Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Arnav Kumar Jain"'
Publikováno v:
SIGIR
Unsupervised multi-lingual language modeling has gained attraction in the last few years and poly-lingual topic models provide a mechanism to learn aligned document representations. However, training such models require translation-aligned data acros
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::733ef0614792c0e1175e6446e8aaf011
https://doi.org/10.1145/3397271.3401231
https://doi.org/10.1145/3397271.3401231
Publikováno v:
CVPR
Contemporary deep learning based semantic inpainting can be approached from two directions. First, and the more explored, approach is to train an offline deep regression network over the masked pixels with an additional refinement by adversarial trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25d4b46e1fa38ee1eec113222e9e487b
https://doi.org/10.1109/cvpr42600.2020.01371
https://doi.org/10.1109/cvpr42600.2020.01371
Publikováno v:
ICIP
In this paper, we propose to improve the inference speed and visual quality of contemporary baseline of Generative Adversarial Networks (GAN) based unsupervised semantic inpainting. This is made possible with better initialization of the core iterati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41aee1ab93618960f3dc1d58bf2ebe93
Publikováno v:
Inpainting and Denoising Challenges ISBN: 9783030256135
We present a supervised video decaptioning algorithm driven by an encoder-decoder pixel prediction. By analogy with auto-encoders, we use U-Net with stacked dilated Convolution layer which is a convolutional neural network trained to generate the dec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4c90ad027caee5789ac4dc851b9cc11
https://doi.org/10.1007/978-3-030-25614-2_6
https://doi.org/10.1007/978-3-030-25614-2_6
Autor:
Ch V. Sai Praveen, Dacheng Tao, Deqing Sun, Jae-Seok Choi, Giang Bui, Luc Van Gool, Lei Zhang, Qi Guo, Yunjin Chen, Karen Egiazarian, Xintao Wang, Ke Yu, Jiahui Yu, Bee Oh Lim, Hojjat Seyed Mousavi, Seungjun Nah, Yulun Zhang, Ming-Hsuan Yang, Yapeng Tian, Tiep H. Vu, Zhimin Tang, Heewon Kim, Cristóvão Cruz, Vishal Monga, Yuchen Fan, Chen Change Loy, Rakesh Mehta, Jinshan Pan, Yoseob Han, Ye Duan, Truc Le, Yu Qiao, Ruxin Wang, Xiangyu Xu, Xuan-Phung Huynh, Chao Dong, Xu Jinchang, Jaejun Yoo, Thomas S. Huang, Radu Timofte, Wei Han, Xueying Qin, Zhiqiang Xia, Shaohui Li, Xu Lin, Haichao Yu, Yujin Zhang, Vladimir Katkovnik, Honghui Shi, Yu Zhao, Woong Bae, Zhengtao Wang, Abhinav Agarwalla, Arnav Kumar Jain, Ding Liu, Liang Lin, Xibin Song, Che Zhu, Wangmeng Zuo, Wen Heng, Xinchao Wang, Shixiang Wu, Zhangyang Wang, Sanghyun Son, Hongdiao Wen, Jianxin Pang, Kyoung Mu Lee, Linkai Luo, Eirikur Agustsson, Ruofan Zhou, Yuchao Dai, Min Fu, Tiantong Guo, Munchurl Kim, Jong Chul Ye, Lei Cao, Kai Zhang
Publikováno v:
CVPR Workshops
This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c975a4416e3af70966bca366ab5260f
https://doi.org/10.1109/cvprw.2017.149
https://doi.org/10.1109/cvprw.2017.149
Publikováno v:
CVPR Workshops
In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and langu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2dcf011de89905c3a34a8a555107a3c0
http://arxiv.org/abs/1611.06492
http://arxiv.org/abs/1611.06492
Publikováno v:
COMAD/CODS
We integrate learning and motion planning for soccer playing differential drive robots using Bayesian optimisation. Trajectories generated using end-slope cubic Bezier splines are first optimised globally through Bayesian optimisation for a set of ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25059df45ceab70546a499d4ab29b565
http://arxiv.org/abs/1611.01851
http://arxiv.org/abs/1611.01851