Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation
机构 * Rutgers University（新泽西罗格斯大学） ； Stanford University（斯坦福大学）
Comments Accepted to Winter Conference on Applications of Computer Vision (WACV) 2026
期刊&会议
WACV
Winter Conference on Applications of Computer Vision · 会议 · Computer Vision
UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets
机构 * Shiv Nadar Institution of Eminence（希夫纳达机构）
Comments 10 pages, Accepted at IEEE/CVF WACV 2026, Source code is available at this URL https://github.com/Arnavadi19/UCDSC
VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
机构 * University of Luxembourg（卢森堡大学）
Comments WACV 2026
CSF-Net: Context-Semantic Fusion Network for Large Mask Inpainting
机构 * Department of Artificial Intelligence Convergence（人工智能融合系）
Comments 8 pages, 5 figures, Accepted to WACV 2026 (to appear)
Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection
机构 * Johns Hopkins University（约翰霍普金斯大学）
Comments 9 pages, 5 figures. To appear in WACV 2026
CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones
机构 * ISTI-CNR（意大利国家研究委员会ISTI研究所） ； University of Pisa（比萨大学）
Comments [Accepted at WACV 2026] 18 pages, 11 figures, 3 tables. Project website: https://lorebianchi98.github.io/CountingDINO/
ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora
机构 * Heinrich Heine University of Düsseldorf（海因里希-海涅大学杜塞尔多夫分校）
Comments Accepted in WACV 2026. Code in https://github.com/HHU-MMBS/clustermine_wacv_official 9 Tables, 11 Figures
PADM: A Physics-aware Diffusion Model for Attenuation Correction
机构 * AI4LIFE, Hanoi University of Science and Technology, Vietnam（AI4LIFE，越南河内科学技术大学） ； Nagoya Univeristy, Japan（名古屋大学） ； National Institute of Advanced Industrial Science and Technology, Japan（日本国家先进工业科学和技术研究院） ； Military Central Hospital, Vietnam（越南108中央军医院）
Comments IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026
Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes
机构 * German Research Center for Artificial Intelligence（德国人工智能研究中心） ； RPTU（鲁尔蓬德大学） ； Technical University of Munich（慕尼黑技术大学）
Comments WACV 2026, project page: https://dfki-av.github.io/inpaint360gs/
Light Future: Multimodal Action Frame Prediction via InstructPix2Pix
机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳））
Comments 9 pages including appendix, 4 tables, 8 figures, to be submitted to WACV 2026
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
机构 * IDEAS NCBR ； Jagiellonian University, Faculty of Mathematics and Computer Science（雅盖隆大学数学与计算机科学学院） ； Jagiellonian University, Doctoral School of Exact and Natural Sciences（雅盖隆大学精确与自然科学博士学院） ； University of Warsaw（华沙大学） ； Warsaw University of Technology（华沙技术大学） ； Tooploox
Comments WACV 2025
QCFace: Image Quality Control for boosting Face Representation & Recognition
机构 * Faculty of Computer Science and Engineering（计算机科学与工程学院） ； Advanced Institute of Interdisciplinary Science and Technology（跨学科科学与技术高级研究所） ； Ho Chi Minh City University of Technology (HCMUT)（胡志明市技术大学） ； School of Clinical Sciences（临床科学学院） ； Monash University（莫纳什大学） ； Monash Health（莫纳什健康）
Comments 21 pages with 11 figures, 14 tables and 71 references. Accepted in Round 1 at WACV 2026, Oral
BoardVision: Deployment-ready and Robust Motherboard Defect Detection with YOLO+Faster-RCNN Ensemble
机构 * University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Comments This paper has been submitted to IEEE/CVF WACV 2026 Applications track and is currently under review
Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation
机构 * IMATAG, France（法国IMATAG机构） ； IRISA, CNRS, France（法国IRISA与CNRS机构） ； LightOn, France（法国LightOn公司）
Comments This paper has been accepted for the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025; Code released at https://github.com/gautierevn/BLIP2IDC
CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving
机构 * Turing Inc.（图灵公司）
Comments WACV 2025, Project Page: https://turingmotors.github.io/covla-ad/
High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
机构 * École de technologie supérieure（蒙特利尔高等技术学院）
Comments WACV 2026: Winter Conference on Applications of Computer Vision 2026
Domain Generalization by Rejecting Extreme Augmentations
Comments WACV 2024: Winter Conference on Applications of Computer Vision 2024
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data
机构 * NEC Corporation（日本电装公司） ； Kyoto University（京都大学）
Comments Accepted by WACV 2025
Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton Information
机构 * Free University of Bozen-Bolzano（博洛尼亚-博兹纳自由大学）
Comments Accepted at the 2025 Winter Conference on Applications of Computer Vision (WACV) Workshops. Visit the project page at https://edowhite.github.io/Gate-Shift-Pose
AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments WACV submission. 13 pages, including the main text (8 pages), references, and supplementary material
RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis
机构 * POSTECH ； ByteDance Seed（字节跳动种子） ； Meta
Comments 18 pages, 13 figures, Accepted to WACV 2026 Round 1
Tumor Synthesis conditioned on Radiomics
机构 * Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea（延世大学电气与计算机工程系） ； Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Suwon, Korea（延世大学医学院放射科与成像科学中心）
Comments WACV'25
3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
机构 * School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, China（智能工程与自动化学院，北京邮电大学）
Comments Submitted to WACV 2026
SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding
机构 * IIT Ropar（印度IIT罗帕尔） ； Queen Mary University of London（伦敦女王玛丽大学） ； Monash University（墨尔本大学）
Comments Accepted at WACV 2026, project page : https://novicemm.github.io/synchrorama
Synthesizing Artifact Dataset for Pixel-level Detection
机构 * Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电子与计算机工程系） ； Meta
Comments Under submission to WACV
Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods
机构 * Department of Computer Science, University of Bucharest（计算机科学系，布加勒斯特大学）
Comments 27 pages, 26 figures, WACV conference
Experimenting with Affective Computing Models in Video Interviews with Spanish-speaking Older Adults
机构 * Universitat Oberta de Catalunya（开放大学（加泰罗尼亚）） ； Northeastern University（东北大学） ； PAL Robotics（PAL机器人研究所）
Journal ref IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)
Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients
机构 * Computer Vision Group, Friedrich Schiller University Jena（耶拿弗里德里希·施勒尔大学计算机视觉组）
Comments Accepted at WACV-2026, 45 pages, 39 figures, 15 tables
Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
机构 * Robotics Institute, Carnegie Mellon University（机器人研究所，卡内基梅隆大学）
Comments Accepted by WACV 2025. Project page: https://zifuwan.github.io/Sigma/
MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection
机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学、欧洲原子能机构、List）
Comments Accepted at WACV 2026
