Picture for Haoyu Gao

Haoyu Gao

QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input

Add code
May 22, 2024
Viaarxiv icon

Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models

Add code
Sep 22, 2023
Figure 1 for Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Figure 2 for Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Figure 3 for Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Figure 4 for Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Viaarxiv icon

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue in Multiple Domains

Add code
May 22, 2023
Figure 1 for SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue in Multiple Domains
Figure 2 for SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue in Multiple Domains
Figure 3 for SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue in Multiple Domains
Figure 4 for SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue in Multiple Domains
Viaarxiv icon

Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment

Add code
May 19, 2023
Figure 1 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 2 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 3 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 4 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Viaarxiv icon

Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation

Add code
May 04, 2023
Figure 1 for Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Figure 2 for Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Figure 3 for Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Viaarxiv icon