AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes

ArXi:2606.02724v1 Announce Type: new Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding. This capability is essential for real-world applications such as intelligent video editing, surveillance, and human-computer interaction. However, existing datasets are largely limited to simple or homogeneous audio-visual scenes with coarse annotations.