WACV

SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark

Marius Kästingschäfer, Théo Gieruc, Sebastian Bernhard, Dylan Campbell, Eldar Insafutdinov, Eyvaz Najafli, Thomas Brox

机构 * Continental ； University of Freiburg（弗赖堡大学） ； Australian National University（澳大利亚国立大学） ； University of Oxford（牛津大学） ； University of Tübingen（图宾根大学） 纠错

Comments WACV 2025. Project page: https://seed4d.github.io/. Code: https://github.com/continental/seed4d

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 7741-7753, 2025

HotSpotter - Patterned Species Instance Recognition

Jonathan P. Crall, Charles V. Stewart, Tanya Y. Berger-Wolf, Daniel I. Rubenstein, Siva R. Sundaresan

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院） ； University of Illinois-Chicago（伊利诺伊大学芝加哥分校） ； Princeton University（普林斯顿大学） ； Denver Zoological Foundation（丹佛动物园基金会） 纠错

Comments Original matlab code: https://github.com/Erotemic/hotspotter-matlab-2013, Python port: https://github.com/Erotemic/hotspotter

Journal ref Proc. IEEE Workshop on Applications of Computer Vision (WACV), pp. 230-237, 2013

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

Krishna Kanth Nakka, Alexandre Alahi

机构 * VITA Lab, EPFL, Switzerland（EPFL生命科学实验室） 纠错

Comments Published at WACV 2025

Localized Gaussian Splatting Editing with Contextual Awareness

Hanyuan Xiao, Yingshu Chen, Huajian Huang, Haolin Xiong, Jing Yang, Pratusha Prasad, Yajie Zhao

机构 * University of Southern California（南加州大学） ； Institute for Creative Technologies（创意科技研究所） ； HKUST（香港科技大学） ； University of California, Los Angeles（加州大学洛杉矶分校） 纠错

Comments WACV 2025

DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos

Ce Zheng, Xianpeng Liu, Qucheng Peng, Tianfu Wu, Pu Wang, Chen Chen

机构 * Carnegie Mellon University（卡内基梅隆大学） ； North Carolina State University（北卡罗来纳州立大学） ； Center for Research in Computer Vision, University of Central Florida（中央佛罗里达大学计算机视觉研究中心） ； University of North Carolina at Charlotte（北卡罗来纳大学教堂山分校） 纠错

Comments WACV 2025

SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting

Pallavi Jain, Dino Ienco, Roberto Interdonato, Tristan Berchoux, Diego Marcos

机构 * Mediterranean Agronomic Institute of Montpellier - CIHEAM-IAMM（地中海农业研究院-CIHEAM-IAMM） ； Inria（法国国家信息与自动化技术研究院） ； INRAE（法国国家农业研究咨询中心） ； Cirad（国际热带农业研究中心） ； UMR TETIS（TETIS联合研究单位） ； Univ. of Montpellier（蒙彼利埃大学） 纠错

Comments Accepted at WACV'25

Generalizable Federated Learning using Client Adaptive Focal Modulation

Tajamul Ashraf, Iqra Altaf Gillani

机构 * Department of Computer Vision（计算机视觉系） ； MBZUAI（穆罕默德·本·拉谢德人工智能研究院） ； Department of Information Technology（信息科技系） ； NIT Srinagar（斋普尔理工学院） 纠错

Comments WACV 2024 Extended Paper

GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo

Vibhas K. Vats, Sripad Joshi, David J. Crandall, Md. Alimoor Reza, Soon-heung Jung

机构 * Indiana University（印第安纳大学） ； Drake University（德拉克大学） ； ETRI 纠错

Comments Accepted in WACV 2024 Link: https://openaccess.thecvf.com/content/WACV2024/html/Vats_GC-MVSNet_Multi-View_Multi-Scale_Geometrically-Consistent_Multi-View_Stereo_WACV_2024_paper.html

Journal ref Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

Texture, Shape, Order, and Relation Matter: A New Transformer Design for Sequential DeepFake Detection

Yunfei Li, Yuezun Li, Baoyuan Wu, Junyu Dong, Guopu Zhu, Siwei Lyu

机构 * University at Buffalo, SUNY（布法罗大学） 纠错

Comments An extension of WACV 2025 (Oral)

Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection

Riku Inoue, Masamitsu Tsuchiya, Yuji Yasui

Comments This paper has been accepted to WACV 2025 (Tucson, Arizona, USA), February 28-March 4 2025

Federated Learning for Commercial Image Sources

Shreyansh Jain, Koteswar Rao Jerripothula

机构 * IIIT Delhi（印度德里理工学院） 纠错

Comments Published in the Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 with DOI: 10.1109/WACV56688.2023.00647

Journal ref 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 6523-6532, 2023

LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization

Marco Paul E. Apolinario, Arani Roy, Kaushik Roy

机构 * Elmore Family School of Electrical and Computer Engineering（埃尔莫尔电气与计算机工程学院） ； Purdue University（普渡大学） 纠错

Comments 12 pages, 4 figures

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025

Unified Face Matching and Physical-Digital Spoofing Attack Detection

Arun Kunwar, Ajita Rattani

机构 * Dept. of Computer Science and Engineering, University of North Texas at Denton, USA（计算机科学与工程系，北德顿大学） 纠错

