1. Home
  2. Proceedings
  3. WACV
  4. WACV 2024
Default Cover Image

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Jan. 3 2024 to Jan. 8 2024

Waikoloa, HI, USA

ISBN: 979-8-3503-1892-0

Table of Contents

Title Page iFreely available from IEEE.pp. 1-1
Title Page iiiFreely available from IEEE.pp. 3-3
Copyright PageFreely available from IEEE.pp. 4-4
Table of ContentsFreely available from IEEE.pp. 5-5
Message from the General and Program ChairsFreely available from IEEE.pp. 6-6
Organizing Committee and Area ChairsFreely available from IEEE.pp. 7-7
SponsorsFreely available from IEEE.pp. 8-8
Asymmetric Image Retrieval with Cross Model Compatible EnsemblesFull-text access may be available. Sign in or learn about subscription options.pp. 1-11
by Alon Shoshan, Ori Linial, Nadav Bhonker, Elad Hirsch, Lior Zamir, Igor Kviatkovsky, Gérard Medioni
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous DataFull-text access may be available. Sign in or learn about subscription options.pp. 12-21
by Sai Aparna Aketi, Kaushik Roy
Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality AssessmentFull-text access may be available. Sign in or learn about subscription options.pp. 22-31
by Suhas Srinath, Shankhanil Mitra, Shika Rao, Rajiv Soundararajan
Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental LearningFull-text access may be available. Sign in or learn about subscription options.pp. 32-41
by Jayateja Kalla, Soma Biswas
PECoP: Parameter Efficient Continual Pretraining for Action Quality AssessmentFull-text access may be available. Sign in or learn about subscription options.pp. 42-52
by Amirhossein Dadashzadeh, Shuchao Duan, Alan Whone, Majid Mirmehdi
Wino Vidi Vici: Conquering Numerical Instability of 8-bit Winograd Convolution for Accurate Inference Acceleration on EdgeFull-text access may be available. Sign in or learn about subscription options.pp. 53-62
by Pierpaolo Mori, Lukas Frickenstein, Shambhavi Balamuthu Sampath, Moritz Thoma, Nael Fasfous, Manoj Rohit Vemparala, Alexander Frickenstein, Christian Unger, Walter Stechele, Daniel Mueller-Gritschneder, Claudio Passerone
Data-Centric Debugging: mitigating model failures via targeted image retrievalFull-text access may be available. Sign in or learn about subscription options.pp. 63-74
by Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri, Soheil Feizi
Distortion-Disentangled Contrastive LearningFull-text access may be available. Sign in or learn about subscription options.pp. 75-85
by Jinfeng Wang, Sifan Song, Jionglong Su, S. Kevin Zhou
GTP-ViT: Efficient Vision Transformers via Graph-based Token PropagationFull-text access may be available. Sign in or learn about subscription options.pp. 86-95
by Xuwei Xu, Sen Wang, Yudong Chen, Yanping Zheng, Zhewei Wei, Jiajun Liu
SequenceMatch Revisiting the design of weak-strong augmentations for Semi-supervised learningFull-text access may be available. Sign in or learn about subscription options.pp. 96-105
by Khanh-Binh Nguyen
Stochastic Binary Network for Universal Domain AdaptationFull-text access may be available. Sign in or learn about subscription options.pp. 106-115
by Saurabh Kumar Jain, Sukhendu Das
Location-Aware Self-Supervised Transformers for Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 116-126
by Mathilde Caron, Neil Houlsby, Cordelia Schmid
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level LatenciesFull-text access may be available. Sign in or learn about subscription options.pp. 127-137
by Kilian Batzner, Lars Heckler, Rebecca König
Efficient Semantic Matching with Hypercolumn CorrelationFull-text access may be available. Sign in or learn about subscription options.pp. 138-147
by Seungwook Kim, Juhong Min, Minsu Cho
Contextual Affinity Distillation for Image Anomaly DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 148-157
by Jie Zhang, Masanori Suganuma, Takayuki Okatani
Offline-to-Online Knowledge Distillation for Video Instance SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 158-167
