{"ID":2826144,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19130","arxiv_id":"2512.19130","title":"Dual-Stream Decoupled Learning for Temporal Consistency and Speaker Interaction in AVSD","abstract":"Audio-Visual Speaker Detection (AVSD) hinges on modeling both individual temporal continuity and inter-personal social context. Existing coupled architectures struggle to reconcile these tasks in shared representation spaces due to conflicting inductive biases: temporal modeling favors low-frequency smoothness, while inter-personal interaction requires high-frequency discriminability. We propose D$^2$Stream, a decoupled dual-stream framework that explicitly isolates these functionalities into parallel, task-specific branches. Specifically, the Intra-speaker Temporal Continuity (ITC) stream captures longitudinal stability, whereas the Inter-personal Social Relation (ISR) stream models transversal social cues. Quantitative gradient analysis reveals an evolutionary divergence in update directions, stabilizing at 86.1°, which confirms the inherent task conflict and the effectiveness of our structural decoupling. D$^2$Stream breaks the long-standing performance plateau, achieving a state-of-the-art 95.6% mAP on AVA-ActiveSpeaker and superior generalization on Columbia ASD, all within a lightweight and efficient design.","short_abstract":"Audio-Visual Speaker Detection (AVSD) hinges on modeling both individual temporal continuity and inter-personal social context. Existing coupled architectures struggle to reconcile these tasks in shared representation spaces due to conflicting inductive biases: temporal modeling favors low-frequency smoothness, while i...","url_abs":"https://arxiv.org/abs/2512.19130","url_pdf":"https://arxiv.org/pdf/2512.19130v2","authors":"[\"Junhao Xiao\",\"Shun Feng\",\"Zhiyu Wu\",\"Jinghan Yu\",\"Haibiao Yao\",\"Zhiyuan Ma\",\"Jianjun Li\",\"Youjun Bao\",\"Yi Chen\"]","published":"2025-12-22T08:21:22Z","proceeding":"cs.MM","tasks":"[\"cs.MM\"]","methods":"[]","has_code":false}