Journal ref 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pp. 1429-1439

Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation

Christian Witte, Jens Behley, Cyrill Stachniss, Marvin Raaijmakers

机构 * CARIAD SE ； Center for Robotics, University of Bonn（机器人中心，波恩大学） ； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所） 纠错

Comments Accepted at WACV 2025

ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts

Mikołaj Sacha, Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński

机构 * Faculty of Mathematics and Computer Science, Jagiellonian University（数学与计算机科学学院，雅盖隆大学） ； Ardigen ； IDEAS NCBR 纠错

Journal ref Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 1481-1492

SONG: Self-Organizing Neural Graphs

Łukasz Struski, Tomasz Danel, Marek Śmieja, Jacek Tabor, Bartosz Zieliński

机构 * Faculty of Mathematics and Computer Science, Jagiellonian University（杰哥利安大学数学与计算机科学学院） ； IDEAS NCBR 纠错

Comments Accepted in WACV 2023

Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration

Leonard Bruns, Jun Zhang, Patric Jensfelt

Comments WACV 2025, Project page: https://kth-rpl.github.io/neural_graph_mapping/

OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data

Raymond Yu, Paul Han, Josh Myers-Dean, Piper Wolters, Favyen Bastani

机构 * University of Washington（华盛顿大学） ； Allen Institute for AI（人工智能 Allen 研究院） 纠错

Comments WACV 2025

Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs

Filipos Gouidis, Konstantinos Papoutsakis, Theodore Patkos, Antonis Argyros, Dimitris Plexousakis

机构 * Foundation for Research and Technology-Hellas（希腊基础研究与技术研究所） ； University of Crete（克里特大学） ； Hellenic Mediterranean University（希腊地中海大学） 纠错

Comments This is the authors' version of the paper published at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025. The definitive version is available at: https://openaccess.thecvf.com/content/WACV2025/html/Gouidis_Recognizing_Unseen_States_of_Unknown_Objects_by_Leveraging_Knowledge_Graphs_WACV_2025_paper.html

Journal ref 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8637-8648

Leveraging Satellite Image Time Series for Accurate Extreme Event Detection

Heng Fang, Hossein Azizpour

机构 * KTH Royal Institute of Technology（皇家理工学院） 纠错

Comments Accepted to the WACV 2025 Workshop on GeoCV. Code, datasets, and model checkpoints available at: https://github.com/hfangcat/SITS-ExtremeEvents

Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering

Adam Ishay, Zhun Yang, Joohyung Lee, Ilgu Kang, Dongjae Lim

机构 * Arizona State University（亚利桑那州立大学） ； Samsung Research（三星研究） 纠错

Comments In Proceedings the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)

EmoVOCA: Speech-Driven Emotional 3D Talking Heads

Federico Nocentini, Claudio Ferrari, Stefano Berretti

机构 * University of Florence（佛罗伦萨大学） ； University of Parma（帕尔马大学） 纠错

Comments WACV 2025

Leveraging CLIP Encoder for Multimodal Emotion Recognition

Yehun Song, Sunyoung Cho

机构 * Agency for Defense Development（国防发展机构） ； Sookmyung Women’s University（苏镜女子大学） 纠错

Comments Accepted at IEEE/CVF WACV 2025, pp.6115-6124, 2025

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp.6115-6124

UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction

Haoran Wang, Nantheera Anantrasirichai, Fan Zhang, David Bull

机构 * School of Computer Science, University of Bristol（计算机科学学院，布里斯托尔大学） 纠错

Comments Accepted at IEEE/CVF WACV 2025

MVAD: A Multiple Visual Artifact Detector for Video Streaming

Chen Feng, Duolikun Danier, Fan Zhang, Alex Mackin, Andrew Collins, David Bull

机构 * Visual Information Lab, University of Bristol（视觉信息实验室，布里斯托大学） ； Amazon Prime Video（亚马逊Prime视频） 纠错

Comments Paper has been accpeted by WACV 2025

HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images

Zhenyue Qin, Yiqun Zhang, Yang Liu, Dylan Campbell

机构 * Seeing Machines ； Australian National University（澳大利亚国立大学） 纠错

Comments 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Journal ref 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution

Charles Laroche, Andrés Almansa, Eva Coupete

Journal ref 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2024

Combined Physics and Event Camera Simulator for Slip Detection

Thilo Reinold, Suman Ghosh, Guillermo Gallego

机构 * Technische Universität Berlin（柏林技术大学） ； Robotics Institute Germany（德国机器人研究所） ； Einstein Center for Digital Future（爱因斯坦数字未来研究中心） ； Science of Intelligence Excellence Cluster（智能科学卓越集群） 纠错

Comments 9 pages, 8 figures, 2 tables, https://github.com/tub-rip/event_slip

Journal ref Winter Conference on Applications of Computer Vision (WACV) Workshops, Tucson (USA), 2025

CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning

Azin Jahedi, Maximilian Luz, Marc Rivinius, Andrés Bruhn

Comments WACV 2024

YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID

Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera

机构 * Universitat de Barcelona（巴塞罗那大学） ； Computer Vision Center（计算机视觉中心） ； Aalborg University（奥尔堡大学） ； Milestone Systems（Milestone系统） 纠错

Comments This paper has been accepted to the 5th Workshop on Real-World Surveillance: Applications and Challenges (WACV 2025)