Browsing by Author "Dobhal, T."

Now showing 1 - 4 of 4

Human Activity Recognition using Binary Motion Image and Deep Learning
(2015) Dobhal, T.; Shitole, V.; Thomas, G.; Navada, G.
View based recognition methods use visual templates for recognition and hence do not extract complex features from the image. Instead they retain the entire raw image as a single feature in high dimensional space. These example images or templates are learnt under different poses and illumination conditions for recognition. With this in mind, we build on the idea of 2-D representation of action video sequence by combining the image sequences into a single image called Binary Motion Image (BMI) to perform human activity recognition. For classification, we employ Convolutional Neural Networks which inherently provide slight invariance to translational and rotational shifts, partial occlusions as well as background noise. We test our method on Weizmann dataset focusing on actions that look similar like run, walk, jump, side and skip actions. We also extended our method to 3-D depth maps using MSR Action3D dataset by extracting three BMI projections namely the front view, the side view and the top view. From the results obtained, we believe that BMI is sufficient for activity recognition and has shown to be invariant to speed of the action performed in addition to the aforementioned variations. � 2015 Published by Elsevier B.V.
Human Activity Recognition using Binary Motion Image and Deep Learning
(Elsevier, 2015) Dobhal, T.; Shitole, V.; Thomas, G.; Girisha Navada, G.
View based recognition methods use visual templates for recognition and hence do not extract complex features from the image. Instead they retain the entire raw image as a single feature in high dimensional space. These example images or templates are learnt under different poses and illumination conditions for recognition. With this in mind, we build on the idea of 2-D representation of action video sequence by combining the image sequences into a single image called Binary Motion Image (BMI) to perform human activity recognition. For classification, we employ Convolutional Neural Networks which inherently provide slight invariance to translational and rotational shifts, partial occlusions as well as background noise. We test our method on Weizmann dataset focusing on actions that look similar like run, walk, jump, side and skip actions. We also extended our method to 3-D depth maps using MSR Action3D dataset by extracting three BMI projections namely the front view, the side view and the top view. From the results obtained, we believe that BMI is sufficient for activity recognition and has shown to be invariant to speed of the action performed in addition to the aforementioned variations. Â© 2015 Published by Elsevier B.V.
Investigating the "wisdom of crowds" at scale
(2015) Mysore, A.S.; Yaligar, V.S.; Ibarra, I.A.; Simoiu, C.; Goel, S.; Arvind, R.; Sumanth, C.; Srikantan, A.; Bhargav, H.S.; Pahadia, M.; Dobhal, T.; Ahmed, A.; Shankar, M.; Agarwal, H.; Agarwal, R.; Anirudh-Kondaveeti, S.; Arun-Gokhale, S.; Attri, A.; Chandra, A.; Chilukuri, Y.; Dharmaji, S.; Garg, D.; Gupta, N.; Gupta, P.; Jacob, G.M.; Jain, S.; Joshi, S.; Khajuria, T.; Khillan, S.; Konam, S.; Kumar-Kolla, P.; Loomba, S.; Madan, R.; Maharaja, A.; Mathur, V.; Munshi, B.; Nawazish, M.; Neehar-Kurukunda, V.; Nirmal-Gavarraju, V.; Parashar, S.; Parikh, H.; Paritala, A.; Patil, A.; Phatak, R.; Pradhan, M.; Ravichander, A.; Sangeeth, K.; Sankaranarayanan, S.; Sehgal, V.; Sheshan, A.; Shibiraj, S.; Singh, A.; Singh, A.; Sinha, P.; Soni, P.; Thomas, B.; Tuteja, L.; Varma-Dattada, K.; Venkataraman, S.; Verma, P.; Yelurwar, I.
In a variety of problem domains, it has been observed that the aggregate opinions of groups are often more accurate than those of the constituent individuals, a phenomenon that has been termed the "wisdom of the crowd." Yet, perhaps surprisingly, there is still little consensus on how generally the phenomenon holds, how best to aggregate crowd judgements, and how social influence affects estimates. We investigate these questions by taking a meta wisdom of crowds approach. With a distributed team of over 100 student researchers across 17 institutions in the United States and India, we develop a large-scale online experiment to systematically study the wisdom of crowds effect for 1,000 different tasks in 50 subject domains. These tasks involve various types of knowledge (e.g., explicit knowledge, tacit knowledge, and prediction), question formats (e.g., multiple choice and point estimation), and inputs (e.g., text, audio, and video). To examine the effect of social influence, participants are randomly assigned to one of three different experiment conditions in which they see varying degrees of information on the responses of others. In this ongoing project, we are now preparing to recruit participants via Amazon's Mechanical Turk.
Investigating the "wisdom of crowds" at scale
(Association for Computing Machinery, Inc acmhelp@acm.org, 2015) Mysore, A.S.; Yaligar, V.S.; Ibarra, I.A.; Simoiu, C.; Goel, S.; Arvind, R.; Sumanth, C.; Srikantan, A.; Bhargav, H.S.; Pahadia, M.; Dobhal, T.; Ahmed, A.; Shankar, M.; Agarwal, H.; Agarwal, R.; Anirudh-Kondaveeti, S.; Arun-Gokhale, S.; Attri, A.; Chandra, A.; Chilukuri, Y.; Dharmaji, S.; Garg, D.; Gupta, N.; Gupta, P.; Jacob, G.M.; Jain, S.; Joshi, S.; Khajuria, T.; Khillan, S.; Konam, S.; Kumar-Kolla, P.; Loomba, S.; Madan, R.; Maharaja, A.; Mathur, V.; Munshi, B.; Nawazish, M.; Neehar-Kurukunda, V.; Nirmal-Gavarraju, V.; Parashar, S.; Parikh, H.; Paritala, A.; Patil, A.; Phatak, R.; Pradhan, M.; Ravichander, A.; Sangeeth, K.; Sankaranarayanan, S.; Sehgal, V.; Sheshan, A.; Shibiraj, S.; Singh, A.; Singh, A.; Sinha, P.; Soni, P.; Thomas, B.; Tuteja, L.; Varma-Dattada, K.; Venkataraman, S.; Verma, P.; Yelurwar, I.
In a variety of problem domains, it has been observed that the aggregate opinions of groups are often more accurate than those of the constituent individuals, a phenomenon that has been termed the "wisdom of the crowd." Yet, perhaps surprisingly, there is still little consensus on how generally the phenomenon holds, how best to aggregate crowd judgements, and how social influence affects estimates. We investigate these questions by taking a meta wisdom of crowds approach. With a distributed team of over 100 student researchers across 17 institutions in the United States and India, we develop a large-scale online experiment to systematically study the wisdom of crowds effect for 1,000 different tasks in 50 subject domains. These tasks involve various types of knowledge (e.g., explicit knowledge, tacit knowledge, and prediction), question formats (e.g., multiple choice and point estimation), and inputs (e.g., text, audio, and video). To examine the effect of social influence, participants are randomly assigned to one of three different experiment conditions in which they see varying degrees of information on the responses of others. In this ongoing project, we are now preparing to recruit participants via Amazon's Mechanical Turk.