Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Shutao Li

Shutao Li

Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

Jul 05, 2022
Bin Li, Yixuan Weng, Ziyu Ma, Bin Sun, Shutao Li

Figure 1 for Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

Figure 2 for Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

Figure 3 for Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

Figure 4 for Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation

* Accepted in NLPCC 2022

Access Paper or Ask Questions

Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

May 10, 2022
Fuyan Ma, Bin Sun, Shutao Li

Figure 1 for Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

Figure 2 for Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

Figure 3 for Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

Figure 4 for Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild

Access Paper or Ask Questions

LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

Apr 20, 2022
Fei Xia, Bin Li, Yixuan Weng, Shizhu He, Kang Liu, Bin Sun, Shutao Li, Jun Zhao

Figure 1 for LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

Figure 2 for LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

Figure 3 for LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

Figure 4 for LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

* 9 pages, 4 figures, 5 tables

Access Paper or Ask Questions

Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

Mar 29, 2022
Bin Li, Yixuan Weng, Bin Sun, Shutao Li

Figure 1 for Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

Figure 2 for Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

Figure 3 for Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

Figure 4 for Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video

* 8 pages, 6 figures, 3 tables

Access Paper or Ask Questions

Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction

Mar 23, 2022
Bin Li, Yixuan Weng, Qiya Song, Fuyan Ma, Bin Sun, Shutao Li

Figure 1 for Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction

Figure 2 for Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction

Figure 3 for Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction

Figure 4 for Prompt-based Pre-trained Model for Personality and Interpersonal Reactivity Prediction

* The shared task paper described the contributions of the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) @ ACL-2022

Access Paper or Ask Questions

PSG: Prompt-based Sequence Generation for Acronym Extraction

Dec 09, 2021
Bin Li, Fei Xia, Yixuan Weng, Xiusheng Huang, Bin Sun, Shutao Li

Figure 1 for PSG: Prompt-based Sequence Generation for Acronym Extraction

Figure 2 for PSG: Prompt-based Sequence Generation for Acronym Extraction

Figure 3 for PSG: Prompt-based Sequence Generation for Acronym Extraction

Figure 4 for PSG: Prompt-based Sequence Generation for Acronym Extraction

* Accepted for Artificial Intelligence on Scientific Document Understanding (SDU) workshop at AAAI 2022

Access Paper or Ask Questions

SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation

Nov 29, 2021
Bin Li, Fei Xia, Yixuan Weng, Xiusheng Huang, Bin Sun, Shutao Li

Figure 1 for SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation

Figure 2 for SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation

Figure 3 for SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation

Figure 4 for SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation

* 6 pages, 2 figures, 3 tables

Access Paper or Ask Questions

Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

Oct 16, 2021
Ziyu Ma, Fuyan Ma, Bin Sun, Shutao Li

Figure 1 for Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

Figure 2 for Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

Figure 3 for Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

Figure 4 for Hybrid Mutimodal Fusion for Dimensional Emotion Recognition

* 8 pages, 2 figures, accepted by ACM MM2021

Access Paper or Ask Questions