Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 135

Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence

Han Hu ⋅ Dongheng Lin ⋅ Yuqi Hou ⋅ Haotian LI ⋅ Hyung Jin Chang ⋅ Jianbo Jiao

Keywords: Video Understanding, Generation and Multimodal Learning