Zobrazeno 1 - 10
of 394
pro vyhledávání: '"Mohan S Kankanhalli"'
Publikováno v:
PLoS ONE, Vol 14, Iss 4, p e0214444 (2019)
Humans are able to achieve visual object recognition rapidly and effortlessly. Object categorization is commonly believed to be achieved by interaction between bottom-up and top-down cognitive processing. In the ultra-rapid categorization scenario wh
Externí odkaz:
https://doaj.org/article/bc4e8112c16341caab925234ddd48b19
Publikováno v:
PLoS ONE, Vol 14, Iss 9, p e0221390 (2019)
Sensor-based human activity recognition aims at detecting various physical activities performed by people with ubiquitous sensors. Different from existing deep learning-based method which mainly extracting black-box features from the raw sensor data,
Externí odkaz:
https://doaj.org/article/592cdbccbc6b452187169a88a0bb6815
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:1682-1699
Attending selectively to emotion-eliciting stimuli is intrinsic to human vision. \ul{In this research, we investigate how emotion-elicitation features of images relate to human selective attention.} We create the EMOtional attention dataset (EMOd). I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71d88b51fa783c2918b8c0f2fa028d37
https://doi.org/10.1109/tpami.2022.3169234
https://doi.org/10.1109/tpami.2022.3169234
Publikováno v:
IEEE Transactions on Affective Computing. 14:308-320
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::107048f9b92435c82da0217cd628b3f8
https://doi.org/10.1109/taffc.2020.3040399
https://doi.org/10.1109/taffc.2020.3040399
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:5931-5943
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb9f89c310250f5b234984fac344e1c4
https://doi.org/10.1109/tcsvt.2022.3164241
https://doi.org/10.1109/tcsvt.2022.3164241
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 18:1-20
Reconstructing three-dimensional (3D) objects from images has attracted increasing attention due to its wide applications in computer vision and robotic tasks. Despite the promising progress of recent deep learning–based approaches, which directly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc82fb672b576df438e0bf7172197e54
https://doi.org/10.1145/3491224
https://doi.org/10.1145/3491224
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:275-285
Hand-object interaction plays a very important role when humans manipulate objects. While existing methods focus on improving hand-object recognition with fully automatic methods, human intention has been largely neglected in the recognition process,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04ec8f24bdaf19707db36b5386751ce5
https://doi.org/10.1109/tcsvt.2021.3058688
https://doi.org/10.1109/tcsvt.2021.3058688
Autor:
Qingfeng Dai, Yongkang Wong, Guofei Sun, Yanwei Wang, Zhou Zhou, Mohan S. Kankanhalli, Xiangdong Li, Weidong Geng
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications.
Biometric signal based human-computer interface (HCI) has attracted increasing attention due to its wide application in healthcare, entertainment, neurocomputing, and so on. In recent years, deep learning based approaches have made great progress on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d493787d06dd553ddb4234ab8990878
https://doi.org/10.1145/3583885
https://doi.org/10.1145/3583885
Autor:
Hon Hock Woon, Hamam Mokayed, Palaiahnakote Shivakumara, Mohan S. Kankanhalli, Umapada Pal, Tong Lu
Publikováno v:
Pattern Recognition Letters. 148:45-53
License plate number detection in drone images is a complex problem because the images are generally captured at oblique angles and pose several challenges like perspective distortion, non-uniform illumination effect, degradations, blur, occlusion, l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea67598a0e4c058c680cbba082f49f12
https://doi.org/10.1016/j.patrec.2021.05.002
https://doi.org/10.1016/j.patrec.2021.05.002
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 31:1031-1041
The scene graph generated for an image structurally represents its object interactions and it substantially aids image scene understanding. To the best of our knowledge, most current works on scene graph generation chiefly focus on pairwise object re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::125d4dad24b178d1851682cad3f568d5
https://doi.org/10.1109/tcsvt.2020.2990989
https://doi.org/10.1109/tcsvt.2020.2990989