Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Yunhong Wang"'
Publikováno v:
MultiMedia Modeling ISBN: 9783030983574
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51e75b8c38c361dcc094a593000ee8ca
https://doi.org/10.1007/978-3-030-98358-1_12
https://doi.org/10.1007/978-3-030-98358-1_12
Publikováno v:
MultiMedia Modeling ISBN: 9783030678319
MMM (1)
MMM (1)
Group activity recognition in multi-person scene videos is a challenging task. Most previous approaches fail to provide a practical solution to describe the person relations and distribution within the scene, which is important for understanding grou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5841e41ed83ea0dbd359396c3fcd8f24
https://doi.org/10.1007/978-3-030-67832-6_11
https://doi.org/10.1007/978-3-030-67832-6_11
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783030606381
PRCV (2)
PRCV (2)
Action quality assessment, which aims at evaluating the performance of specific actions, has drawn more and more attention due to its extensive demand in sports, health care, etc. Unlike action recognition, in which a few typical frames are sufficien
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89f1e434a9d13f744f1e224a404de313
https://doi.org/10.1007/978-3-030-60639-8_1
https://doi.org/10.1007/978-3-030-60639-8_1
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585167
ECCV (16)
ECCV (16)
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5285f65e13c2aa353387aeee35d15808
https://doi.org/10.1007/978-3-030-58517-4_27
https://doi.org/10.1007/978-3-030-58517-4_27
Publikováno v:
MultiMedia Modeling ISBN: 9783030377304
MMM (1)
MMM (1)
Visual sentiment analysis (VSA) is a challenging task which attracts wide attention from researchers for its great application potentials. Existing works for VSA mostly extract global representations of images for sentiment prediction, ignoring the d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2016624e8b9b5ef68c39e6eca7df0bf7
https://doi.org/10.1007/978-3-030-37731-1_25
https://doi.org/10.1007/978-3-030-37731-1_25
Publikováno v:
Neural Information Processing ISBN: 9783030367077
ICONIP (1)
ICONIP (1)
Nowadays, the research for learning representations with deep neural networks (DNNs) is attracting more and more attentions. In general, most of studies focus on designing principles for learning representations when the learning model is stochastic,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b47d4464730be13561f69e503152890
https://doi.org/10.1007/978-3-030-36708-4_21
https://doi.org/10.1007/978-3-030-36708-4_21
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783030317225
PRCV (2)
PRCV (2)
In this paper, we first tackle the problem of pedestrian attribute recognition by video-based approach. The challenge mainly lies in spatial and temporal modeling and how to integrating them for effective and dynamic pedestrian representation. To sol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58b0bfd2b1d5e4e36fd7c37f0775bfe1
https://doi.org/10.1007/978-3-030-31723-2_18
https://doi.org/10.1007/978-3-030-31723-2_18
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030305079
ICANN (3)
ICANN (3)
Detecting visual relationships between objects in an image still remains challenging, because the relationships are difficult to be modeled and the class imbalance problem tends to jeopardize the predictions. To alleviate these problems, we propose a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85971efb9dd97e39241b4e223513b004
https://doi.org/10.1007/978-3-030-30508-6_49
https://doi.org/10.1007/978-3-030-30508-6_49
Publikováno v:
MultiMedia Modeling ISBN: 9783030057091
MMM (1)
MMM (1)
This paper addresses multiple athletes tracking problem. Athletes tracking is the key to whether sports video analysis can be more effective and practical or not. One great challenge faced by multi-athlete tracking is that athletes, especially the at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93d8f95217077351b60aa41d00eb14b2
https://doi.org/10.1007/978-3-030-05710-7_34
https://doi.org/10.1007/978-3-030-05710-7_34
Publikováno v:
MultiMedia Modeling ISBN: 9783319736020
MMM (1)
MMM (1)
Remote sensing image fusion (or pan-sharpening) aims at generating high resolution multi-spectral (MS) image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral image. In this pape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4917dfc78de668284f856570bf6e96a
https://doi.org/10.1007/978-3-319-73603-7_35
https://doi.org/10.1007/978-3-319-73603-7_35