by Hojin Kim, Seunghun Lee, Hyeon Kang, Sunghoon Im
Disentangled Pre-training for Image MattingFull-text access may be available. Sign in or learn about subscription options.pp. 168-177
by Yanda Li, Zilong Huang, Gang Yu, Ling Chen, Yunchao Wei, Jianbo Jiao
Conditional Velocity Score Estimation for Image RestorationFull-text access may be available. Sign in or learn about subscription options.pp. 178-187
by Ziqiang Shi, Rujie Liu
ARNIQA: Learning Distortion Manifold for Image Quality AssessmentFull-text access may be available. Sign in or learn about subscription options.pp. 188-197
by Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini, Alberto Del Bimbo
Hard Sample-aware Consistency for Low-resolution Facial Expression RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 198-207
by Bokyeung Lee, Kyungdeuk Ko, Jonghwan Hong, Hanseok Ko
ArcGeo: Localizing Limited Field-of-View Images using Cross-view MatchingFull-text access may be available. Sign in or learn about subscription options.pp. 208-217
by Maxim Shugaev, Ilya Semenov, Kyle Ashley, Michael Klaczynski, Naresh Cuntoor, Mun Wai Lee, Nathan Jacobs
Open-Set Object Detection By Aligning Known Class RepresentationsFull-text access may be available. Sign in or learn about subscription options.pp. 218-227
by Hiran Sarkar, Vishal Chudasama, Naoyuki Onoe, Pankaj Wasnik, Vineeth N Balasubramanian
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 228-238
by Inkyu Shin, Dahun Kim, Qihang Yu, Jun Xie, Hong-Seok Kim, Bradley Green, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
DeVOS: Flow-Guided Deformable Transformer for Video Object SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 239-248
by Volodymyr Fedynyak, Yaroslav Romanus, Bohdan Hlovatskyi, Bohdan Sydor, Oles Dobosevych, Igor Babin, Roman Riazantsev
Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix AugmentationFull-text access may be available. Sign in or learn about subscription options.pp. 249-258
by Md Awsafur Rahman, Shaikh Anowarul Fattah
Training Ensembles with Inliers and Outliers for Semi-supervised Active LearningFull-text access may be available. Sign in or learn about subscription options.pp. 259-268
by Vladan Stojnić, Zakaria Laskar, Giorgos Tolias
Multi-view Classification Using Hybrid Fusion and Mutual DistillationFull-text access may be available. Sign in or learn about subscription options.pp. 269-279
by Samuel Black, Richard Souvenir
Amodal Intra-class Instance Segmentation: Synthetic Datasets and BenchmarkFull-text access may be available. Sign in or learn about subscription options.pp. 280-289
by Jiayang Ao, Qiuhong Ke, Krista A. Ehinger
Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 290-301
by Balamurali Murugesan, Rukhshanda Hussain, Rajarshi Bhattacharya, Ismail Ben Ayed, Jose Dolz
RSMPNet: Relationship Guided Semantic Map PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 302-311
by Jingwen Sun, Jing Wu, Ze Ji, Yu-Kun Lai
3SD: Self-Supervised Saliency Detection With No LabelsFull-text access may be available. Sign in or learn about subscription options.pp. 312-321
by Rajeev Yasarla, Renliang Weng, Wongun Choi, Vishal M. Patel, Amir Sadeghian
Training-free Object Counting with PromptsFull-text access may be available. Sign in or learn about subscription options.pp. 322-330
by Zenglin Shi, Ying Sun, Mengmi Zhang
Unsupervised and semi-supervised co-salient object detection via segmentation frequency statisticsFull-text access may be available. Sign in or learn about subscription options.pp. 331-341
by Souradeep Chakraborty, Shujon Naha, Muhammet Bastan, Amit Kumar K C, Dimitris Samaras
Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd CountingFull-text access may be available. Sign in or learn about subscription options.pp. 342-351
by Zheng Xiong, Liangyu Chai, Wenxi Liu, Yongtuo Liu, Sucheng Ren, Shengfeng He
TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 352-361
by Yahia Dalbah, Jean Lahoud, Hisham Cholakkal
Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with AttentionFull-text access may be available. Sign in or learn about subscription options.pp. 362-371
by Jinwoo Hwang, Philipp Benz, Pete Kim
360BEV: Panoramic Semantic Mapping for Indoor Bird’s-Eye ViewFull-text access may be available. Sign in or learn about subscription options.pp. 372-381
by Zhifeng Teng, Jiaming Zhang, Kailun Yang, Kunyu Peng, Hao Shi, Simon Reiß, Ke Cao, Rainer Stiefelhagen
Learning Saliency From FixationsFull-text access may be available. Sign in or learn about subscription options.pp. 382-392
by Yasser Abdelaziz Dahou Djilali, Kevin McGuinness, Noel O’Connor
Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReIDFull-text access may be available. Sign in or learn about subscription options.pp. 393-402
by Qilei Li, Shaogang Gong
MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) DecoderFull-text access may be available. Sign in or learn about subscription options.pp. 403-412
by Md Motiur Rahman, Shiva Shokouhmand, Smriti Bhatt, Miad Faezipour
Small Objects Matters in Weakly-supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 413-422
by Cheolhyun Mun, Sanghuk Lee, Youngjung Uh, Junsuk Choe, Hyeran Byun
Gradient-Guided Knowledge Distillation for Object DetectorsFull-text access may be available. Sign in or learn about subscription options.pp. 423-432
by Qizhen Lan, Qing Tian
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 433-442
by Beoungwoo Kang, Seunghun Moon, Yubin Cho, Hyunwoo Yu, Suk-Ju Kang
Panelformer: Sewing Pattern Reconstruction from 2D Garment ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 443-452
by Cheng-Hsiu Chen, Jheng-Wei Su, Min-Chun Hu, Chih-Yuan Yao, Hung-Kuo Chu
From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 453-463
by Ruxue Wen, Hangjie Yuan, Dong Ni, Wenbo Xiao, Yaoyao Wu
Guided Distillation for Semi-Supervised Instance SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 464-472
by Tariq Berrada, Camille Couprie, Karteek Alahari, Jakob Verbeek
Real-Time User-guided Adaptive Colorization with Vision TransformerFull-text access may be available. Sign in or learn about subscription options.pp. 473-482
by Gwanghan Lee, Saebyeol Shin, Taeyoung Na, Simon S. Woo
Mining and Unifying Heterogeneous Contrastive Relations for Weakly-Supervised Actor-Action SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 483-492
by Bin Duan, Hao Tang, Changchang Sun, Ye Zhu, Yan Yan
Graph Neural Networks for End-to-End Information Extraction from Handwritten DocumentsFull-text access may be available. Sign in or learn about subscription options.pp. 493-501
by Yessine Khanfir, Marwa Dhiaf, Emna Ghodhbani, Ahmed Cheikh Rouhou, Yousri Kessentini
CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language PromptingFull-text access may be available. Sign in or learn about subscription options.pp. 502-511
by Lei Li
Foundation Model Assisted Weakly Supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 512-521
by Xiaobo Yang, Xiaojin Gong
On the Importance of Large Objects in CNN Based Object Detection AlgorithmsFull-text access may be available. Sign in or learn about subscription options.pp. 522-531
by Ahmed Ben Saad, Gabriele Facciolo, Axel Davy
Deep Metric Learning with Chance ConstraintsFull-text access may be available. Sign in or learn about subscription options.pp. 532-542
by Yeti Z. Gürbüz, Oğul Can, A. Aydın Alatan
TransFed: A way to epitomize Focal Modulation using Transformer-based Federated LearningFull-text access may be available. Sign in or learn about subscription options.pp. 543-552
by Tajamul Ashraf, Fuzayil Bin Afzal Mir, Iqra Altaf Gillani
Learning Better Keypoints for Multi-Object 6DoF Pose EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 553-563
by Yangzheng Wu, Michael Greenspan
Object Aware Contrastive Prior for Interactive Image SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 564-573
by Praful Mathur, Shashi Kumar Parwani, Mrinmoy Sen, Roopa Sheshadri, Aman Sharma
