X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
Dual-Stream Decoupled Learning for Temporal Consistency and Speaker Interaction in AVSD
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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{\deg}, 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.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A decoupled dual-stream model for audio-visual speaker detection reaches 95.6% mAP on AVA-ActiveSpeaker by isolating temporal continuity and inter-personal social modeling into separate branches.
citing papers explorer
-
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
-
Dual-Stream Decoupled Learning for Temporal Consistency and Speaker Interaction in AVSD
A decoupled dual-stream model for audio-visual speaker detection reaches 95.6% mAP on AVA-ActiveSpeaker by isolating temporal continuity and inter-personal social modeling into separate branches.