Paper
Team LEYA in 10th ABAW Competition: Multimodal Ambivalence/Hesitancy Recognition Approach
Authors
Elena Ryumina, Alexandr Axyonov, Dmitry Sysoev, Timur Abdulkadirov, Kirill Almetov, Yulia Morozova, Dmitry Ryumin
Abstract
Ambivalence/hesitancy recognition in unconstrained videos is a challenging problem due to the subtle, multimodal, and context-dependent nature of this behavioral state. In this paper, a multimodal approach for video-level ambivalence/hesitancy recognition is presented for the 10th ABAW Competition. The proposed approach integrates four complementary modalities: scene, face, audio, and text. Scene dynamics are captured with a VideoMAE-based model, facial information is encoded through emotional frame-level embeddings aggregated by statistical pooling, acoustic representations are extracted with EmotionWav2Vec2.0 and processed by a Mamba-based temporal encoder, and linguistic cues are modeled using fine-tuned transformer-based text models. The resulting unimodal embeddings are further combined using multimodal fusion models, including prototype-augmented variants. Experiments on the BAH corpus demonstrate clear gains of multimodal fusion over all unimodal baselines. The best unimodal configuration achieved an average MF1 of 70.02%, whereas the best multimodal fusion model reached 83.25%. The highest final test performance, 71.43%, was obtained by an ensemble of five prototype-augmented fusion models. The obtained results highlight the importance of complementary multimodal cues and robust fusion strategies for ambivalence/hesitancy recognition.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.12848v1</id>\n <title>Team LEYA in 10th ABAW Competition: Multimodal Ambivalence/Hesitancy Recognition Approach</title>\n <updated>2026-03-13T09:50:03Z</updated>\n <link href='https://arxiv.org/abs/2603.12848v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.12848v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Ambivalence/hesitancy recognition in unconstrained videos is a challenging problem due to the subtle, multimodal, and context-dependent nature of this behavioral state. In this paper, a multimodal approach for video-level ambivalence/hesitancy recognition is presented for the 10th ABAW Competition. The proposed approach integrates four complementary modalities: scene, face, audio, and text. Scene dynamics are captured with a VideoMAE-based model, facial information is encoded through emotional frame-level embeddings aggregated by statistical pooling, acoustic representations are extracted with EmotionWav2Vec2.0 and processed by a Mamba-based temporal encoder, and linguistic cues are modeled using fine-tuned transformer-based text models. The resulting unimodal embeddings are further combined using multimodal fusion models, including prototype-augmented variants. Experiments on the BAH corpus demonstrate clear gains of multimodal fusion over all unimodal baselines. The best unimodal configuration achieved an average MF1 of 70.02%, whereas the best multimodal fusion model reached 83.25%. The highest final test performance, 71.43%, was obtained by an ensemble of five prototype-augmented fusion models. The obtained results highlight the importance of complementary multimodal cues and robust fusion strategies for ambivalence/hesitancy recognition.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-13T09:50:03Z</published>\n <arxiv:comment>8 pages, 2 figures</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Elena Ryumina</name>\n <arxiv:affiliation>St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Alexandr Axyonov</name>\n <arxiv:affiliation>St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Dmitry Sysoev</name>\n <arxiv:affiliation>HSE University, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Timur Abdulkadirov</name>\n <arxiv:affiliation>HSE University, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Kirill Almetov</name>\n <arxiv:affiliation>HSE University, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Yulia Morozova</name>\n <arxiv:affiliation>HSE University, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n <author>\n <name>Dmitry Ryumin</name>\n <arxiv:affiliation>St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia</arxiv:affiliation>\n <arxiv:affiliation>HSE University, St. Petersburg, Russia</arxiv:affiliation>\n </author>\n </entry>"
}