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

Add to Chrome

Add to Firefox

Picture for Yuexian Zou

Yuexian Zou

CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning

Nov 30, 2021
Bang Yang, Yuexian Zou

Figure 1 for CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning

Figure 2 for CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning

Figure 3 for CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning

Figure 4 for CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning

* 10 pages, 9 figures, 5 tables

Access Paper or Ask Questions

Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information

Oct 12, 2021
Zhongjie Ye, Helin Wang, Dongchao Yang, Yuexian Zou

Figure 1 for Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information

Figure 2 for Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information

Figure 3 for Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information

Figure 4 for Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information

* 5 pages, 1 figure, accepted by DCASE 2021 workshop

Access Paper or Ask Questions

A Mutual learning framework for Few-shot Sound Event Detection

Oct 09, 2021
Dongchao Yang, Helin Wang, Yuexian Zou, Zhongjie Ye, Wenwu Wang

Figure 1 for A Mutual learning framework for Few-shot Sound Event Detection

Figure 2 for A Mutual learning framework for Few-shot Sound Event Detection

Figure 3 for A Mutual learning framework for Few-shot Sound Event Detection

Figure 4 for A Mutual learning framework for Few-shot Sound Event Detection

* Submitted to ICASSP2022

Access Paper or Ask Questions

Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Sep 22, 2021
Dongsheng Chen, Zhiqi Huang, Xian Wu, Shen Ge, Yuexian Zou

Figure 1 for Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Figure 2 for Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Figure 3 for Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Figure 4 for Towards Joint Intent Detection and Slot Filling via Higher-order Attention

* The authors withdraw the manuscript and will update it in the original arXiv address (arXiv:2108.11916)

Access Paper or Ask Questions

On Pursuit of Designing Multi-modal Transformer for Video Grounding

Sep 13, 2021
Meng Cao, Long Chen, Mike Zheng Shou, Can Zhang, Yuexian Zou

Figure 1 for On Pursuit of Designing Multi-modal Transformer for Video Grounding

Figure 2 for On Pursuit of Designing Multi-modal Transformer for Video Grounding

Figure 3 for On Pursuit of Designing Multi-modal Transformer for Video Grounding

Figure 4 for On Pursuit of Designing Multi-modal Transformer for Video Grounding

* Accepted by Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

Access Paper or Ask Questions

Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

Aug 25, 2021
Cong Wang, Yan Huang, Yuexian Zou, Yong Xu

Figure 1 for Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

Figure 2 for Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

Figure 3 for Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

Figure 4 for Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

* 13 pages, 10 figures

Access Paper or Ask Questions