S
Subhashini Venugopalan
Researcher at Google
Publications - 62
Citations - 19468
Subhashini Venugopalan is an academic researcher from Google. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 22, co-authored 50 publications receiving 15683 citations. Previous affiliations of Subhashini Venugopalan include IBM & University of Texas at Austin.
Papers
More filters
Posted Content
A Multi-scale Multiple Instance Video Description Network
TL;DR: This paper integrates the base CNN into several fully convolutional neural networks to form a multi-scale network that handles multiple receptive field sizes in the original image and incorporates the Multiple Instance Learning mechanism (MIL) to consider objects in different positions and at different scales simultaneously.
Journal ArticleDOI
Predicting Risk of Developing Diabetic Retinopathy using Deep Learning.
Ashish Bora,Siva Balasubramanian,Boris Babenko,Sunny Virmani,Subhashini Venugopalan,Akinori Mitani,Guilherme de Oliveira Marinho,Jorge Cuadros,Paisan Ruamviboonsuk,Greg S. Corrado,Lily Peng,Dale R. Webster,Avinash V. Varadarajan,Naama Hammel,Yun Liu,Pinal Bavishi +15 more
TL;DR: The deep-learning systems predicted diabetic retinopathy development using colour fundus photographs, and the systems were independent of and more informative than available risk factors.
Proceedings ArticleDOI
Semantic Text Summarization of Long Videos
Shagan Sah,Sourabh Kulhare,Allison Gray,Subhashini Venugopalan,Emily Prud'hommeaux,Raymond Ptucha +5 more
TL;DR: This work proposes methods to generate visual summaries of long videos, and in addition proposes techniques to annotate and generate textual summary of the videos using recurrent networks.
Proceedings ArticleDOI
Guided Integrated Gradients: an Adaptive Path Method for Removing Noise
Andrei Kapishnikov,Subhashini Venugopalan,Besim Avci,Ben Wedin,Michael Terry,Tolga Bolukbasi +5 more
TL;DR: Guided integrated gradient (Guided IG) as mentioned in this paper proposes to adapt the attribution path itself by conditioning the path not only on the image, but also on the model being explained.
Posted Content
Captioning Images with Diverse Objects
Subhashini Venugopalan,Lisa Anne Hendricks,Marcus Rohrbach,Raymond J. Mooney,Trevor Darrell,Kate Saenko +5 more
TL;DR: The Novel Object Captioner (NOC) is proposed, a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets, taking advantage of external sources, labeled images from object recognition datasets, and semantic knowledge extracted from unannotated text.