Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Hou, Zhijian"'
Autor:
Hou, Zhijian, Ji, Lei, Gao, Difei, Zhong, Wanjun, Yan, Kun, Li, Chao, Chan, Wing-Kwong, Ngo, Chong-Wah, Duan, Nan, Shou, Mike Zheng
In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Mot
Externí odkaz:
http://arxiv.org/abs/2306.15255
Autor:
Hou, Zhijian, Zhong, Wanjun, Ji, Lei, Gao, Difei, Yan, Kun, Chan, Wing-Kwong, Ngo, Chong-Wah, Shou, Zheng, Duan, Nan
This technical report describes the CONE approach for Ego4D Natural Language Queries (NLQ) Challenge in ECCV 2022. We leverage our model CONE, an efficient window-centric COarse-to-fiNE alignment framework. Specifically, CONE dynamically slices the l
Externí odkaz:
http://arxiv.org/abs/2211.08776
Autor:
Hou, Zhijian, Zhong, Wanjun, Ji, Lei, Gao, Difei, Yan, Kun, Chan, Wing-Kwong, Ngo, Chong-Wah, Shou, Zheng, Duan, Nan
This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, w
Externí odkaz:
http://arxiv.org/abs/2209.10918
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven trai
Externí odkaz:
http://arxiv.org/abs/2207.00282
This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel CONtextual
Externí odkaz:
http://arxiv.org/abs/2109.10016
Publikováno v:
In Energy Reports June 2024 11:5125-5138
This notebook paper presents an overview and comparative analysis of our system designed for activity detection in extended videos (ActEV-PC) in ActivityNet Challenge 2019. Specifically, we exploit person/vehicle detections in spatial level and actio
Externí odkaz:
http://arxiv.org/abs/1906.08547
Autor:
Du, Heng, Lian, Zhiwei, Lai, Dayi, Duanmu, Lin, Zhai, Yongchao, Cao, Bin, Zhang, Yufeng, Zhou, Xiang, Wang, Zhaojun, Zhang, Xiaojing, Hou, Zhijian
Publikováno v:
In Energy & Buildings 15 September 2022 271
Publikováno v:
In Energy & Buildings 1 July 2022 266
Autor:
Du, Heng, Lian, Zhiwei, Lai, Dayi, Duanmu, Lin, Zhai, Yongchao, Cao, Bin, Zhang, Yufeng, Zhou, Xiang, Wang, Zhaojun, Zhang, Xiaojing, Hou, Zhijian
Publikováno v:
In Building and Environment 1 February 2022 209