CVPR 2026 Open Access Repository

10th Affective & Behavior Analysis in-the-wild

Hierarchical Granularity Alignment and State Space Modeling for Robust Multimodal AU Detection in the Wild: Jun Yu,

Yunxiang Zhang,

Naixiang Zheng,

Lingsi Zhu,

Guoyuan Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2026_CVPR, author = {Yu, Jun and Zhang, Yunxiang and Zheng, Naixiang and Zhu, Lingsi and Wang, Guoyuan}, title = {Hierarchical Granularity Alignment and State Space Modeling for Robust Multimodal AU Detection in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5483-5490} }
Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation: Lingsi Zhu,

Yuefeng Zou,

Yunxiang Zhang,

Naixiang Zheng,

Guoyuan Wang,

Jun Yu,

Jiaen Liang,

Wei Huang,

Shengping Liu,

Ximin Zheng; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2026_CVPR, author = {Zhu, Lingsi and Zou, Yuefeng and Zhang, Yunxiang and Zheng, Naixiang and Wang, Guoyuan and Yu, Jun and Liang, Jiaen and Huang, Wei and Liu, Shengping and Zheng, Ximin}, title = {Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5491-5498} }
A Two-Stage Dual-Modality Model for Facial Expression Recognition: Jiajun Sun,

Zhe Gao; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2026_CVPR, author = {Sun, Jiajun and Gao, Zhe}, title = {A Two-Stage Dual-Modality Model for Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5453-5463} }
Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis: Emile Bergeron,

Tadagbé Dhossou,

Sébastien Tremblay,

Jean-François Lalonde; [pdf] [supp]
[bibtex]
@InProceedings{Bergeron_2026_CVPR, author = {Bergeron, Emile and Dhossou, Tadagb\'e and Tremblay, S\'ebastien and Lalonde, Jean-Fran\c{c}ois}, title = {Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5234-5241} }
VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction: Vasiliki Vasileiou,

Panagiotis P Filntisis,

Petros Maragos,

Kostas Daniilidis; [pdf] [arXiv]
[bibtex]
@InProceedings{Vasileiou_2026_CVPR, author = {Vasileiou, Vasiliki and Filntisis, Panagiotis P and Maragos, Petros and Daniilidis, Kostas}, title = {VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5464-5473} }
A Dual-Branch Transformer for Affective Computing: Tackling Missing Modalities and Imbalance via Safe Attention and Focal Loss: Jun Yu,

Naixiang Zheng,

Guoyuan Wang,

Yunxiang Zhang,

Lingsi Zhu,

Jiaen Liang,

Wei Huang,

Shengping Liu; [pdf]
[bibtex]
@InProceedings{Yu_2026_CVPR, author = {Yu, Jun and Zheng, Naixiang and Wang, Guoyuan and Zhang, Yunxiang and Zhu, Lingsi and Liang, Jiaen and Huang, Wei and Liu, Shengping}, title = {A Dual-Branch Transformer for Affective Computing: Tackling Missing Modalities and Imbalance via Safe Attention and Focal Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5474-5482} }
Beyond the Mean: Modelling Annotation Distributions in Continuous Affect Prediction: Kosmas Pinitas,

Ilias Maglogiannis; [pdf] [arXiv]
[bibtex]
@InProceedings{Pinitas_2026_CVPR, author = {Pinitas, Kosmas and Maglogiannis, Ilias}, title = {Beyond the Mean: Modelling Annotation Distributions in Continuous Affect Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5370-5378} }
Trust What You Fuse: Reliability-Aware Cross-Attention for Multimodal Physiological Stress Assessment in the Wild: Kaveti Pavan Kumar,

Nagarajan Ganapathy; [pdf] [supp]
[bibtex]
@InProceedings{Kumar_2026_CVPR, author = {Kumar, Kaveti Pavan and Ganapathy, Nagarajan}, title = {Trust What You Fuse: Reliability-Aware Cross-Attention for Multimodal Physiological Stress Assessment in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5341-5350} }
Multimodal Emotion Regression with Multi-Objective Optimization and VAD-Aware Audio Modeling for the 10th ABAW EMI Track: Jiawen Huang,

