Zobrazeno 1 - 10
of 308
pro vyhledávání: '"Jake K. Aggarwal"'
Publikováno v:
Computer Vision ISBN: 9783030032432
Computer Vision
Computer Vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b22e12e58d9418b7cc5563db1e5415cf
https://doi.org/10.1007/978-3-030-03243-2_776-1
https://doi.org/10.1007/978-3-030-03243-2_776-1
Publikováno v:
IEEE Robotics and Automation Letters. 1:593-600
Activity recognition is very useful in scenarios where robots interact with, monitor, or assist humans. In the past years many types of activities—single actions, two persons interactions or ego-centric activities, to name a few—have been analyze
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97efc87c2a281a7f01b2640185cd63d5
https://doi.org/10.1109/lra.2016.2525002
https://doi.org/10.1109/lra.2016.2525002
Publikováno v:
Pattern Recognition Letters. 65:157-162
We develop a 4D facial expression recognition algorithm.Our algorithm is suitable for both high and low-resolution RGB-D videos.4D feature learning is used for facial expression recognition.We demonstrate that feature learning is extremely effective
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be59085c91f2df2168961097823caebe
https://doi.org/10.1016/j.patrec.2015.07.039
https://doi.org/10.1016/j.patrec.2015.07.039
Publikováno v:
IJCAI
The literature in computer vision is rich of works where different types of activities -- single actions, two persons interactions or ego-centric activities, to name a few -- have been analyzed. However, traditional methods treat such types of activi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::32c10abc76a71fa258d0092412924c23
https://doi.org/10.24963/ijcai.2017/680
https://doi.org/10.24963/ijcai.2017/680
Autor:
Jake K. Aggarwal, Shaohua Wan
Publikováno v:
Pattern Recognition. 47:1859-1868
Spontaneous facial expression recognition is significantly more challenging than recognizing posed ones. We focus on two issues that are still under-addressed in this area. First, due to the inherent subtlety, the geometric and appearance features of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a1793b09201499fa55640203580da8b
https://doi.org/10.1016/j.patcog.2013.11.025
https://doi.org/10.1016/j.patcog.2013.11.025
Publikováno v:
Neurocomputing. 119:82-93
Video event description is an important research topic in video analysis with a vast amount of applications, such as visual surveillance, video retrieval, video annotation, video database indexing, and interactive system. In this paper, we present a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::351696af1b6356e1ed7d1f7bba9bce9a
https://doi.org/10.1016/j.neucom.2012.03.037
https://doi.org/10.1016/j.neucom.2012.03.037
Autor:
Michael S. Ryoo, Jake K. Aggarwal
Publikováno v:
ACM Computing Surveys. 43:1-43
Human activity recognition is an important area of computer vision research. Its applications include surveillance systems, patient monitoring systems, and a variety of systems that involve interactions between persons and electronic devices such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb664633a3b47c97007923c0acc1e6c8
https://doi.org/10.1145/1922649.1922653
https://doi.org/10.1145/1922649.1922653
Autor:
Jake K. Aggarwal, Michael S. Ryoo
Publikováno v:
International Journal of Computer Vision. 93:183-200
This paper describes a stochastic methodology for the recognition of various types of high-level group activities. Our system maintains a probabilistic representation of a group activity, describing how individual activities of its group members must
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff5de346fc6b8baa01e4b5628a50b1f5
https://doi.org/10.1007/s11263-010-0355-5
https://doi.org/10.1007/s11263-010-0355-5
Publikováno v:
Computer Vision and Image Understanding. 114:520-534
We introduce a vision-based human-computer interaction system which collaborates with a user by providing feedback during user activities. We design an intelligent workspace system that analyzes the context of a user's tasks and generates appropriate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8582c74f5994a24ca26e16d37d278371
https://doi.org/10.1016/j.cviu.2009.12.009
https://doi.org/10.1016/j.cviu.2009.12.009
Autor:
Elden Yu, Jake K. Aggarwal
Publikováno v:
International Journal of Pattern Recognition and Artificial Intelligence. 23:1309-1332
In this paper, we present two approaches to recognize a special type of human action, e.g. climbing a fence, from continuous monocular videos. Both approaches represent human activities as time series of discrete observations. In the first approach,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec888a71a1fbdbc54519db133be3abb9
https://doi.org/10.1142/s0218001409007570
https://doi.org/10.1142/s0218001409007570