Deng Cai

发表

SCALoss: Side and Corner Aligned Loss for Bounding Box Regression

Zili Liu, Tu Zheng, Shuai Zhao, 2021, AAAI.

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

Xiaofei He, Xiaofei He, Deng Cai, 2022, Neurocomputing.

Lidar Point Cloud Guided Monocular 3D Object Detection

Deng Cai, Liang Peng, Fei Liu, 2021, ECCV.

Towards Efficient Adversarial Training on Vision Transformers

Xiaofei He, Zhifeng Li, Boxi Wu, 2022, ECCV.

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

Xiaofei He, Xiaopei Wu, Xiaofei He, 2022, ECCV.

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Xiaopei Wu, Deng Cai, Liang Peng, 2022, ECCV.

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System pdf

Elman Mansimov, Yi-An Lai, Yi Zhang, 2021, ACL.

Boosting Semi-Supervised 3D Object Detection with Semi-Sampling

Wanli Ouyang, Binbin Lin, Xiaopei Wu, 2022, ArXiv.

OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

Binbin Lin, Deng Cai, Chenxi Huang, 2022, ArXiv.

One-shot Implicit Animatable Avatars with Model-based Priors

Binbin Lin, Weiyang Liu, Boxi Wu, 2022, ArXiv.

Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations

Minghao Chen, Boxi Wu, Deng Cai, 2022, ArXiv.

Apparel-Invariant Feature Learning for Person Re-Identification

Xiansheng Hua, Xiaofei He, Jianqiang Huang, 2022, IEEE Transactions on Multimedia.

Out-of-distribution Generalization via Partial Feature Decorrelation

Xiaofei He, Xin Guo, Jianqiang Huang, 2020, 2007.15241.

Robust Principal Component Analysis via Truncated Nuclear

Yao Hu, Xiaofei He, Deng Cai, 2015 .

X-View: Non-Egocentric Multi-View 3D Object Detector pdf

Guodong Xu, Deng Cai, Xiaofei He, 2021, IEEE Transactions on Image Processing.

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

Elman Mansimov, Yixuan Su, Lei Shu, 2021, ACL.

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

Xiaofei He, Deng Cai, Liang Xie, 2022, Neurocomputing.

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

Wei Liu, Wenxiao Wang, Deng Cai, 2021, ICLR.

CLRNet: Cross Layer Refinement Network for Lane Detection

Xiaofei He, Tu Zheng, Yang Liu, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Xiaopei Wu, Deng Cai, Chenxi Huang, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

Xiaofei He, Boxi Wu, Deng Cai, 2022, ICLR.

OCM3D: Object-Centric Monocular 3D Object Detection pdf

Senbo Yan, Liang Peng, Deng Cai, 2021, ArXiv.

Suppress-and-Refine Framework for End-to-End 3d Object Detection

Minghao Chen, Guodong Xu, Kuoliang Wu, 2021, SSRN Electronic Journal.

SparsePoint: Fully End-to-End Sparse 3D Object Detector

Zili Liu, Guodong Xu, Deng Cai, 2021, ArXiv.

General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Xiaofei He, Binbin Lin, Deng Cai, 2023, ArXiv.

Domain Reconstruction and Resampling for Robust Salient Object Detection

Deng Cai, Liang Peng, Zheng Yang, 2022, ACM Multimedia.

APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding

Binbin Lin, Boxi Wu, Tu Zheng, 2023, ArXiv.

One-shot Implicit Animatable Avatars with Model-based Priors

Binbin Lin, Weiyang Liu, Boxi Wu, 2022, ArXiv.

DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network

Xiaofei He, Jie Song, Tu Zheng, 2021, AAAI.

Supplementary Material: Lidar Point Cloud Guided Monocular 3D Object Detection

Fei Liu, Deng Cai, Liang Peng, 2022 .

CrossFormer: A Versatile Vision Transformer Based on Cross-scale Attention pdf

Wei Liu, Wenxiao Wang, Deng Cai, 2021, ArXiv.

Attacking Adversarial Attacks as A Defense pdf

Boxi Wu, Jindong Gu, Wei Liu, 2021, ArXiv.

Optimizing traffic efficiency via a reinforcement learning approach based on time allocation

Xiansheng Hua, Yao Hu, Xiaofei He, 2023, International Journal of Machine Learning and Cybernetics.

TTFNeXt for real-time object detection

Zili Liu, Guodong Xu, Haifeng Liu, 2021, Neurocomputing.

Learning Occupancy for Monocular 3D Object Detection

Xiaopei Wu, Boxi Wu, Deng Cai, 2023, ArXiv.

Urban Traffic Light Control via Active Multi-Agent Communication and Supply-Demand Modeling

Xiaofei He, Xin Guo, Jianqiang Huang, 2023, IEEE Transactions on Knowledge and Data Engineering.

Salient Object Ranking with Position-Preserved Attention pdf

Yao Hu, Minghao Chen, Yi Zhang, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations

Minghao Chen, Boxi Wu, Deng Cai, 2022, ArXiv.

One-shot Implicit Animatable Avatars with Model-based Priors

Binbin Lin, Weiyang Liu, Boxi Wu, 2022, ArXiv.

Discriminative-Generative Dual Memory Video Anomaly Detection pdf

Zhongming Jin, Jianqiang Huang, Deng Cai, 2021, ArXiv.

General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment

Xiaofei He, Binbin Lin, Deng Cai, 2023, ArXiv.

One-shot Implicit Animatable Avatars with Model-based Priors

Binbin Lin, Weiyang Liu, Boxi Wu, 2022, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection

Deng Cai, Liang Peng, Kejie Li, 2023, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

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

Xiaopei Wu, Deng Cai, Chenxi Huang, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

AutoTaskFormer: Searching Vision Transformers for Multi-task Learning

Shen Yan, Mi Zhang, Yang Liu, 2023, ArXiv.