Zobrazeno 61 - 70
of 370
pro vyhledávání: '"Sun, Xiaoshuai"'
Autor:
Chen, Fuhai, Ji, Rongrong, Dai, Chengpeng, Sun, Xiaoshuai, Lin, Chia-Wen, Ji, Jiayi, Zhang, Baochang, Huang, Feiyue, Cao, Liujuan
Image deblurring has achieved exciting progress in recent years. However, traditional methods fail to deblur severely blurred images, where semantic contents appears ambiguously. In this paper, we conduct image deblurring guided by the semantic conte
Externí odkaz:
http://arxiv.org/abs/1910.03853
Image captioning has attracted ever-increasing research attention in the multimedia community. To this end, most cutting-edge works rely on an encoder-decoder framework with attention mechanisms, which have achieved remarkable progress. However, such
Externí odkaz:
http://arxiv.org/abs/1908.02632
Autor:
Ji, Rongrong, Li, Ke, Wang, Yan, Sun, Xiaoshuai, Guo, Feng, Guo, Xiaowei, Wu, Yongjian, Huang, Feiyue, Luo, Jiebo
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a lar
Externí odkaz:
http://arxiv.org/abs/1908.02126
Autor:
Hu, Jie, Ji, Rongrong, Zhang, ShengChuan, Sun, Xiaoshuai, Ye, Qixiang, Lin, Chia-Wen, Tian, Qi
Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information ca
Externí odkaz:
http://arxiv.org/abs/1906.01288
Autor:
Lin, Mingbao, Ji, Rongrong, Chen, Shen, Zheng, Feng, Sun, Xiaoshuai, Zhang, Baochang, Cao, Liujuan, Guo, Guodong, Huang, Feiyue
Online hashing has attracted extensive research attention when facing streaming data. Most online hashing methods, learning binary codes based on pairwise similarities of training instances, fail to capture the semantic relationship, and suffer from
Externí odkaz:
http://arxiv.org/abs/1905.13382
Online image hashing has attracted increasing research attention recently, which receives large-scale data in a streaming manner to update the hash functions on-the-fly. Its key challenge lies in the difficulty of balancing the learning timeliness an
Externí odkaz:
http://arxiv.org/abs/1905.04454
Recovering the 3D representation of an object from single-view or multi-view RGB images by deep neural networks has attracted increasing attention in the past few years. Several mainstream works (e.g., 3D-R2N2) use recurrent neural networks (RNNs) to
Externí odkaz:
http://arxiv.org/abs/1901.11153
When facing large-scale image datasets, online hashing serves as a promising solution for online retrieval and prediction tasks. It encodes the online streaming data into compact binary codes, and simultaneously updates the hash functions to renew co
Externí odkaz:
http://arxiv.org/abs/1901.10185
Autor:
Sun, Xiaoshuai
In this paper, we proposed an integrated model of semantic-aware and contrast-aware saliency combining both bottom-up and top-down cues for effective saliency estimation and eye fixation prediction. The proposed model processes visual information usi
Externí odkaz:
http://arxiv.org/abs/1811.03736
Autor:
Sun, Xiaoshuai, He, Xiaojun, Zhu, Yue, Obeng, Enoch, Zeng, Bairui, Deng, Hui, Shen, Jianliang, Hu, Rongdang
Publikováno v:
In Chemical Engineering Journal 1 January 2023 451 Part 4