CVPR 2025 Open Access Repository

8th Workshop and Competition on Affective & Behavior Analysis in-the-wild

Datasets for Valence and Arousal Inference: A Survey: Helen Schneider,

Svetlana Pavlitska,

Helen Gremmelmaier,

Marius Zöllner; [pdf]
[bibtex]
@InProceedings{Schneider_2025_CVPR, author = {Schneider, Helen and Pavlitska, Svetlana and Gremmelmaier, Helen and Z\"ollner, Marius}, title = {Datasets for Valence and Arousal Inference: A Survey}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5657-5664} }
Selective Test-time Domain Adaptation Using Fisher Information for Robust Facial Expression Recognition In-the-wild: Mohammadmahdi Honarmand,

Onur Cezmi Mutlu,

Parnian Azizian,

Saimourya Surabhi,

Dennis Wall; [pdf]
[bibtex]
@InProceedings{Honarmand_2025_CVPR, author = {Honarmand, Mohammadmahdi and Mutlu, Onur Cezmi and Azizian, Parnian and Surabhi, Saimourya and Wall, Dennis}, title = {Selective Test-time Domain Adaptation Using Fisher Information for Robust Facial Expression Recognition In-the-wild}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5800-5810} }
Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition: Dimitrios Kollias,

Panagiotis Tzirakis,

Alan Cowen,

Stefanos Zafeiriou,

Irene Kotsia,

Eric Granger,

Marco Pedersoli,

Simon Bacon,

Alice Baird,

Chris Gagne,

Chunchang Shao,

Guanyu Hu,

Soufiane Belharbi,

Muhammad Haseeb Aslam; [pdf]
[bibtex]
@InProceedings{Kollias_2025_CVPR, author = {Kollias, Dimitrios and Tzirakis, Panagiotis and Cowen, Alan and Zafeiriou, Stefanos and Kotsia, Irene and Granger, Eric and Pedersoli, Marco and Bacon, Simon and Baird, Alice and Gagne, Chris and Shao, Chunchang and Hu, Guanyu and Belharbi, Soufiane and Aslam, Muhammad Haseeb}, title = {Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5572-5583} }
Semantic Matters: Multimodal Features for Affective Analysis: Tobias Hallmen,

Robin-Nico Kampa,

Fabian Deuser,

Norbert Oswald,

Elisabeth André; [pdf] [arXiv]
[bibtex]
@InProceedings{Hallmen_2025_CVPR, author = {Hallmen, Tobias and Kampa, Robin-Nico and Deuser, Fabian and Oswald, Norbert and Andr\'e, Elisabeth}, title = {Semantic Matters: Multimodal Features for Affective Analysis}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5715-5724} }
Learning Pose-aware Representations in Vision Transformers for Understanding Activities of Daily Living: Dominick Reilly,

Srijita Das,

Srijan Das; [pdf]
[bibtex]
@InProceedings{Reilly_2025_CVPR, author = {Reilly, Dominick and Das, Srijita and Das, Srijan}, title = {Learning Pose-aware Representations in Vision Transformers for Understanding Activities of Daily Living}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5542-5551} }
Neighbor-Based Feature and Index Enhancement for Person Re-Identification: Chao Yuan,

Tianyi Zhang,

Guanglin Niu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_CVPR, author = {Yuan, Chao and Zhang, Tianyi and Niu, Guanglin}, title = {Neighbor-Based Feature and Index Enhancement for Person Re-Identification}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5762-5769} }
DAF: Distillation, Augmentation and Filtering based Framework for Efficient Smartphone Human Activity Recognition: Ujjal Kr Dutta,

Guan-Ming Su; [pdf]
[bibtex]
@InProceedings{Dutta_2025_CVPR, author = {Dutta, Ujjal Kr and Su, Guan-Ming}, title = {DAF: Distillation, Augmentation and Filtering based Framework for Efficient Smartphone Human Activity Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5594-5602} }
Enhancing Facial Expression Recognition with LSTM through Dual-Direction Attention Mixed Feature Networks and CLIP: Josep Cabacas-Maso,

