论文解读Live Gurbani Tracking: A Benchmark and Reference System for Captioning Sikh Kirtan音频字幕生成 | 7.4/10
论文解读CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning音频字幕生成 | 6.3/10
论文解读TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions音视频理解 | 9.4/10