Zobrazeno 1 - 10
of 1 423
pro vyhledávání: '"Chen Dapeng"'
Autor:
Liu, Hanchao, Xue, Wenyuan, Chen, Yifei, Chen, Dapeng, Zhao, Xiutian, Wang, Ke, Hou, Liping, Li, Rongjun, Peng, Wei
Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual c
Externí odkaz:
http://arxiv.org/abs/2402.00253
Large-scale visual-language pre-trained models have achieved significant success in various video tasks. However, most existing methods follow an "adapt then align" paradigm, which adapts pre-trained image encoders to model video-level representation
Externí odkaz:
http://arxiv.org/abs/2311.15619
We present PBFormer, an efficient yet powerful scene text detector that unifies the transformer with a novel text shape representation Polynomial Band (PB). The representation has four polynomial curves to fit a text's top, bottom, left, and right si
Externí odkaz:
http://arxiv.org/abs/2308.15004
Visual chart recognition systems are gaining increasing attention due to the growing demand for automatically identifying table headers and values from chart images. Current methods rely on keypoint detection to estimate data element shapes in charts
Externí odkaz:
http://arxiv.org/abs/2308.07743
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 10170-10180
Visual-Language Models (VLMs) have significantly advanced action video recognition. Supervised by the semantics of action labels, recent works adapt the visual branch of VLMs to learn video representations. Despite the effectiveness proved by these w
Externí odkaz:
http://arxiv.org/abs/2303.09756
Autor:
Huang, Yongshuai, Lu, Ning, Chen, Dapeng, Li, Yibo, Xie, Zecheng, Zhu, Shenggao, Gao, Liangcai, Peng, Wei
Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest end-to-end image-to-text approaches simultaneously predict the two structures by two decoders, wher
Externí odkaz:
http://arxiv.org/abs/2303.06949
Autor:
Chen, Dapeng1 (AUTHOR), Tong, Wen1 (AUTHOR), Ang, Bing2 (AUTHOR), Bai, Yi3 (AUTHOR), Dong, Wenhui4 (AUTHOR), Deng, Xiyue1 (AUTHOR), Wang, Chunjiong4 (AUTHOR), Zhang, Yamin3 (AUTHOR) 5020200824@nankai.edu.cn
Publikováno v:
BMC Cancer. 9/9/2024, Vol. 24 Issue 1, p1-18. 18p.
Autor:
Zeng, Bohan, Liu, Boyu, Li, Hong, Liu, Xuhui, Liu, Jianzhuang, Chen, Dapeng, Peng, Wei, Zhang, Baochang
Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the soph
Externí odkaz:
http://arxiv.org/abs/2209.10340
Autor:
Wu, Lin, Liu, Deyin, Zhang, Wenying, Chen, Dapeng, Ge, Zongyuan, Boussaid, Farid, Bennamoun, Mohammed, Shen, Jialie
Publikováno v:
IEEE Transactions on Image Processing 2022
Person re-identification (re-ID) is of great importance to video surveillance systems by estimating the similarity between a pair of cross-camera person shorts. Current methods for estimating such similarity require a large number of labeled samples
Externí odkaz:
http://arxiv.org/abs/2207.13035
Autor:
Zhou, Teng, Chen, Dapeng, Chen, Qiang, Jin, Xiuhong, Su, Min, Zhang, Hong, Tian, Liyuan, Wen, Shunhang, Zhong, Lili, Ma, Yu, Ma, Dongli, Liang, Lu, Lu, Xiaoxia, Ni, Qian, Yang, Nan, Pi, Guanghuan, Zhu, Yulin, Chen, Xing, Ma, Jinhai, Jiang, Min, Wang, Jichun, Luo, Xupeng, Li, Lan, Zhang, Xiaoning, Ma, Zhan, Zhang, Man, Zhang, Hailin, Lin, Li, Xiao, Niguang, Jiang, Wujun, Gu, Wenjing, Cai, Defeng, Chen, Hongyu, Chen, Li, Lei, Jia, Du, Hui, Li, Ying, Shao, Lili, Shang, Yunxiao, Xie, Na, Lei, Xunming, Ding, Shenggang, Liang, Yan, Dong, Linghua, Chen, Xiaoyuan, Li, Yan, Zhang, Xiaobo, He, Baoping, Ren, Luo, Liu, Enmei
Publikováno v:
In Respiratory Medicine November-December 2024 234