Elena Ortega-Beltrán,

Ismael Benito-Altamirano,

Carles Ventura; [pdf]
[bibtex]
@InProceedings{Cabacas-Maso_2025_CVPR, author = {Cabacas-Maso, Josep and Ortega-Beltr\'an, Elena and Benito-Altamirano, Ismael and Ventura, Carles}, title = {Enhancing Facial Expression Recognition with LSTM through Dual-Direction Attention Mixed Feature Networks and CLIP}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5665-5671} }
Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation: Sarosij Bose,

Hannah Dela Cruz,

Arindam Dutta,

Elena Kokkoni,

Konstantinos Karydis,

Amit Kumar Roy Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bose_2025_CVPR, author = {Bose, Sarosij and Cruz, Hannah Dela and Dutta, Arindam and Kokkoni, Elena and Karydis, Konstantinos and Chowdhury, Amit Kumar Roy}, title = {Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5562-5571} }
EmoVLM-KD: Fusing Distilled Expertise with Vision-Language Models for Visual Emotion Analysis: SangEun Lee,

Yubeen Lee,

Eunil Park; [pdf]
[bibtex]
@InProceedings{Lee_2025_CVPR, author = {Lee, SangEun and Lee, Yubeen and Park, Eunil}, title = {EmoVLM-KD: Fusing Distilled Expertise with Vision-Language Models for Visual Emotion Analysis}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5633-5642} }
Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task: Aviral Chharia,

Tianyu Ren,

Tomotake Furuhata,

Kenji Shimada; [pdf]
[bibtex]
@InProceedings{Chharia_2025_CVPR, author = {Chharia, Aviral and Ren, Tianyu and Furuhata, Tomotake and Shimada, Kenji}, title = {Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5811-5820} }
MMDrive: Multi-modal Remote Physiological Signal Measurement Dataset for Driver Status Monitoring: Jiho Choi,

Sang Jun Lee; [pdf]
[bibtex]
@InProceedings{Choi_2025_CVPR, author = {Choi, Jiho and Lee, Sang Jun}, title = {MMDrive: Multi-modal Remote Physiological Signal Measurement Dataset for Driver Status Monitoring}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5691-5698} }
Robust Stage-Wise LVLM Adaptation: Multi-Phase Prompt Lora Fine-tuning for Compound Expression Recognition: Xilong Lu,

Jun Yu,

Yunxiang Zhang,

Lingsi Zhu,

Yang Zheng,

Yongqi Wang,

Qiang Ling; [pdf]
[bibtex]
@InProceedings{Lu_2025_CVPR, author = {Lu, Xilong and Yu, Jun and Zhang, Yunxiang and Zhu, Lingsi and Zheng, Yang and Wang, Yongqi and Ling, Qiang}, title = {Robust Stage-Wise LVLM Adaptation: Multi-Phase Prompt Lora Fine-tuning for Compound Expression Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5770-5777} }
V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression Recognition: JunGyu Lee,

Kunyoung Lee,

Haesol Park,

Ig-Jae Kim,

Gi Pyo Nam; [pdf]
[bibtex]
@InProceedings{Lee_2025_CVPR, author = {Lee, JunGyu and Lee, Kunyoung and Park, Haesol and Kim, Ig-Jae and Nam, Gi Pyo}, title = {V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5643-5650} }
Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model: Hatef Otroshi Shahreza,

Anjith George,

Sébastien Marcel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shahreza_2025_CVPR, author = {Shahreza, Hatef Otroshi and George, Anjith and Marcel, S\'ebastien}, title = {Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5584-5593} }
Leveraging Lightweight Facial Models and Textual Modality in Audio-visual Emotional Understanding in-the-Wild: Andrey Savchenko,