Chenxi Huang,

Zhuofan Wen,

Hailiang Yao,

Shun Chen,

Longjiang Yang,

Cong Yu,

Fengyu Zhang,

Ran Liu,

Bin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2026_CVPR, author = {Huang, Jiawen and Huang, Chenxi and Wen, Zhuofan and Yao, Hailiang and Chen, Shun and Yang, Longjiang and Yu, Cong and Zhang, Fengyu and Liu, Ran and Liu, Bin}, title = {Multimodal Emotion Regression with Multi-Objective Optimization and VAD-Aware Audio Modeling for the 10th ABAW EMI Track}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5286-5293} }
Confidence-Gated Calibration for Video-based Facial Expression Recognition in-the-Wild: Andrey V Savchenko; [pdf]
[bibtex]
@InProceedings{Savchenko_2026_CVPR, author = {Savchenko, Andrey V}, title = {Confidence-Gated Calibration for Video-based Facial Expression Recognition in-the-Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5429-5436} }
MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model: Eyal Hanania,

Nadav Kirsch,

Daniel Arkushin,

Jonathan Benvenisti,

Amos Bercovich,

Elie Zemmour,

Sahar Froim; [pdf]
[bibtex]
@InProceedings{Hanania_2026_CVPR, author = {Hanania, Eyal and Kirsch, Nadav and Arkushin, Daniel and Benvenisti, Jonathan and Bercovich, Amos and Zemmour, Elie and Froim, Sahar}, title = {MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5267-5276} }
Deconfounding Demographic Bias Estimation in Facial Expression Recognition: Iván Ferre,

Roberto Valle,

José M. Buenaposada,

Luis Baumela; [pdf]
[bibtex]
@InProceedings{Ferre_2026_CVPR, author = {Ferre, Iv\'an and Valle, Roberto and Buenaposada, Jos\'e M. and Baumela, Luis}, title = {Deconfounding Demographic Bias Estimation in Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5257-5266} }
Distance-Aware Soft Prompt Guidance for Multimodal Valence-Arousal Estimation: Byeongjin Jung,

Chanyeong Park,

Sejoon Lim; [pdf]
[bibtex]
@InProceedings{Jung_2026_CVPR, author = {Jung, Byeongjin and Park, Chanyeong and Lim, Sejoon}, title = {Distance-Aware Soft Prompt Guidance for Multimodal Valence-Arousal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5294-5301} }
SAGE: Stage-Adaptive Guided Reliability Modeling for Continuous Valence-Arousal Estimation: Yubeen Lee,

Sangeun Lee,

Junyeop Cha,

Eunil Park; [pdf]
[bibtex]
@InProceedings{Lee_2026_CVPR, author = {Lee, Yubeen and Lee, Sangeun and Cha, Junyeop and Park, Eunil}, title = {SAGE: Stage-Adaptive Guided Reliability Modeling for Continuous Valence-Arousal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5312-5319} }
Pose2Lang3D: Distilling 3D Reasoning from 2D Skeletons via Language Supervision: Sai Bhargav Rongali,

Kenji Okuma; [pdf]
[bibtex]
@InProceedings{Rongali_2026_CVPR, author = {Rongali, Sai Bhargav and Okuma, Kenji}, title = {Pose2Lang3D: Distilling 3D Reasoning from 2D Skeletons via Language Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5399-5408} }
Beyond the Fold: Quantifying Split-Level Noise and the Case for Leave-One-Dataset-Out AU Evaluation: Saurabh Hinduja,

