Picture for Yin Chen

Yin Chen

DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation

Add code
Oct 11, 2024
Figure 1 for DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Figure 2 for DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Figure 3 for DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Figure 4 for DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Viaarxiv icon

Multi-intent Aware Contrastive Learning for Sequential Recommendation

Add code
Sep 13, 2024
Viaarxiv icon

UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos

Add code
Sep 10, 2024
Figure 1 for UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos
Figure 2 for UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos
Figure 3 for UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos
Figure 4 for UniLearn: Enhancing Dynamic Facial Expression Recognition through Unified Pre-Training and Fine-Tuning on Images and Videos
Viaarxiv icon

Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective Model

Add code
Sep 01, 2024
Viaarxiv icon

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

Add code
Dec 09, 2023
Viaarxiv icon

Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers

Add code
Mar 16, 2023
Viaarxiv icon

MRS-VPR: a multi-resolution sampling based global visual place recognition method

Add code
Feb 26, 2019
Figure 1 for MRS-VPR: a multi-resolution sampling based global visual place recognition method
Figure 2 for MRS-VPR: a multi-resolution sampling based global visual place recognition method
Figure 3 for MRS-VPR: a multi-resolution sampling based global visual place recognition method
Figure 4 for MRS-VPR: a multi-resolution sampling based global visual place recognition method
Viaarxiv icon