Lyudmila Savchenko; [pdf]
[bibtex]
@InProceedings{Savchenko_2025_CVPR, author = {Savchenko, Andrey and Savchenko, Lyudmila}, title = {Leveraging Lightweight Facial Models and Textual Modality in Audio-visual Emotional Understanding in-the-Wild}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5778-5788} }
Read My Ears! Horse Ear Movement Detection for Equine Affective State Assessment: Joao Alves,

Pia Haubro Andersen,

Rikke Gade; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alves_2025_CVPR, author = {Alves, Joao and Andersen, Pia Haubro and Gade, Rikke}, title = {Read My Ears! Horse Ear Movement Detection for Equine Affective State Assessment}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5672-5680} }
Cross-Modal Facial Expression Recognition with Global Channel-Spatial Attention: Modal Enhancement and Proportional Criterion Fusion: Jun Yu,

Yang Zheng,

Lei Wang,

Yongqi Wang,

Shengfan Xu; [pdf]
[bibtex]
@InProceedings{Yu_2025_CVPR, author = {Yu, Jun and Zheng, Yang and Wang, Lei and Wang, Yongqi and Xu, Shengfan}, title = {Cross-Modal Facial Expression Recognition with Global Channel-Spatial Attention: Modal Enhancement and Proportional Criterion Fusion}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5707-5714} }
Towards Robust Multimodal AU Detection: STN-Enhanced Visual Encoding and Audio-Visual Spatial-Temporal Alignment: Jun Yu,

Yunxiang Zhang,

Fengzhao Sun,

Leilei Wang,

Renjie Lu,

Lingsi Zhu,

Xilong Lu,

Yang Zheng,

Yongqi Wang; [pdf]
[bibtex]
@InProceedings{Yu_2025_CVPR, author = {Yu, Jun and Zhang, Yunxiang and Sun, Fengzhao and Wang, Leilei and Lu, Renjie and Zhu, Lingsi and Lu, Xilong and Zheng, Yang and Wang, Yongqi}, title = {Towards Robust Multimodal AU Detection: STN-Enhanced Visual Encoding and Audio-Visual Spatial-Temporal Alignment}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5725-5732} }
Interactive Multimodal Framework with Temporal Modeling for Emotion Recognition: Jun Yu,

Yongqi Wang,

Lei Wang,

Yang Zheng,

Shengfan Xu; [pdf]
[bibtex]
@InProceedings{Yu_2025_CVPR, author = {Yu, Jun and Wang, Yongqi and Wang, Lei and Zheng, Yang and Xu, Shengfan}, title = {Interactive Multimodal Framework with Temporal Modeling for Emotion Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5699-5706} }
VRU-CIPI: Crossing Intention Prediction at Intersections for Improving Vulnerable Road Users Safety: Ahmed S. Abdelrahman,

Mohamed Abdel-Aty,

Quoc Dai Tran; [pdf]
[bibtex]
@InProceedings{Abdelrahman_2025_CVPR, author = {Abdelrahman, Ahmed S. and Abdel-Aty, Mohamed and Tran, Quoc Dai}, title = {VRU-CIPI: Crossing Intention Prediction at Intersections for Improving Vulnerable Road Users Safety}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5623-5632} }
Is Multi-Person Gait Recognition Feasible under Mutual Occlusion? A Human Model Regression-based Approach: Ziruo Li,

Chi Xu,

Xiang Li,

Shuqiong Wu,

Yasushi Yagi; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_CVPR, author = {Li, Ziruo and Xu, Chi and Li, Xiang and Wu, Shuqiong and Yagi, Yasushi}, title = {Is Multi-Person Gait Recognition Feasible under Mutual Occlusion? A Human Model Regression-based Approach}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5603-5613} }
MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network: Vrushank Ahire,

