2 papers
cs.AI2024
DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework
Zhifei Xie, Daniel Tang, Dingwei Tan +3
Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \texttt{DreamFactory}, an LLM-based framework t…
cs.CL2023
Emotion Detection in Unfix-length-Context Conversation
Xiaochen Zhang, Daniel Tang
We leverage different context windows when predicting the emotion of different utterances. New modules are included to realize variable-length context: 1) two speaker-aware units,…