Zobrazeno 1 - 10
of 124
pro vyhledávání: '"John R. Kender"'
Autor:
Alexander Haubold, John R. Kender
Publikováno v:
2007 Annual Conference & Exposition Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c66fa002d11eb39748fb6e45e1082f3
https://doi.org/10.18260/1-2--2422
https://doi.org/10.18260/1-2--2422
Autor:
Siyu Huo, Patrick Watson, Bishwaranjan Bhattacharjee, Sharath Pankanti, Brian M. Belgodere, John R. Kender, Parijat Dube, Michael R. Glass, Noel C. F. Codella, Matthew L. Hill
Publikováno v:
CVPR Workshops
Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for use in a n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec947aa30545ea8ace75e0b1e4c60021
https://doi.org/10.1109/cvprw50498.2020.00388
https://doi.org/10.1109/cvprw50498.2020.00388
Publikováno v:
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing.
Transfer learning is a popular technique to learn a task using less training data and fewer compute resources. However, selecting the correct source model for transfer learning is a challenging task. We demonstrate a novel predictive method that dete
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a249057222461601837b957d60f5b71
https://doi.org/10.18653/v1/2020.sustainlp-1.15
https://doi.org/10.18653/v1/2020.sustainlp-1.15
Publikováno v:
CVPR Workshops
Predicting and understanding human motion dynamics has many applications, such as motion synthesis, augmented reality, security, and autonomous vehicles. Due to the recent success of generative adversarial networks (GAN), there has been much interest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a09d66e7bccbd6cb23d7440fddf3d685
https://doi.org/10.1109/cvprw.2018.00191
https://doi.org/10.1109/cvprw.2018.00191
Autor:
Chun-Yu Tsai, John R. Kender
Publikováno v:
ACM Multimedia (Thematic Workshops)
Many videos on the Web about international events are maintained in different countries, and some come with text descriptions from different cultural points of view. We introduce a new task-detecting culture-specific tags for news videos: given video
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e57a43ae792192c5d88d953eb86427ff
https://doi.org/10.1145/3126686.3126754
https://doi.org/10.1145/3126686.3126754
Publikováno v:
iV&L-MM@MM
We present a novel and efficient constrained tensor factorization algorithm that first represents a video archive, of multimedia news stories concerning a news event, as a sparse tensor of order 4. The dimensions correspond to extracted visual memes,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::952775213df05a9d83d254f2b3bb714c
https://doi.org/10.1145/2983563.2983564
https://doi.org/10.1145/2983563.2983564
Publikováno v:
2016 International Conference on Audio, Language and Image Processing (ICALIP).
When analyzing news videos, finding an efficient way of extracting visual memes is very important. Videos might be very long and visual meme extraction itself is computationally expensive, so it is essential to make this process as efficient as possi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c00d3c41e3ee92cabbc61c809b8297c
https://doi.org/10.1109/icalip.2016.7846669
https://doi.org/10.1109/icalip.2016.7846669
Publikováno v:
Data Mining and Knowledge Discovery. 21:153-185
The global pattern mining step in existing pattern-based hierarchical clustering algorithms may result in an unpredictable number of patterns. In this paper, we propose IDHC, a pattern-based hierarchical clustering algorithm that builds a cluster hie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c0cc0839d8cdd52e27865ad7b7aa4258
https://doi.org/10.1007/s10618-010-0172-z
https://doi.org/10.1007/s10618-010-0172-z
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 18:12-22
In this paper, we introduce a new method to estimate a parametric description of the dominant motion existing in a video sequence, a key task needed to face more complex video analysis problems. In order to do so, we use motion data provided by the M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9aa4ebdbb82a58588704464a31bbdfa4
https://doi.org/10.1109/tcsvt.2007.903804
https://doi.org/10.1109/tcsvt.2007.903804
Autor:
Chun-Yu Tsai, John R. Kender
Publikováno v:
ACM Multimedia
Many videos on the Web are created in different countries about the same international event. Their specialized video content, as well as their viewing and reposting rates, reflect different cultural interests. Effectively tracking cross-cultural vis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0e0fb165e238201f07afd639de0253a
https://doi.org/10.1145/2733373.2806372
https://doi.org/10.1145/2733373.2806372