4 papers
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
Ziqi Zhou, Weize Quan, Mining Tan +6
Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grain…
MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
Haitian Li, Yanghao Zhou, Heyan Huang +15
In recent years, Multi-Talker Audio-Video Generation (MTAVG) models have shown promising performance on fundamental metrics such as lip-sync and audio-visual alignment. However, th…
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation
Yang-Hao Zhou, Haitian Li, Rexar Lin +12
Recent advances in text-to-audio-video (T2AV) generation have enabled models to synthesize audio-visual videos with multi-participant dialogues. However, existing evaluation benchm…
TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis
Weize Quan, Yunfei Feng, Ming Zhou +3
Multimodal Sentiment Analysis (MSA) endeavors to understand human sentiment by leveraging language, visual, and acoustic modalities. Despite the remarkable performance exhibited by…