Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Han Chuchu"'
Autor:
Zhang, Huaxin, Xu, Xiaohao, Wang, Xiang, Zuo, Jialong, Han, Chuchu, Huang, Xiaonan, Gao, Changxin, Wang, Yuehuan, Sang, Nong
Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that levera
Externí odkaz:
http://arxiv.org/abs/2406.12235
Autor:
Chen, Qiang, Su, Xiangbo, Zhang, Xinyu, Wang, Jian, Chen, Jiahui, Shen, Yunpeng, Han, Chuchu, Chen, Ziliang, Xu, Weixiang, Li, Fanrong, Zhang, Shan, Yao, Kun, Ding, Errui, Zhang, Gang, Wang, Jingdong
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages rece
Externí odkaz:
http://arxiv.org/abs/2406.03459
Publikováno v:
Zeitschrift für Kristallographie - New Crystal Structures, Vol 236, Iss 1, Pp 219-221 (2021)
C22H25NO5, monoclinic, P21/c (no. 14), a = 15.7241(13) Å, b = 7.0223(5) Å, c = 18.4613(14) Å, β = 100.329(4)°, V = 2005.4(3) Å3, Z = 4, Rgt(F) = 0.0495, wRref(F2) = 0.1564, T = 296(2) K.
Externí odkaz:
https://doaj.org/article/4a5263ba328e411fa0503adcb72c2d6f
Publikováno v:
Zeitschrift für Kristallographie - New Crystal Structures, Vol 235, Iss 6, Pp 1335-1337 (2020)
C15H16O2, triclinic, P1̄ (no. 2), a = 5.6034(7) Å, b = 8.7105(11) Å, c = 12.5661(16) Å, α = 92.790(7)°, β = 100.516(7)°, γ = 106.105(6)°, V = 576.15(13) Å3, Z = 2, Rgt(F) = 0.0476, wRref(F2) = 0.1348, T = 296.15 K.
Externí odkaz:
https://doaj.org/article/d5f4a2c2f5ec401e8dfca56174478007
Autor:
Zhang, Huaxin, Wang, Xiang, Xu, Xiaohao, Huang, Xiaonan, Han, Chuchu, Wang, Yuehuan, Gao, Changxin, Zhang, Shanjun, Sang, Nong
In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite significant progress, these methods still suffer from unsatisfactory results
Externí odkaz:
http://arxiv.org/abs/2403.06154
Autor:
Hong, Jiahao, Zuo, Jialong, Han, Chuchu, Zheng, Ruochen, Tian, Ming, Gao, Changxin, Sang, Nong
Recent unsupervised person re-identification (re-ID) methods achieve high performance by leveraging fine-grained local context. These methods are referred to as part-based methods. However, most part-based methods obtain local contexts through horizo
Externí odkaz:
http://arxiv.org/abs/2403.00261
Publikováno v:
Zeitschrift für Kristallographie - New Crystal Structures, Vol 235, Iss 6, Pp 1347-1348 (2020)
C15H16O, monoclinic, P21/c (no. 14), a = 5.4371(7) Å, b = 17.567(2) Å, c = 11.8840(18) Å, β = 101.043(9)°, V = 1114.1(3) Å3, Z = 4, Rgt(F) = 0.0422, wRref(F2) = 0.1155, T = 296(2) K.
Externí odkaz:
https://doaj.org/article/06c562d2ede34175aaef9f1277e7f068
Autor:
Chen, Qiang, Wang, Jian, Han, Chuchu, Zhang, Shan, Li, Zexian, Chen, Xiaokang, Chen, Jiahui, Wang, Xiaodi, Han, Shuming, Zhang, Gang, Feng, Haocheng, Yao, Kun, Han, Junyu, Ding, Errui, Wang, Jingdong
We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~\cite{dosovitskiy2020image}, a DETR variant DINO~\cite{zhang2022dino}, and an e
Externí odkaz:
http://arxiv.org/abs/2211.03594
Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent
Externí odkaz:
http://arxiv.org/abs/2202.13123
Autor:
Wu, Yuhang, Huang, Tengteng, Yao, Haotian, Zhang, Chi, Shao, Yuanjie, Han, Chuchu, Gao, Changxin, Sang, Nong
Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the ins
Externí odkaz:
http://arxiv.org/abs/2112.11689