Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Houdong Hu"'
Publikováno v:
Journal of Nonlinear Science. 32
Publikováno v:
AAAI
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and
Autor:
Xiaotian Han, Quanzeng You, Chunyu Wang, Zhizheng Zhang, Peng Chu, Houdong Hu, Jiang Wang, Zicheng Liu
Multi-camera tracking systems are gaining popularity in applications that demand high-quality tracking results, such as frictionless checkout because monocular multi-object tracking (MOT) systems often fail in cluttered and crowded environments due t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ad7e4f3cba2add9ff8eb9b186d788d75
http://arxiv.org/abs/2111.15157
http://arxiv.org/abs/2111.15157
Autor:
Furu Wei, Chunyuan Li, Pengchuan Zhang, Yejin Choi, Lijuan Wang, Jianfeng Gao, Li Dong, Houdong Hu, Lei Zhang, Xi Yin, Xiaowei Hu, Xiujun Li
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585761
ECCV (30)
ECCV (30)
Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c334dda622bf9088a373d1e3fa72a53
https://doi.org/10.1007/978-3-030-58577-8_8
https://doi.org/10.1007/978-3-030-58577-8_8
Autor:
Xi Chen, Meenaz Merchant, Huang Jiapei, Houdong Hu, Yan Wang, Wu Ye, Arun Sacheti, Linjun Yang, Pavel Komlev, Huang Li
Publikováno v:
KDD
In this paper, we introduce a web-scale general visual search system deployed in Microsoft Bing. The system accommodates tens of billions of images in the index, with thousands of features for each image, and can respond in less than 200 ms. In order
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f79dbc0cbb15e66b92a7cb35fccf1cb3
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012243
ECCV (4)
ECCV (4)
In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained interplay betwee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67ef77556de63db355d868cf4a849a42
https://doi.org/10.1007/978-3-030-01225-0_13
https://doi.org/10.1007/978-3-030-01225-0_13
Publikováno v:
WACV
We propose a new framework to rank image attractiveness using a novel pairwise deep network trained with a large set of side-by-side multi-labeled image pairs from a web image index. The judges only provide relative ranking between two images without
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e593c6f4a65482bcecde12e234c4ae0b
Publikováno v:
Frontiers in Optics 2011/Laser Science XXVII.
We proposed a compact, low-cost and alignment-free plasmonic dark field microscopy and demonstrated its high contrast imaging capability through utilizing chip-scale integrated plasmonic structures to substitute for conventional condenser optics.
Publikováno v:
Applied Physics Letters. 96:113107
We propose plasmonic dark field microscopy, which utilizes a chip-scale integrated plasmonic multilayered structure to substitute the bulky and expensive conventional condenser optics. Experimental results show that we can get high contrast image usi
Publikováno v:
Applied Physics Letters; 3/15/2010, Vol. 96 Issue 11, p113107, 3p, 2 Black and White Photographs, 1 Diagram