Picture for Dong Won Lee

Dong Won Lee

Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback

Add code
Mar 17, 2024
Viaarxiv icon

HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer

Add code
May 21, 2023
Viaarxiv icon

Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations

Add code
Apr 19, 2023
Viaarxiv icon

Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides

Add code
Aug 17, 2022
Figure 1 for Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides
Figure 2 for Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides
Figure 3 for Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides
Figure 4 for Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides
Viaarxiv icon

Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach

Add code
Jul 24, 2020
Figure 1 for Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach
Figure 2 for Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach
Figure 3 for Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach
Figure 4 for Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach
Viaarxiv icon