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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Deng Cai

Deng Cai

Automatic Prosody Annotation with Pre-Trained Text-Speech Model



Ziqian Dai , Jianwei Yu , Yan Wang , Nuo Chen , Yanyao Bian , Guangzhi Li , Deng Cai , Dong Yu

Figure 1 for Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Figure 2 for Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Figure 3 for Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Figure 4 for Automatic Prosody Annotation with Pre-Trained Text-Speech Model
* accepted by INTERSPEECH2022 
   Access Paper or Ask Questions

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation



Jin Xu , Xiaojiang Liu , Jianhao Yan , Deng Cai , Huayang Li , Jian Li

Figure 1 for Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
Figure 2 for Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
Figure 3 for Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
Figure 4 for Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

   Access Paper or Ask Questions

Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning



Liang Xie , Yibo Yang , Deng Cai , Xiaofei He

Figure 1 for Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
Figure 2 for Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
Figure 3 for Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
Figure 4 for Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
* 25 pages, 5 figures 
   Access Paper or Ask Questions

Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning



Minghao Chen , Fangyun Wei , Chong Li , Deng Cai

Figure 1 for Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
Figure 2 for Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
Figure 3 for Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
Figure 4 for Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
* Accepted by CVPR 2022 
   Access Paper or Ask Questions

Linearizing Transformer with Key-Value Memory Bank



Yizhe Zhang , Deng Cai

Figure 1 for Linearizing Transformer with Key-Value Memory Bank
Figure 2 for Linearizing Transformer with Key-Value Memory Bank
Figure 3 for Linearizing Transformer with Key-Value Memory Bank
Figure 4 for Linearizing Transformer with Key-Value Memory Bank
* Work in progress 
   Access Paper or Ask Questions

CLRNet: Cross Layer Refinement Network for Lane Detection



Tu Zheng , Yifei Huang , Yang Liu , Wenjian Tang , Zheng Yang , Deng Cai , Xiaofei He

Figure 1 for CLRNet: Cross Layer Refinement Network for Lane Detection
Figure 2 for CLRNet: Cross Layer Refinement Network for Lane Detection
Figure 3 for CLRNet: Cross Layer Refinement Network for Lane Detection
Figure 4 for CLRNet: Cross Layer Refinement Network for Lane Detection
* CVPR2022 Acceptance 
   Access Paper or Ask Questions

Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion



Xiaopei Wu , Liang Peng , Honghui Yang , Liang Xie , Chenxi Huang , Chengqi Deng , Haifeng Liu , Deng Cai

Figure 1 for Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
Figure 2 for Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
Figure 3 for Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
Figure 4 for Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
* CVPR 2022 
   Access Paper or Ask Questions

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection



Liang Peng , Senbo Yan , Boxi Wu , Zheng Yang , Xiaofei He , Deng Cai

Figure 1 for WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
Figure 2 for WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
Figure 3 for WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
Figure 4 for WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
* Accepted by ICLR 2022 
   Access Paper or Ask Questions

A Survey on Retrieval-Augmented Text Generation



Huayang Li , Yixuan Su , Deng Cai , Yan Wang , Lemao Liu

Figure 1 for A Survey on Retrieval-Augmented Text Generation
* all authors contributed equally 
   Access Paper or Ask Questions
1
2
3
4
5
6
7
>>