Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Saneem A. Chemmengath"'
Autor:
Saneem A. Chemmengath, Brian Kingsbury, Ashish Mittal, Shreya Khare, Karthik Sankaranarayanan, Samarth Bharadwaj
Publikováno v:
INTERSPEECH
Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or commands, which restricts the quick customization of personal devices to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0dbec6925bf735a7f5b186566ae738bc
http://arxiv.org/abs/2106.15238
http://arxiv.org/abs/2106.15238
Autor:
Michael R. Glass, Vishwajeet Kumar, Feifei Pan, Alfio Gliozzo, Saneem A. Chemmengath, Rishav Chakravarti, Nicolas Rodolfo Fauceglia, Samarth Bharadwaj, Avi Sil, Mustafa Canim
Publikováno v:
NAACL-HLT
Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy on this task, specialized pre-training techniques have been developed and applied on millions of open-domain web table
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c8348b4fc76b281009d9d6af851f9fc
http://arxiv.org/abs/2104.08303
http://arxiv.org/abs/2104.08303
Autor:
Soumava Paul, Saneem A. Chemmengath, Karthik Sankaranarayanan, Suranjana Samanta, Samarth Bharadwaj
Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the resulting chang
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4de6b4682794984a33f3008b946d6b67
http://arxiv.org/abs/2003.00845
http://arxiv.org/abs/2003.00845
Autor:
Saneem A. Chemmengath, Shivkumar Kalyanaraman, Amar Prakash Azad, Vikas C. Raykar, Sachin Mehta
Publikováno v:
WACV
The impact of soiling on solar panels is an important and well-studied problem in renewable energy sector. In this paper, we present the first convolutional neural network (CNN) based approach for solar panel soiling and defect analysis. Our approach
Autor:
Disha Shrivastava, S. Agrawal, Karthik Sankaranarayanan, Anirban Laha, Anush Sankaran, Saneem A. Chemmengath
Publikováno v:
IBM Journal of Research and Development. 63:3:1-3:12
In this new era of computational creativity, where artificial intelligence (AI) systems are attempting to achieve human-level creativity, a set of golden questions needs to be answered, such as “What kind of systems are creative systems?” and “