Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Jian-Fang Hu"'
Publikováno v:
IEEE Transactions on Image Processing. 29:29-43
Collective activity recognition, which tells what activity a group of people is performing, is a cutting-edge research topic in computer vision. Different from action performed by individuals, collective activity needs to consider the complex interac
Publikováno v:
Artificial Intelligence ISBN: 9783031204968
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bdb2eb827c896273e49973c18c3bff6c
https://doi.org/10.1007/978-3-031-20497-5_25
https://doi.org/10.1007/978-3-031-20497-5_25
Publikováno v:
Artificial Intelligence ISBN: 9783031204968
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb97a18464ea5289c67fcee2c4741682
https://doi.org/10.1007/978-3-031-20497-5_42
https://doi.org/10.1007/978-3-031-20497-5_42
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Publikováno v:
AAAI
Predicting action class from partially observed videos, which is known as action prediction, is an important task in computer vision field with many applications. The challenge for action prediction mainly lies in the lack of discriminative action in
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(7)
Despite the remarkable progress achieved in conventional instance segmentation, the problem of predicting instance segmentation results for unobserved future frames remains challenging due to the unobservability of future data. Existing methods mainl
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783030606329
PRCV (1)
PRCV (1)
In this paper, we focus on aggregating spatio-temporal contextual information for video object segmentation. Our approach exploits the spatio-temporal relationship among image regions by modelling the dependencies among the corresponding visual featu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca87f61298e3d2cb996af1cdcd9a7f20
https://doi.org/10.1007/978-3-030-60633-6_45
https://doi.org/10.1007/978-3-030-60633-6_45
Publikováno v:
CVPR
In this paper, we focus on heterogeneous features learning for RGB-D activity recognition. We find that features from different channels (RGB, depth) could share some similar hidden structures, and then propose a joint learning model to simultaneousl
Publikováno v:
Pattern Recognition. 68:272-285
A sparse transfer model was proposed to fuse a set of source face shapes in a selective way in order to assist the shape reconstruction of target face.A non-Lambertian reflectance model was formulated to model the interaction between light and the su
Publikováno v:
Environmental Pollution. 226:394-403
Polybrominated dibenzo-p-dioxins (PBDDs) and hydroxylated polybrominated diphenyl ethers (OH-PBDEs) can be formed from bromophenols (BPs) by thermal degradation, biosynthesis or phototransformation. However, it is unknown whether PBDDs and OH-PBDEs c