Beyond Classification: Definition and Density-based Estimation of Calibration in Object DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 574-583
by Teodora Popordanoska, Aleksei Tiulpin, Matthew B. Blaschko
FAKD: Feature Augmented Knowledge Distillation for Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 584-594
by Jianlong Yuan, Minh Hieu Phan, Liyang Liu, Yifan Liu
Efficient MAE towards Large-Scale Vision TransformersFull-text access may be available. Sign in or learn about subscription options.pp. 595-604
by Qiu Han, Gongjie Zhang, Jiaxing Huang, Peng Gao, Zhang Wei, Shijian Lu
MS-EVS: Multispectral event-based vision for deep learning based face detectionFull-text access may be available. Sign in or learn about subscription options.pp. 605-614
by Saad Himmi, Vincent Parret, Ajad Chhatkuli, Luc Van Gool
Interactive Network Perturbation between Teacher and Students for Semi-Supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 615-624
by Hyuna Cho, Injun Choi, Suha Kwak, Won Hwa Kim
Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location ReasoningFull-text access may be available. Sign in or learn about subscription options.pp. 625-634
by Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp
USDN: A Unified Sample-wise Dynamic Network with Mixed-Precision and Early-ExitFull-text access may be available. Sign in or learn about subscription options.pp. 635-643
by Ji-Ye Jeon, Xuan Truong Nguyen, Soojung Ryu, Hyuk-Jae Lee
Beyond Fusion: Modality Hallucination-based Multispectral Fusion for Pedestrian DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 644-653
by Qian Xie, Ta-Ying Cheng, Jia-Xing Zhong, Kaichen Zhou, Andrew Markham, Niki Trigoni
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 654-663
by Fangchen Yu, Yina Xie, Lei Wu, Yafei Wen, Guozhi Wang, Shuai Ren, Xiaoxin Chen, Jianfeng Mao, Wenye Li
Learning to Recognize Occluded and Small Objects with Partial InputsFull-text access may be available. Sign in or learn about subscription options.pp. 664-673
by Hasib Zunair, A. Ben Hamza
Temporally-Consistent Video Semantic Segmentation with Bidirectional Occlusion-guided Feature PropagationFull-text access may be available. Sign in or learn about subscription options.pp. 674-684
by Razieh Kaviani Baghbaderani, Yuanxin Li, Shuangquan Wang, Hairong Qi
Domain-Aware Knowledge Distillation for Continual Model GeneralizationFull-text access may be available. Sign in or learn about subscription options.pp. 685-696
by Nikhil Reddy, Mahsa Baktashmotlagh, Chetan Arora
Let’s Observe Them Over Time: An Improved Pedestrian Attribute Recognition ApproachFull-text access may be available. Sign in or learn about subscription options.pp. 697-706
by Kamalakar Vijay Thakare, Debi Prosad Dogra, Heeseung Choi, Haksub Kim, Ig-Jae Kim
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting PerformanceFull-text access may be available. Sign in or learn about subscription options.pp. 707-717
by Alloy Das, Sanket Biswas, Ayan Banerjee, Josep Lladós, Umapada Pal, Saumik Bhattacharya
Patch-based Selection and Refinement for Early Object DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 718-727
by Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo, Baoxin Li, Jae-Sun Seo, Yu Cao
Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated DepthFull-text access may be available. Sign in or learn about subscription options.pp. 728-737
by Cagri Gungor, Adriana Kovashka
C2AIR: Consolidated Compact Aerial Image Haze RemovalFull-text access may be available. Sign in or learn about subscription options.pp. 738-747
by Ashutosh Kulkarni, Shruti S. Phutke, Santosh Kumar Vipparthi, Subrahmanyam Murala
Favoring One Among Equals - Not a Good Idea: Many-to-one Matching for Robust Transformer based Pedestrian DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 748-757
by K.N Ajay Shastry, K. Ravi Sri Teja, Aditya Nigam, Chetan Arora
Improving Vision-and-Language Reasoning via Spatial Relations ModelingFull-text access may be available. Sign in or learn about subscription options.pp. 758-767
