Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Sukhwani, Mohak"'
Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of being progr
Externí odkaz:
http://arxiv.org/abs/2104.10218
Approximately 75% of energy used in petrochemical and refining industries is consumed by furnaces. Operating furnaces at optimal conditions results in huge amounts of savings. In this paper, we model the furnace efficiency optimization as a multi-obj
Externí odkaz:
http://arxiv.org/abs/2104.08586
In this paper, we present a model for semantic memory that allows machines to collect information and experiences to become more proficient with time. Post semantic analysis of the sensory and other related data, the processed information is stored i
Externí odkaz:
http://arxiv.org/abs/2101.01099
Autor:
Jain, Parag, Agrawal, Priyanka, Mishra, Abhijit, Sukhwani, Mohak, Laha, Anirban, Sankaranarayanan, Karthik
Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity. Effective solutions or, at least evaluations of modern
Externí odkaz:
http://arxiv.org/abs/1707.05501
Autor:
Sukhwani, Mohak, Kothari, Ravi
We present a parameterized approach to produce personalized variable length summaries of soccer matches. Our approach is based on temporally segmenting the soccer video into 'plays', associating a user-specifiable 'utility' for each type of play and
Externí odkaz:
http://arxiv.org/abs/1706.09193
Autor:
Sukhwani, Mohak, Jawahar, C. V.
Automatically describing videos has ever been fascinating. In this work, we attempt to describe videos from a specific domain - broadcast videos of lawn tennis matches. Given a video shot from a tennis match, we intend to generate a textual commentar
Externí odkaz:
http://arxiv.org/abs/1511.08522
Autor:
Sahu, Devendra Kumar, Sukhwani, Mohak
We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution which uses connectionist temporal classification (
Externí odkaz:
http://arxiv.org/abs/1511.04176
Publikováno v:
2016 IEEE International Conference on Robotics & Automation (ICRA); 2016, p5121-5127, 7p
Publikováno v:
Computer Vision - ECCV 2016 Workshops; 2016, p856-870, 15p
Autor:
Sukhwani, Mohak, Singh, Suriya, Goyal, Anirudh, Behl, Aseem, Mohapatra, Pritish, Bharti, Brijendra, Jawahar, C.
Publikováno v:
2014 IEEE International Conference on Vehicular Electronics & Safety; 2014, p11-16, 6p