Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Xinchu Shi"'
Publikováno v:
IEEE Transactions on Image Processing. 31:4447-4457
Weakly supervised action localization is a challenging task with extensive applications, which aims to identify actions and the corresponding temporal intervals with only video-level annotations available. This paper analyzes the order-sensitive and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39deed15742a677f555de34a73e92724
https://doi.org/10.1109/tip.2022.3185485
https://doi.org/10.1109/tip.2022.3185485
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198175
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebf39d82f034a6859b49c1c43ea1b0b3
https://doi.org/10.1007/978-3-031-19818-2_16
https://doi.org/10.1007/978-3-031-19818-2_16
Recently, deep learning has been successfully applied to unsupervised active learning. However, the current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design more e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d662b3160bc72bab03e98e5dd0301446
http://arxiv.org/abs/2111.04286
http://arxiv.org/abs/2111.04286
Publikováno v:
International Journal of Computer Vision. 128:360-392
The multi-dimensional assignment problem is universal for data association analysis such as data association-based visual multi-object tracking and multi-graph matching. In this paper, multi-dimensional assignment is formulated as a rank-1 tensor app
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3380d5ace991bf2ebf3ab106320f2ed
https://doi.org/10.1007/s11263-019-01231-y
https://doi.org/10.1007/s11263-019-01231-y
Publikováno v:
International Journal of Computer Vision. 127:1063-1083
High-order motion information is important in multi-target tracking (MTT) especially when dealing with large inter-target ambiguities. Such high-order information can be naturally modeled as a multi-dimensional assignment (MDA) problem, whose global
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05350ae0c42d18684974a3a19ee00853
https://doi.org/10.1007/s11263-018-01147-z
https://doi.org/10.1007/s11263-018-01147-z
Publikováno v:
CVPR
Due to its wide range of applications, matching between two graphs has been extensively studied and remains an active topic. By contrast, it is still under-exploited on how to jointly match multiple graphs, partly due to its intrinsic combinatorial i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca4d981d829604af36403cd51bea5733
https://doi.org/10.1109/cvpr.2016.547
https://doi.org/10.1109/cvpr.2016.547
Publikováno v:
Context-Enhanced Information Fusion ISBN: 9783319289694
Context-Enhanced Information Fusion
Context-Enhanced Information Fusion
Entity estimation includes tracking the numbers and types of targets in a scene and is challenging in large area surveillance due to high target density, severe similar target ambiguity, and a low sensor frame rate. Moving vehicle detection from wide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::730192d3e701db9213f76d2d0995ccf3
https://doi.org/10.1007/978-3-319-28971-7_21
https://doi.org/10.1007/978-3-319-28971-7_21
Publikováno v:
International Journal of Computer Vision. 91:303-327
Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based algorithms cannot effectively represent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df06395322d342367547c530222ca7ba
https://doi.org/10.1007/s11263-010-0399-6
https://doi.org/10.1007/s11263-010-0399-6
Publikováno v:
CVPR
Interactions between moving targets often provide dis- criminative clues for multiple target tracking (MTT), though many existing approaches ignore such interactions due to d- ifficulty in effectively handling them. In this paper, we mod- el interact
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::566d4328f337d23543062ac3093902b8
https://doi.org/10.1109/cvpr.2014.450
https://doi.org/10.1109/cvpr.2014.450
Publikováno v:
CVPR
In this paper we formulate multi-target tracking (MTT) as a rank-1 tensor approximation problem and propose an l1 norm tensor power iteration solution. In particular, a high order tensor is constructed based on trajectories in the time window, with e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1cddce4bc4138f97fd2a6f2c3075da4
https://doi.org/10.1109/cvpr.2013.309
https://doi.org/10.1109/cvpr.2013.309