Zobrazeno 1 - 10
of 274
pro vyhledávání: '"Songde, Ma"'
Publikováno v:
Neurocomputing. 172:225-234
The goal of this paper is to simultaneously segment the object regions in a set of images with the same object class, known as object co-segmentation. Different from typical methods, simply assuming that the common regions among images are the object
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd10e285007a50e3dab94a5f03ff7415
https://doi.org/10.1016/j.neucom.2014.12.110
https://doi.org/10.1016/j.neucom.2014.12.110
Publikováno v:
Neurocomputing. 135:155-162
With the explosive growth of surveillance video data, video synopsis technology is presented for fast browsing a day's worth of video in several minutes. However, for most existing solutions, motion structure in original videos may be destroyed even
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65d5520085f8eec73b613f238f4bc4da
https://doi.org/10.1016/j.neucom.2013.12.041
https://doi.org/10.1016/j.neucom.2013.12.041
Publikováno v:
Journal of Chemical Physics; 8/22/2003, Vol. 119 Issue 8, p4592, 5p, 2 Diagrams, 1 Chart
Publikováno v:
Pattern Recognition. 46:1841-1850
The explosive growth of cameras in public areas demands a technique which develops a fully automated surveillance and monitoring system. In this paper, we propose a novel unsupervised approach to automatically explore motion patterns occurring in dyn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab0b68a8e44e10b92e35ba78db887c6d
https://doi.org/10.1016/j.patcog.2012.11.013
https://doi.org/10.1016/j.patcog.2012.11.013
Publikováno v:
IEEE MultiMedia. 19:58-68
Using higher-level visual elements to represent images, the authors have developed a sparsity-constrained bilinear model (SBLM) and have combined a set of SBLMs in a boosting-like procedure to enhance performance.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e48dc2d4164745af2cfae148e4e031ec
https://doi.org/10.1109/mmul.2011.20
https://doi.org/10.1109/mmul.2011.20
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 17:1531-1544
In this paper, we propose a novel partwise framework for cross-parameterization between 3D mesh models. Unlike most existing methods that use regular parameterization domains, our framework uses nonregular approximation domains to build the cross-par
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e58365a75c8c5f067ddd7fab9d4964e6
https://doi.org/10.1109/tvcg.2010.231
https://doi.org/10.1109/tvcg.2010.231
Publikováno v:
Journal of Computer Science and Technology. 25:583-594
This paper proposes a novel method, called model transduction, to directly transfer pose between different meshes, without the need of building the skeleton configurations for meshes. Different from previous retargetting methods, such as deformation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d77526a92e33126390e44f2d5c391891
https://doi.org/10.1007/s11390-010-9347-8
https://doi.org/10.1007/s11390-010-9347-8
Publikováno v:
IEEE Transactions on Multimedia. 11:272-285
In recent years, weblogs (or blogs) have received great popularity worldwide, among which video blogs (or vlogs) are playing an increasingly important role. However, research on vlog analysis is still in the early stage, and how to manage vlogs effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67720a614fc971acc06abcbdce0050aa
https://doi.org/10.1109/tmm.2008.2009689
https://doi.org/10.1109/tmm.2008.2009689
Publikováno v:
Pattern Recognition. 42:218-228
Image annotation has been an active research topic in recent years due to its potential impact on both image understanding and web image search. In this paper, we propose a graph learning framework for image annotation. First, the image-based graph l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8051e1708d33cba668dd51497ed58e44
https://doi.org/10.1016/j.patcog.2008.04.012
https://doi.org/10.1016/j.patcog.2008.04.012
Publikováno v:
Neurocomputing. 71:1850-1856
In this paper, we first conceive a new perception of the kernel feature. The kernel subspace methods can be regarded as two independent steps: an explicit kernel feature extraction step and a linear subspace analysis step on the extracted kernel feat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::88a2243acd0de25cd670dd7d6f49b4b0
https://doi.org/10.1016/j.neucom.2007.10.024
https://doi.org/10.1016/j.neucom.2007.10.024