Key Laboratory of Virtual Reality Technology and Systems, SCSE & QRI, Beihang University(虚拟现实技术与系统国家重点实验室,北京航空航天大学)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00346 2025-09-03 cs.CV

LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables

Xunpeng Yi, Yibing Zhang, Xinyu Xiang, Qinglong Yan, Han Xu, Jiayi Ma

机构 * Electronic Information School, Wuhan University(武汉大学电子信息学院) School of Automation, Southeast University(东南大学自动化学院)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.05063 2025-09-03 cs.CV cs.CL cs.LG

CytoDiff: AI-Driven Cytomorphology Image Synthesis for Medical Diagnostics

Jan Carreras Boada, Rao Muhammad Umer, Carsten Marr

机构 * Institute of AI for Health, Helmholtz Zentrum München - German Research Center for Environmental Health(人工智能与健康研究所,慕尼黑德国环境健康研究中心) Department of Medicine III, Ludwig-Maximilian-University Hospital(第三医学部,路德维希-马克西米利安大学医院) DKTK, German Cancer Consortium(德国癌症联盟,DKTK) Escola Superior de Comerç Internacional, Universitat Pompeu Fabra (ESCI-UPF)(国际商业学校,庞培法布拉大学(ESCI-UPF))

Comments Accepted at ICCV 2025, 7-8 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20491 2025-09-03 cs.CV cs.CL cs.LG

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

Jiale Cheng, Ruiliang Lyu, Xiaotao Gu, Xiao Liu, Jiazheng Xu, Yida Lu, Jiayan Teng, Zhuoyi Yang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang

机构 * The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University(清华大学对话人工智能(CoAI)小组) Zhipu AI(智谱AI) The Knowledge Engineering Group (KEG), Tsinghua University(清华大学知识工程小组(KEG))

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10684 2025-09-03 cs.CV cs.AI

Open-World Skill Discovery from Unsegmented Demonstrations

Jingwen Deng, Zihao Wang, Shaofei Cai, Anji Liu, Yitao Liang

机构 * Peking University(北京大学) University of California, Los Angeles(美国加州大学洛杉矶分校)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.15058 2025-09-03 cs.CV cs.LG eess.IV

MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance

Hallee E. Wong, Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca

机构 * MIT CSAIL(麻省理工学院计算机科学与人工智能实验室) MGH(麻省总医院) Databricks(Databricks公司) MGH,HMS(麻省总医院,哈佛医学院)

Comments Accepted by ICCV 2025. Project Website: https://multiverseg.csail.mit.edu Keywords: interactive segmentation, in-context learning, medical image analysis, biomedical imaging, image annotation, visual prompting

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05548 2025-09-03 cs.CV

Street Gaussians without 3D Object Tracker

Ruida Zhang, Chengxi Li, Chenyangguang Zhang, Xingyu Liu, Haili Yuan, Yanyan Li, Xiangyang Ji, Gim Hee Lee

机构 * Tsinghua University(清华大学) National University of Singapore(新加坡国立大学)

Comments Accepted by ICCV 2025, website: https://lolrudy.github.io/No3DTrackSG/

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.02592 2025-09-03 cs.CV

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, Wentao Zhang

机构 * Shanghai AI Laboratory(上海人工智能实验室) Peking University(北京大学) The University of HongKong(香港大学) Shanghai Jiaotong University(上海交通大学) Beihang University(北京航空航天大学)

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.21824 2025-09-01 cs.CV

DriveQA: Passing the Driving Knowledge Test

Maolin Wei, Wanzhou Liu, Eshed Ohn-Bar

机构 * Boston University(波士顿大学) Washington University in St. Louis(华盛顿大学圣路易斯分校)

Comments Accepted by ICCV 2025. Project page: https://driveqaiccv.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