Picture for Long Ma

Long Ma

DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting

May 23, 2023
Shubo Lv, Xiong Wang, Sining Sun, Long Ma, Lei Xie

* Accepted by INTERSPEECH2023

Access Paper or Ask Questions

MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

May 18, 2023
Xingyuan Li, Jingyuan Liu, Yixin Lei, Long Ma, Xin Fan, Risheng Liu

Figure 1 for MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

Figure 2 for MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

Figure 3 for MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

Figure 4 for MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

* 10 pages, 5 figures, 3 tables

Access Paper or Ask Questions

Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

May 11, 2023
Zhu Liu, Jinyuan Liu, Guanyao Wu, Long Ma, Xin Fan, Risheng Liu

Figure 1 for Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

Figure 2 for Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

Figure 3 for Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

Figure 4 for Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

* 9 pages,6 figures, published to IJCAI

Access Paper or Ask Questions

PAI at SemEval-2023 Task 2: A Universal System for Named Entity Recognition with External Entity Information

May 10, 2023
Long Ma, Kai Lu, Tianbo Che, Hailong Huang, Weiguo Gao, Xuan Li

* win 2 first places, 4 second places, and 1 third place out of 13 tracks

Access Paper or Ask Questions

Practical Exposure Correction: Great Truths Are Always Simple

Dec 29, 2022
Long Ma, Tianjiao Ma, Xinwei Xue, Xin Fan, Zhongxuan Luo, Risheng Liu

Figure 1 for Practical Exposure Correction: Great Truths Are Always Simple

Figure 2 for Practical Exposure Correction: Great Truths Are Always Simple

Figure 3 for Practical Exposure Correction: Great Truths Are Always Simple

Figure 4 for Practical Exposure Correction: Great Truths Are Always Simple

* Under Review. Project Page: https://rsliu.tech/PEC

Access Paper or Ask Questions

Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

Nov 19, 2022
Di Wang, Long Ma, Risheng Liu, Xin Fan

Figure 1 for Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

Figure 2 for Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

Figure 3 for Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

Figure 4 for Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

* Accepted by ICRA2022

Access Paper or Ask Questions

CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Jul 04, 2022
Zhanheng Yang, Sining Sun, Jin Li, Xiaoming Zhang, Xiong Wang, Long Ma, Lei Xie

Figure 1 for CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Figure 2 for CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Figure 3 for CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Figure 4 for CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

* Accepted by Interspeech 2022

Access Paper or Ask Questions