Picture for Yu Ding

Yu Ding

Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

Feb 18, 2023
Jinming Ma, Feng Wu, Yingfeng Chen, Xianpeng Ji, Yu Ding

Figure 1 for Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

Figure 2 for Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

Figure 3 for Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

Figure 4 for Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

* 10 pages, 12 figures, This article is an extended version of the Extended Abstract accepted by the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-2022)

Access Paper or Ask Questions

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

Jan 03, 2023
Yifeng Ma, Suzhen Wang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Zhidong Deng, Xin Yu

Figure 1 for StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

Figure 2 for StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

Figure 3 for StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

Figure 4 for StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

* Accepted at AAAI2023. Demo: https://youtu.be/mO2Tjcwr4u8

Access Paper or Ask Questions

InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis

Dec 20, 2022
Feng Qiu, Wanzeng Kong, Yu Ding

Figure 1 for InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis

Figure 2 for InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis

Figure 3 for InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis

Figure 4 for InterMulti:Multi-view Multimodal Interactions with Text-dominated Hierarchical High-order Fusion for Emotion Analysis

* 9 pages, 3 figures. arXiv admin note: text overlap with arXiv:2212.08661

Access Paper or Ask Questions

EffMulti: Efficiently Modeling Complex Multimodal Interactions for Emotion Analysis

Dec 16, 2022
Feng Qiu, Chengyang Xie, Yu Ding, Wanzeng Kong

Figure 1 for EffMulti: Efficiently Modeling Complex Multimodal Interactions for Emotion Analysis

Figure 2 for EffMulti: Efficiently Modeling Complex Multimodal Interactions for Emotion Analysis

Figure 3 for EffMulti: Efficiently Modeling Complex Multimodal Interactions for Emotion Analysis

* 6 pages,1 figure

Access Paper or Ask Questions