Kunal Shah,

Mudasir Khan,

Nikhil Pakhale,

Lownish Sookha,

Mudasir Ganaie,

Abhinav Dhall; [pdf] [arXiv]
[bibtex]
@InProceedings{Ahire_2025_CVPR, author = {Ahire, Vrushank and Shah, Kunal and Khan, Mudasir and Pakhale, Nikhil and Sookha, Lownish and Ganaie, Mudasir and Dhall, Abhinav}, title = {MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5789-5799} }
Dual-Stage Cross-Modal Network with Dynamic Feature Fusion for Emotional Mimicry Intensity Estimation: Jun Yu,

Lingsi Zhu,

Yanjun Chi,

Yunxiang Zhang,

Yang Zhen,

Yongqi Wang,

Xilong Lu; [pdf]
[bibtex]
@InProceedings{Yu_2025_CVPR, author = {Yu, Jun and Zhu, Lingsi and Chi, Yanjun and Zhang, Yunxiang and Zhen, Yang and Wang, Yongqi and Lu, Xilong}, title = {Dual-Stage Cross-Modal Network with Dynamic Feature Fusion for Emotional Mimicry Intensity Estimation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5733-5740} }
Decoupling Identity Confounders for Enhanced Facial Expression Recognition: An Information-Theoretic Approach: Mohd Aquib,

Nishchal K. Verma,

M. Jaleel Akhtar; [pdf]
[bibtex]
@InProceedings{Aquib_2025_CVPR, author = {Aquib, Mohd and Verma, Nishchal K. and Akhtar, M. Jaleel}, title = {Decoupling Identity Confounders for Enhanced Facial Expression Recognition: An Information-Theoretic Approach}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5552-5561} }
Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose: Narges Rashvand,

Ghazal Alinezhad Noghre,

Armin Danesh Pazho,

Babak Rahimi Ardabili,

Hamed Tabkhi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rashvand_2025_CVPR, author = {Rashvand, Narges and Noghre, Ghazal Alinezhad and Pazho, Armin Danesh and Ardabili, Babak Rahimi and Tabkhi, Hamed}, title = {Shopformer: Transformer-Based Framework for Detecting Shoplifting via Human Pose}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5752-5761} }
Multimodal Emotion Prediction in Interpersonal Videos Integrating Facial and Speech Cues: Hajer Guerdelli,

Claudio Ferrari,

Stefano Berretti,

Alberto Del Bimbo; [pdf]
[bibtex]
@InProceedings{Guerdelli_2025_CVPR, author = {Guerdelli, Hajer and Ferrari, Claudio and Berretti, Stefano and Del Bimbo, Alberto}, title = {Multimodal Emotion Prediction in Interpersonal Videos Integrating Facial and Speech Cues}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5681-5690} }
United we stand, Divided we fall: Handling Weak Complementarity for Audio-Visual Emotion Recognition in Valence-Arousal Space: Gnana Praveen Rajasekhar,

Jahangir Alam,

Eric Charton; [pdf]
[bibtex]
@InProceedings{Rajasekhar_2025_CVPR, author = {Rajasekhar, Gnana Praveen and Alam, Jahangir and Charton, Eric}, title = {United we stand, Divided we fall: Handling Weak Complementarity for Audio-Visual Emotion Recognition in Valence-Arousal Space}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5741-5751} }
Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space: Yuheng Liang,

Zheyu Wang,

Feng Liu,

Mingzhou Liu,

Yu Yao; [pdf]
[bibtex]
@InProceedings{Liang_2025_CVPR, author = {Liang, Yuheng and Wang, Zheyu and Liu, Feng and Liu, Mingzhou and Yao, Yu}, title = {Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5651-5656} }
Advancing Facial Age Progression for Occluded Faces: Ankit Birla,

Akshay Agarwal; [pdf]
[bibtex]
@InProceedings{Birla_2025_CVPR, author = {Birla, Ankit and Agarwal, Akshay}, title = {Advancing Facial Age Progression for Occluded Faces}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {5614-5622} }