ICCV - arXivDaily 期刊&会议

2510.06040 2025-10-08 cs.CV cs.AI

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）

Comments Accepted by ICCV 2025

2510.05903 2025-10-08 cs.CV cs.AI cs.LG

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）

Comments Accepted to ICCV 2025

2510.05836 2025-10-08 cs.CV

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）

Comments Accepted to ICCV' 2025

2508.14599 2025-10-08 cs.CV

Incremental Object Detection with Prompt-based Methods

Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Pani Paudel, Luc Van Gool

机构 * ETH Zürich（苏黎世联邦理工学院）； Bosch Research（博世研究）

Comments Accepted to ICCV Workshops 2025: v2 update affiliation

2508.13878 2025-10-08 cs.CV

RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection

Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Pani Paudel, Luc Van Gool

机构 * ETH Zürich（苏黎世联邦理工学院）； Bosch Research（博世研究）

Comments Accepted to ICCV Workshops 2025; v2: add GitHub link and update affiliation

2504.03501 2025-10-08 cs.CV

LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders

Ilan Naiman, Emanuel Ben-Baruch, Oron Anschel, Alon Shoshan, Igor Kviatkovsky, Manoj Aggarwal, Gerard Medioni

机构 * Amazon（亚马逊）

Comments Accepted to the International Conference on Computer Vision, ICCV 2025

2410.13564 2025-10-08 cs.CV

Imagining the Unseen: Generative Location Modeling for Object Placement

Jooyeol Yun, Davide Abati, Mohamed Omran, Jaegul Choo, Amirhossein Habibian, Auke Wiggers

机构 * Qualcomm AI Research（高通人工智能研究）

Comments Accepted by ICCV 2025 DRL4Real Workshop