DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation

no code implementations • 13 Mar 2024 • Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu

However, many of these works face challenges in identifying correct output modalities and generating coherent images accordingly as the number of output modalities increases and the conversations go deeper.

Prompt Engineering Text-to-Image Generation

Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation

no code implementations • 9 Dec 2022 • Jie Jiang, Zhimin Li, Jiangfeng Xiong, Rongwei Quan, Qinglin Lu, Wei Liu

Therefore, TAVS is distinguished from previous temporal segmentation datasets due to its multi-modal information, holistic view of categories, and hierarchical granularities.

Multi-Label Classification Scene Segmentation +3

Overview of Tencent Multi-modal Ads Video Understanding Challenge

no code implementations • 16 Sep 2021 • Zhenzhi Wang, Liyu Wu, Zhimin Li, Jiangfeng Xiong, Qinglin Lu

Our challenge includes two tasks: video structuring in the temporal dimension and multi-modal video classification.

Multi-Label Classification Video Classification +1