ICCV

Context Guided Transformer Entropy Modeling for Video Compression

Junlong Tong, Wei Zhang, Yaohui Jin, Xiaoyu Shen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室） ； Institute of Digital Twin（数字孪生研究院） 纠错

Comments ICCV 2025. This is an update to the camera-ready version

Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models

Anita Kriz, Elizabeth Laura Janes, Xing Shen, Tal Arbel

机构 * McGill University（麦吉尔大学） ； Mila – Quebec AI Institute（魁北克AI研究所） 纠错

Comments Accepted to ICCV 2025 Workshop CVAMD

DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy

Ming Dai, Wenxuan Cheng, Jiang-jiang Liu, Sen Yang, Wenxiao Cai, Yanpeng Sun, Wankou Yang

机构 * Southeast University（东南大学） ； Baidu VIS（百度VIS） ； Stanford University（斯坦福大学） 纠错

Comments Accepted by ICCV 2025

BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning

Shengao Wang, Arjun Chandra, Aoming Liu, Venkatesh Saligrama, Boqing Gong

机构 * Boston University（波士顿大学） 纠错

Comments Accepted to ICCV 2025

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Nupur Kumari, Xi Yin, Jun-Yan Zhu, Ishan Misra, Samaneh Azadi

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Meta 纠错

Comments ICCV 2025. Project webpage: https://www.cs.cmu.edu/~syncd-project/

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement

Jieming Bian, Lei Wang, Letian Zhang, Jie Xu

机构 * University of Florida（佛罗里达大学） ； Middle Tennessee State University（中田纳西州立大学） 纠错

Comments ICCV 2025, Code is available: https://github.com/jmbian/LoRA-FAIR

SMC++: Masked Learning of Unsupervised Video Semantic Compression

Yuan Tian, Xiaoyue Ling, Cong Geng, Qiang Hu, Guo Lu, Guangtao Zhai

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； JIUTIAN Research（JIUTIAN研究） ； Cooperative Medianet Innovation Center（协作中继创新中心） ； Shanghai Jiao Tong University（上海交通大学） ； Institute of Image Communication and Network Engineering（图像通信与网络工程研究所） 纠错

Comments Accepted to TPAMI; Substantial Extension of ICCV 2023 paper

Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification

Haohua Dong, Ana Manzano Rodríguez, Camille Guinaudeau, Shin'ichi Satoh

机构 * National Institute of Informatics, Japan（日本信息机构国家研究所） ； INESC-ID, Instituto Superior Técnico, University of Lisbon, Portugal（里斯本大学技术高等学院、INESC-ID，葡萄牙） ； University of Amsterdam, The Netherlands（荷兰阿姆斯特丹大学） ； LIMSI, CNRS / Université Paris-Saclay, France（法国CNRS/巴黎萨克雷大学LIMSI） 纠错

Comments 8 pages. Accepted for publication in the ICCV 2025 Workshop Proceedings (2nd FAILED Workshop). Also available on HAL (hal-05210445v1)

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Kuangpu Guo, Lijun Sheng, Yongcan Yu, Jian Liang, Zilei Wang, Ran He

机构 * University of Science and Technology of China（中国科学技术大学） ； NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） 纠错

Comments Accepted by ICCV 2025

{S\textsuperscript{2}M\textsuperscript{2}}: Scalable Stereo Matching Model for Reliable Depth Estimation

Junhong Min, Youngpil Jeon, Jimin Kim, Minyong Choi

机构 * Samsung Electronics（三星电子） 纠错

Comments 8 pages, 5 figures, ICCV accepted paper

Blind Video Super-Resolution based on Implicit Kernels

Qiang Zhu, Yuxuan Jiang, Shuyuan Zhu, Fan Zhang, David Bull, Bing Zeng

机构 * University of Electronic Science and Technology of China（电子科技大学） ； University of Bristol（布里斯托大学） 纠错

Comments Accepted by ICCV 2025

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

Yuanhao Cai, He Zhang, Kai Zhang, Yixun Liang, Mengwei Ren, Fujun Luan, Qing Liu, Soo Ye Kim, Jianming Zhang, Zhifei Zhang, Yuqian Zhou, Yulun Zhang, Xiaokang Yang, Zhe Lin, Alan Yuille

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Adobe Research（Adobe研究） ； HKUST（香港科技大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments ICCV 2025; A novel one-stage 3DGS-based diffusion for 3D object generation and scene reconstruction from a single view in ~6 seconds

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

Wenyao Zhang, Hongsi Liu, Bohan Li, Jiawei He, Zekun Qi, Yunnan Wang, Shengyang Zhao, Xinqiang Yu, Wenjun Zeng, Xin Jin

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（人工智能 MOE 实验室，上海交通大学人工智能学院） ； Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China（宁波数字孪生研究所，东技术研究所，宁波，中国） ； Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Ningbo, China（宁波空间智能与数字衍生关键实验室，宁波，中国） ； University of Science and Technology of China（中国科学技术大学） ； CASIA ； Tsinghua University（清华大学） 纠错

Comments ICCV 2025

TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis

Tri Ton, Ji Woo Hong, Chang D. Yoo

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） 纠错

Comments Accepted to ICCV 2025. Please visit our project page at https://triton99.github.io/taro-site/

ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition

Sanjoy Kundu, Shanmukha Vellamcheti, Sathyanarayanan N. Aakur

机构 * CSSE Department, Auburn University（计算机科学与工程系，阿伯丁大学） 纠错

Comments Accepted to ICCV 2025. 17 pages, 6 figures, 3 tables

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

Youwei Zheng, Yuxi Ren, Xin Xia, Xuefeng Xiao, Xiaohua Xie

机构 * Sun Yat-sen University（中山大学） ； ByteDance Intelligent Creation（字节跳动智能创作） ； ByteDance Seed Vision（字节跳动种子视觉） ； Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室） ； Pazhou Lab (Huangpu)（琶洲实验室（黄埔）） 纠错

Comments Accepted by ICCV 2025

Modeling Time-Lapse Trajectories to Characterize Cranberry Growth

Ronan John, Anis Chihoub, Ryan Meegan, Gina Sidelli, Jeffery Neyhart, Peter Oudemans, Kristin Dana

Comments Accepted to ICCV Workshops 2025

RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation

Xianfeng Tan, Yuhan Li, Wenxiang Shang, Yubo Wu, Jian Wang, Xuanhong Chen, Yi Zhang, Ran Lin, Bingbing Ni

机构 * Shanghai Jiao Tong University（上海交通大学） ； Alibaba Group（阿里巴巴集团） 纠错

Comments Accept by ICCV 2025 (Highlight). Project website: https://colorful-liyu.github.io/RAGDiffusion-page/

Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration

Darshan Thaker, Abhishek Goyal, René Vidal

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

Comments Accepted at International Conference on Computer Vision (ICCV) 2025

ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classification

Alvaro Lopez Pellicer, Andre Mariucci, Plamen Angelov, Marwan Bukhari, Jemma G. Kerns

机构 * School of Computing and Communications（计算与通讯学院） ； Lancaster Medical School（兰卡斯特医学学院） 纠错

Comments ICCV 2025 (PHAROS-AFE-AIMI: Adaptation, Fairness, and Explainability in Medical Imaging). 8 pages, 5 figures, 4 tables. Keywords: multi-modal, multimodal, prototype learning, explainable AI, interpretable models, case-based reasoning, medical imaging, DEXA, bone health, osteoporosis, osteopenia, diagnosis, classification, clustering

Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data

Aditya Chakravarty

Journal ref ICCV 2025 Workshop on Sustainability with Earth observation and AI

Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes

Sarosij Bose, Arindam Dutta, Sayak Nag, Junge Zhang, Jiachen Li, Konstantinos Karydis, Amit K. Roy Chowdhury

机构 * University of California, Riverside, USA（加州大学河滨分校） 纠错

Comments ICCV 2025

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking

Inzamamul Alam, Md Tanvir Islam, Khan Muhammad, Simon S. Woo

机构 * Sungkyunkwan University（顺天大学） 纠错

Comments ICCV 2025 Accepted Paper

Online Generic Event Boundary Detection

Hyungrok Jung, Daneul Kim, Seunggyun Lim, Jeany Son, Jonghyun Choi

机构 * GIST（韩国科学技术院） ； Seoul National University（首尔国立大学） ； POSTECH 纠错

Comments ICCV 2025

Lattice-allocated Real-time Line Segment Feature Detection and Tracking Using Only an Event-based Camera

Mikihiro Ikura, Arren Glover, Masayoshi Mizuno, Chiara Bartolozzi

机构 * Istituto Italiano di Tecnologia（意大利技术研究院） ； Sony Interactive Entertainment Inc.（索尼互动娱乐公司） 纠错

Comments 12 pages, 13 figures, 6 tables, ICCV Workshop NeVi2025

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance

Jaeseok Jeong, Junho Kim, Gayoung Lee, Yunjey Choi, Youngjung Uh

机构 * Yonsei University（延世大学） ； NAVER AI Lab（NAVER AI实验室） 纠错

Comments Accepted to ICCV 2025; CVPRW AI4CC 2024 (Best Paper + Oral)

Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts

Ibtihel Amara, Ahmed Imtiaz Humayun, Ivana Kajic, Zarana Parekh, Natalie Harris, Sarah Young, Chirag Nagpal, Najoung Kim, Junfeng He, Cristina Nader Vasconcelos, Deepak Ramachandran, Golnoosh Farnadi, Katherine Heller, Mohammad Havaei, Negar Rostamzadeh

机构 * Google Research（谷歌研究） ； McGill University（麦吉尔大学） ； Rice University（里士满大学） ； Google Deepmind（谷歌DeepMind） 纠错

Comments Accepted for publication at ICCV 2025

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization

Xinye Cao, Hongcan Guo, Jiawen Qian, Guoshun Nan, Chao Wang, Yuqi Pan, Tianhao Hou, Xiaojuan Wang, Yutong Gao

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Minzu University of China（民族大学） 纠错

Comments Accepted by ICCV 2025

Kaputt: A Large-Scale Dataset for Visual Defect Detection

Sebastian Höfer, Dorian Henning, Artemij Amiranashvili, Douglas Morrison, Mariliza Tzes, Ingmar Posner, Marc Matvienko, Alessandro Rennola, Anton Milan

机构 * Amazon, Fulfillment Technologies & Robotics（亚马逊，履约技术与机器人） ； University of Oxford, Applied AI Lab（牛津大学应用人工智能实验室） 纠错

Comments Accepted to ICCV 2025

Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow

Ruyang Liu, Shangkun Sun, Haoran Tang, Ge Li, Wei Gao

机构 * School of Electronic and Computer Engineering, Shenzhen Graduate School, 2 Peng Cheng LaboratoryPeking University（1 电子与计算机工程学院，深圳研究生院，2 深圳鹏城实验室，北京大学） 纠错

Comments Accepted to ICCV' 2025