by Cheng Yang, Rui Xu, Ye Guo, Peixiang Huang, Yiru Chen, Wenkui Ding, Zhongyuan Wang, Hong Zhou
LP-OVOD: Open-Vocabulary Object Detection by Linear ProbingFull-text access may be available. Sign in or learn about subscription options.pp. 768-777
by Chau Pham, Truong Vu, Khoi Nguyen
Continuous Adaptation for Interactive Segmentation Using Teacher-Student ArchitectureFull-text access may be available. Sign in or learn about subscription options.pp. 778-788
by Barsegh Atanyan, Levon Khachatryan, Shant Navasardyan, Yunchao Wei, Humphrey Shi
Interpretable Object Recognition by Semantic Prototype AnalysisFull-text access may be available. Sign in or learn about subscription options.pp. 789-798
by Qiyang Wan, Ruiping Wang, Xilin Chen
RecycleNet: Latent Feature Recycling Leads to Iterative Decision RefinementFull-text access may be available. Sign in or learn about subscription options.pp. 799-807
by Gregor Koehler, Tassilo Wald, Constantin Ulrich, David Zimmerer, Paul F. Jaeger, Jörg K. H. Franke, Simon Kohl, Fabian Isensee, Klaus H. Maier-Hein
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 808-817
by JuneHyoung Kwon, Eunju Lee, Yunsung Cho, YoungBin Kim
Elusive Images: Beyond Coarse Analysis for Fine-Grained RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 818-828
by Connor Anderson, Matt Gwilliam, Evelyn Gaskin, Ryan Farrell
Understanding Dark Scenes by Contrasting Multi-Modal ObservationsFull-text access may be available. Sign in or learn about subscription options.pp. 829-839
by Xiaoyu Dong, Naoto Yokoya
MaskConver: Revisiting Pure Convolution Model for Panoptic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 840-850
by Abdullah Rashwan, Jiageng Zhang, Ali Taalimi, Fan Yang, Xingyi Zhou, Chaochao Yan, Liang-Chieh Chen, Yeqing Li
Masked Collaborative Contrast for Weakly Supervised Semantic SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 851-860
by Fangwen Wu, Jingxuan He, Yufei Yin, Yanbin Hao, Gang Huang, Lechao Cheng
Universal Semi-supervised Model Adaptation via Collaborative Consistency TrainingFull-text access may be available. Sign in or learn about subscription options.pp. 861-871
by Zizheng Yan, Yushuang Wu, Yipeng Qin, Xiaoguang Han, Shuguang Cui, Guanbin Li
STEP - Towards Structured Scene-Text SpottingFull-text access may be available. Sign in or learn about subscription options.pp. 872-881
by Sergi Garcia-Bordils, Dimosthenis Karatzas, Marçal Rusiñol
Efficient Feature Distillation for Zero-shot Annotation Object DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 882-891
by Zhuoming Liu, Xuefeng Hu, Ram Nevatia
Hierarchical Text Spotter for Joint Text Spotting and Layout AnalysisFull-text access may be available. Sign in or learn about subscription options.pp. 892-902
by Shangbang Long, Siyang Qin, Yasuhisa Fujii, Alessandro Bissacco, Michalis Raptis
iBARLE: imBalance-Aware Room Layout EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 903-913
by Taotao Jing, Lichen Wang, Naji Khosravan, Zhiqiang Wan, Zachary Bessinger, Zhengming Ding, Sing Bing Kang
TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene UnderstandingFull-text access may be available. Sign in or learn about subscription options.pp. 914-923
by Shuo Wang, Jing Li, Zibo Zhao, Dongze Lian, Binbin Huang, Xiaomei Wang, Zhengxin Li, Shenghua Gao
Implicit neural representation for change detectionFull-text access may be available. Sign in or learn about subscription options.pp. 924-934
by Peter Naylor, Diego Di Carlo, Arianna Traviglia, Makoto Yamada, Marco Fiorucci
Label-Free Synthetic Pretraining of Object DetectorsFull-text access may be available. Sign in or learn about subscription options.pp. 935-945
by Hei Law, Jia Deng
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-WidthsFull-text access may be available. Sign in or learn about subscription options.pp. 946-956
by Ximeng Sun, Rameswar Panda, Chun-Fu Richard Chen, Naigang Wang, Bowen Pan, Aude Oliva, Rogerio Feris, Kate Saenko
Showing 100 out of 853
Load More
Load All