Zobrazeno 1 - 10
of 3 003
pro vyhledávání: '"WANG, XIAOBING"'
Scene Graph Generation (SGG) remains a challenging task due to its compositional property. Previous approaches improve prediction efficiency through end-to-end learning. However, these methods exhibit limited performance as they assume unidirectional
Externí odkaz:
http://arxiv.org/abs/2407.18715
Composed Image Retrieval (CIR) aims to retrieve images based on a query image with text. Current Zero-Shot CIR (ZS-CIR) methods try to solve CIR tasks without using expensive triplet-labeled training datasets. However, the gap between ZS-CIR and trip
Externí odkaz:
http://arxiv.org/abs/2407.05795
Autor:
Xu, Xiaoyun, Wang, Xiaobing, Muinonen, Karri, Penttil, Antti, Luo, Nanping, Gu, Shenghong, Sun, Leilei, Xu, Fukun, Liu, Yisi, Xiang, Yue, Cao, Dongtao, Wang, Jianhua
The lightcurves of asteroids are essential for determining their physical characteristics, including shape, spin, size, and surface composition. However, most asteroids are missing some of these basic physical parameters due to lack of photometric da
Externí odkaz:
http://arxiv.org/abs/2401.15320
Autor:
Zhang, Dafeng, Wang, Xiaobing
Publikováno v:
2022 IEEE International Conference on Multimedia and Expo (ICME), 2022, pp. 1-6
Recent works achieve excellent results in defocus deblurring task based on dual-pixel data using convolutional neural network (CNN), while the scarcity of data limits the exploration and attempt of vision transformer in this task. In addition, the ex
Externí odkaz:
http://arxiv.org/abs/2209.06040
Transformer-based methods have achieved impressive image restoration performance due to their capacities to model long-range dependency compared to CNN-based methods. However, advances like SwinIR adopts the window-based and local attention strategy
Externí odkaz:
http://arxiv.org/abs/2208.11247
Autor:
Yang, Ren, Timofte, Radu, Li, Xin, Zhang, Qi, Zhang, Lin, Liu, Fanglong, He, Dongliang, li, Fu, Zheng, He, Yuan, Weihang, Ostyakov, Pavel, Vyal, Dmitry, Zhussip, Magauiya, Zou, Xueyi, Yan, Youliang, Li, Lei, Tang, Jingzhu, Chen, Ming, Zhao, Shijie, Zhu, Yu, Qin, Xiaoran, Li, Chenghua, Leng, Cong, Cheng, Jian, Rota, Claudio, Buzzelli, Marco, Bianco, Simone, Schettini, Raimondo, Zhang, Dafeng, Huang, Feiyu, Liu, Shizhuo, Wang, Xiaobing, Jin, Zhezhu, Li, Bingchen, Li, Mingxi, Liu, Ding, Zou, Wenbin, Dong, Peijie, Ye, Tian, Zhang, Yunchen, Tan, Ming, Niu, Xin, Ayazoglu, Mustafa, Conde, Marcos, Choi, Ui-Jin, Jia, Zhuang, Xu, Tianyu, Zhang, Yijian, Ye, Mao, Luo, Dengyan, Pan, Xiaofeng, Peng, Liuhan
This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track~2 targets the super-resolution of compressed video
Externí odkaz:
http://arxiv.org/abs/2208.11184
Autor:
Peng, Yanan, Chen, Liping, Chen, Xiaojia, Lin, Jun, Wei, Jia, Cheng, Jie, Zhou, Feng, Ge, Liuqing, Zhou, Rui, Ding, Feng, Wang, Xiaobing
Publikováno v:
In International Immunopharmacology 5 December 2024 142 Part B
Publikováno v:
In Case Studies in Construction Materials December 2024 21
Publikováno v:
In Microbiological Research December 2024 289
Publikováno v:
In Cities December 2024 155