Gurmeet Kaur,

Maneesh Bilalpur,

Jeffrey F. Cohn,

Shaun Canavan; [pdf] [arXiv]
[bibtex]
@InProceedings{Hinduja_2026_CVPR, author = {Hinduja, Saurabh and Kaur, Gurmeet and Bilalpur, Maneesh and Cohn, Jeffrey F. and Canavan, Shaun}, title = {Beyond the Fold: Quantifying Split-Level Noise and the Case for Leave-One-Dataset-Out AU Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5277-5285} }
SBF: Augmenting Skeleton for Effective Video-based Human Action Recognition: Zhuoxuan Peng,

Yiyi Ding,

Yang Lin,

S.-H. Gary Chan; [pdf] [supp]
[bibtex]
@InProceedings{Peng_2026_CVPR, author = {Peng, Zhuoxuan and Ding, Yiyi and Lin, Yang and Chan, S.-H. Gary}, title = {SBF: Augmenting Skeleton for Effective Video-based Human Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5351-5361} }
LaScA: Language-Conditioned Scalable Modelling of Affective Dynamics: Kosmas Pinitas,

Ilias Maglogiannis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pinitas_2026_CVPR, author = {Pinitas, Kosmas and Maglogiannis, Ilias}, title = {LaScA: Language-Conditioned Scalable Modelling of Affective Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5379-5388} }
Two-Stage Multimodal Framework for Emotion Mimicry Intensity Prediction: Dinithi Dissanayake,

Shaveen Silva,

Ovindu Atukorala,

Prasanth Sasikumar,

Suranga Nanayakkara; [pdf] [arXiv]
[bibtex]
@InProceedings{Dissanayake_2026_CVPR, author = {Dissanayake, Dinithi and Silva, Shaveen and Atukorala, Ovindu and Sasikumar, Prasanth and Nanayakkara, Suranga}, title = {Two-Stage Multimodal Framework for Emotion Mimicry Intensity Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5249-5256} }
Ensemble-based Prototype-Augmented Multimodal Fusion for Ambivalence/Hesitancy Recognition: Elena Ryumina,

Alexandr Axyonov,

Dmitry Sysoev,

Timur Abdulkadirov,

Kirill Almetov,

Yulia Morozova,

Dmitry Ryumin; [pdf]
[bibtex]
@InProceedings{Ryumina_2026_CVPR, author = {Ryumina, Elena and Axyonov, Alexandr and Sysoev, Dmitry and Abdulkadirov, Timur and Almetov, Kirill and Morozova, Yulia and Ryumin, Dmitry}, title = {Ensemble-based Prototype-Augmented Multimodal Fusion for Ambivalence/Hesitancy Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5409-5418} }
DivFusion: Divergence-Based Multimodal Fusion for Ambivalence and Hesitancy Recognition: Aislan Gabriel O. Souza,

Bruno Fernandes,

Leandro Honorato Silva,

Agostinho Freire; [pdf] [supp]
[bibtex]
@InProceedings{Souza_2026_CVPR, author = {Souza, Aislan Gabriel O. and Fernandes, Bruno and Silva, Leandro Honorato and Freire, Agostinho}, title = {DivFusion: Divergence-Based Multimodal Fusion for Ambivalence and Hesitancy Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5446-5452} }
BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy: Alexandre Pereira,

Pablo Barros,

Bruno Fernandes; [pdf] [arXiv]
[bibtex]
@InProceedings{Pereira_2026_CVPR, author = {Pereira, Alexandre and Barros, Pablo and Fernandes, Bruno}, title = {BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5362-5369} }
Multimodal Expression Recognition Via Bi-directional Cross-Attention and Temporal Modeling: Junhyeong Byeon,

Jeongyeol Kim,

Sejoon Lim; [pdf]
[bibtex]
@InProceedings{Byeon_2026_CVPR, author = {Byeon, Junhyeong and Kim, Jeongyeol and Lim, Sejoon}, title = {Multimodal Expression Recognition Via Bi-directional Cross-Attention and Temporal Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5242-5248} }
Efficient Pretrained Representations for Video-based Fine-Grained Violence Detection, Action Unit Detection, and Valence-Arousal Estimation: Andrey Savchenko,

