Zobrazeno 1 - 10
of 346
pro vyhledávání: '"Huang Jianqiang"'
Autor:
Liu, Qi, Tang, Xingyuan, Huang, Jianqiang, Yu, Xiangqian, Jin, Haoran, Chen, Jin, Pu, Yuanhao, Lian, Defu, Qu, Tan, Wang, Zhe, Cheng, Jia, Lei, Jun
Natural content and advertisement coexist in industrial recommendation systems but differ in data distribution. Concretely, traffic related to the advertisement is considerably sparser compared to that of natural content, which motivates the developm
Externí odkaz:
http://arxiv.org/abs/2408.16238
Autor:
Chen Xiaobin, Xu Zhaojun, Liu Tao, Dai Tianzeng, Huang Xuemei, Zheng Fan, Huang Chunyin, Huang Jianqiang, Lin Chen
Publikováno v:
Journal of Immunology Research, Vol 2022 (2022)
Background. Gastric cancer is among the most common malignant tumors at home and abroad, because its early symptoms are mostly insidious, which leads to distant metastasis when gastric cancer is first diagnosed. The common metastatic sites of gastric
Externí odkaz:
https://doaj.org/article/0a615859aae1490aad332574deba5cf7
Room acoustic parameters (RAPs) and room physical parameters (RPPs) are essential metrics for parameterizing the room acoustical characteristics (RACs) of a sound field around a listener's local environment, offering comprehensive indications for var
Externí odkaz:
http://arxiv.org/abs/2405.04476
Spatiotemporal prediction aims to generate future sequences by paradigms learned from historical contexts. It is essential in numerous domains, such as traffic flow prediction and weather forecasting. Recently, research in this field has been predomi
Externí odkaz:
http://arxiv.org/abs/2309.00314
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local struct
Externí odkaz:
http://arxiv.org/abs/2305.03944
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only foreground
Externí odkaz:
http://arxiv.org/abs/2211.10931
Autor:
Chen, Yingjie, Zhong, Huasong, Chen, Chong, Shen, Chen, Huang, Jianqiang, Wang, Tao, Liang, Yun, Sun, Qianru
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity,
Externí odkaz:
http://arxiv.org/abs/2207.11895
Autor:
Sheng, Hualian, Cai, Sijia, Zhao, Na, Deng, Bing, Huang, Jianqiang, Hua, Xian-Sheng, Zhao, Min-Jian, Lee, Gim Hee
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors. Recently, seve
Externí odkaz:
http://arxiv.org/abs/2207.09332
Autor:
Chen, Ze, Fu, Zhihang, Huang, Jianqiang, Tao, Mingyuan, Jiang, Rongxin, Tian, Xiang, Chen, Yaowu, Hua, Xian-sheng
Publikováno v:
Image and Vision Computing, Volume 116, 2021, 104314, ISSN 0262-8856
Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention from researchers. However, most of the existing methods, which are based
Externí odkaz:
http://arxiv.org/abs/2204.06899
Autor:
Hu, Mu, Feng, Junyi, Hua, Jiashen, Lai, Baisheng, Huang, Jianqiang, Gong, Xiaojin, Hua, Xiansheng
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavi
Externí odkaz:
http://arxiv.org/abs/2204.00826