Papers by Min-Jae Kim
Open Your Model’s Eyes: Video and Context-Aware Multimodal Backchannel Prediction (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for predicting backchannels rely on audio and text . existing methods omit visual cues and conversational contexts for accurate prediction . |
| Approach: | They propose a framework that leverages visual cues and conversational contexts to enhance backchannel prediction. |
| Outcome: | The proposed framework outperforms existing methods and simple multimodal baselines in recognizing complex backchannels such as empathy. |