Kseniia Tsypliakova; [pdf]
[bibtex]
@InProceedings{Savchenko_2026_CVPR, author = {Savchenko, Andrey and Tsypliakova, Kseniia}, title = {Efficient Pretrained Representations for Video-based Fine-Grained Violence Detection, Action Unit Detection, and Valence-Arousal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5437-5445} }
From Affect to Complex Behavior: Advancing Multimodal Human-Centered AI at the 10th ABAW Workshop & Competition: Dimitrios Kollias,

Panagiotis Tzirakis,

Alan Cowen,

Stefanos Zafeiriou,

Irene Kotsia,

Eric Granger,

Marco Pedersoli,

Simon Bacon,

Jens Madsen,

Soufiane Belharbi,

Muhammad Haseeb Aslam,

Chunchang Shao,

Guanyu Hu; [pdf]
[bibtex]
@InProceedings{Kollias_2026_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 Madsen, Jens and Belharbi, Soufiane and Aslam, Muhammad Haseeb and Shao, Chunchang and Hu, Guanyu}, title = {From Affect to Complex Behavior: Advancing Multimodal Human-Centered AI at the 10th ABAW Workshop \& Competition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5302-5311} }
From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection: Narges Rashvand,

Shanle Yao,

Armin Danesh Pazho,

Babak Rahimi Ardabili,

Hamed Tabkhi; [pdf] [arXiv]
[bibtex]
@InProceedings{Rashvand_2026_CVPR, author = {Rashvand, Narges and Yao, Shanle and Pazho, Armin Danesh and Ardabili, Babak Rahimi and Tabkhi, Hamed}, title = {From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5389-5398} }
Topology-Guided Test-Time Adaptation via Persistent Homology: From Affective Behavior Analysis to Autonomous Driving: Onur Cezmi Mutlu,

Mohammadmahdi Honarmand,

Parnian Azizian,

Saimourya Surabhi,

Dennis P Wall; [pdf]
[bibtex]
@InProceedings{Mutlu_2026_CVPR, author = {Mutlu, Onur Cezmi and Honarmand, Mohammadmahdi and Azizian, Parnian and Surabhi, Saimourya and Wall, Dennis P}, title = {Topology-Guided Test-Time Adaptation via Persistent Homology: From Affective Behavior Analysis to Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5331-5340} }
From Faces to Behavior Analysis: Adaptive Multimodal Fusion for Valence-Arousal Estimation in-the-Wild: Elena Ryumina,

Maxim Markitantov,

Alexandr Axyonov,

Dmitry Ryumin,

Mikhail Dolgushin,

Denis Dresvyanskiy,

Alexey Karpov; [pdf]
[bibtex]
@InProceedings{Ryumina_2026_CVPR, author = {Ryumina, Elena and Markitantov, Maxim and Axyonov, Alexandr and Ryumin, Dmitry and Dolgushin, Mikhail and Dresvyanskiy, Denis and Karpov, Alexey}, title = {From Faces to Behavior Analysis: Adaptive Multimodal Fusion for Valence-Arousal Estimation in-the-Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5419-5428} }
SenBen: Sensitive Scene Graphs for Explainable Content Moderation: Fatih Cagatay Akyon,

Alptekin Temizel; [pdf] [arXiv]
[bibtex]
@InProceedings{Akyon_2026_CVPR, author = {Akyon, Fatih Cagatay and Temizel, Alptekin}, title = {SenBen: Sensitive Scene Graphs for Explainable Content Moderation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5225-5233} }
MuPPet: Multi-person 2D-to-3D Pose Lifting: Thomas Markhorst,

Zhi-Yi Lin,

Jouh Yeong Chew,

Jan Van Gemert,

Xucong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Markhorst_2026_CVPR, author = {Markhorst, Thomas and Lin, Zhi-Yi and Chew, Jouh Yeong and Van Gemert, Jan and Zhang, Xucong}, title = {MuPPet: Multi-person 2D-to-3D Pose Lifting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5320-5330} }