S
Sanketh Shetty
Researcher at Google
Publications - 23
Citations - 10325
Sanketh Shetty is an academic researcher from Google. The author has contributed to research in topics: Classifier (UML) & Block-matching algorithm. The author has an hindex of 7, co-authored 23 publications receiving 9109 citations. Previous affiliations of Sanketh Shetty include Stanford University & University of Illinois at Urbana–Champaign.
Papers
More filters
Proceedings ArticleDOI
Large-Scale Video Classification with Convolutional Neural Networks
TL;DR: This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training.
Proceedings ArticleDOI
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
TL;DR: In this paper, a cross-domain transfer between video frames and web images, using pre-trained deep convolutional neural networks, is proposed to train action recognition models with long short-term memory networks.
Proceedings ArticleDOI
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
TL;DR: This work proposes a simple yet effective method that takes weak video labels and noisy image labels as input, and generates localized action frames as output that are used to train action recognition models with long short-term memory networks.
Patent
Selecting and presenting representative frames for video previews
Sanketh Shetty,Tomas Izo,Min-Hsuan Tsai,Sudheendra Vijayanarasimhan,Apostol Natsev,Sami Abu-El-Haija,George Toderici,Susanna Ricco,Balakrishnan Varadarajan,Nicola Muscettola,WeiHsin Gu,Weilong Yang,Nitin Khandelwal,Phuong B. Le +13 more
TL;DR: In this paper, a computer-implemented method for selecting representative frames for videos is presented, which includes receiving a video and identifying a set of features for each of the frames of the video.