Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when drivi...
Ye-Xin Liu, Yun-Long Lin, Zehan Wang et al.· 0 citations
Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairing layouts, or tracing routes. Solving these problems requires understanding a scene, inferring what must change to achieve a goal, and realizing that change without di...
Wenjie Shu, Ye-Xin Liu, Harold Haodong Chen et al.· 0 citations
This work introduces principled criteria for desirable VQ behavior and demonstrates that aligning feature and code vector distributions provides a unifying mechanism for mitigating training instability and codebook collapse, and instantiate this framework using a Wasserstein-based objective with an efficient closed-for...