Alert button
Picture for Dapeng Chen

Dapeng Chen

Alert button

A Survey on Hallucination in Large Vision-Language Models

Feb 01, 2024
Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, Wei Peng

Viaarxiv icon

Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition

Nov 27, 2023
Yifei Chen, Dapeng Chen, Ruijin Liu, Sai Zhou, Wenyuan Xue, Wei Peng

Viaarxiv icon

PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer

Aug 29, 2023
Ruijin Liu, Ning Lu, Dapeng Chen, Cheng Li, Zejian Yuan, Wei Peng

Figure 1 for PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
Figure 2 for PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
Figure 3 for PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
Figure 4 for PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
Viaarxiv icon

ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition

Aug 15, 2023
Wenyuan Xue, Dapeng Chen, Baosheng Yu, Yifei Chen, Sai Zhou, Wei Peng

Figure 1 for ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Figure 2 for ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Figure 3 for ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Figure 4 for ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Viaarxiv icon

Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling

Mar 20, 2023
Yongshuai Huang, Ning Lu, Dapeng Chen, Yibo Li, Zecheng Xie, Shenggao Zhu, Liangcai Gao, Wei Peng

Figure 1 for Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Figure 2 for Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Figure 3 for Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Figure 4 for Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Viaarxiv icon

Video Action Recognition with Attentive Semantic Units

Mar 17, 2023
Yifei Chen, Dapeng Chen, Ruijin Liu, Hao Li, Wei Peng

Figure 1 for Video Action Recognition with Attentive Semantic Units
Figure 2 for Video Action Recognition with Attentive Semantic Units
Figure 3 for Video Action Recognition with Attentive Semantic Units
Figure 4 for Video Action Recognition with Attentive Semantic Units
Viaarxiv icon

FNeVR: Neural Volume Rendering for Face Animation

Sep 21, 2022
Bohan Zeng, Boyu Liu, Hong Li, Xuhui Liu, Jianzhuang Liu, Dapeng Chen, Wei Peng, Baochang Zhang

Figure 1 for FNeVR: Neural Volume Rendering for Face Animation
Figure 2 for FNeVR: Neural Volume Rendering for Face Animation
Figure 3 for FNeVR: Neural Volume Rendering for Face Animation
Figure 4 for FNeVR: Neural Volume Rendering for Face Animation
Viaarxiv icon

Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints

Dec 31, 2021
Ruijin Liu, Dapeng Chen, Tie Liu, Zhiliang Xiong, Zejian Yuan

Figure 1 for Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
Figure 2 for Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
Figure 3 for Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
Figure 4 for Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
Viaarxiv icon

Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification

May 26, 2021
Shijie Yu, Feng Zhu, Dapeng Chen, Rui Zhao, Haobin Chen, Shixiang Tang, Jinguo Zhu, Yu Qiao

Figure 1 for Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
Figure 2 for Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
Figure 3 for Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
Figure 4 for Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
Viaarxiv icon