Mouse Behavior Recognition with The Wisdom of Crowd
In this thesis, we designed and implemented a crowdsourcing system to annotatemouse behaviors in videos; this involves the development of a novel clip-based video labeling tools, that is more efficient than traditional labeling tools in crowdsourcing platform, as well as the design of probabilistic...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/80815 |
| _version_ | 1811098423119577088 |
|---|---|
| author | Ni, Yuzhao Frogner, Charles A. Poggio, Tomaso A. |
| author2 | Tomaso Poggio |
| author_facet | Tomaso Poggio Ni, Yuzhao Frogner, Charles A. Poggio, Tomaso A. |
| author_sort | Ni, Yuzhao |
| collection | MIT |
| description | In this thesis, we designed and implemented a crowdsourcing system to annotatemouse behaviors in videos; this involves the development of a novel clip-based video labeling tools, that is more efficient than traditional labeling tools in crowdsourcing platform, as well as the design of probabilistic inference algorithms that predict the true labels and the workers' expertise from multiple workers' responses. Our algorithms are shown to perform better than majority vote heuristic. We also carried out extensive experiments to determine the effectiveness of our labeling tool, inference algorithms and the overall system. |
| first_indexed | 2024-09-23T17:14:36Z |
| id | mit-1721.1/80815 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T17:14:36Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | mit-1721.1/808152019-04-12T20:51:07Z Mouse Behavior Recognition with The Wisdom of Crowd Ni, Yuzhao Frogner, Charles A. Poggio, Tomaso A. Tomaso Poggio Center for Biological and Computational Learning (CBCL) crowdsourcing video labeling human computation mouse phenotyping action recognition In this thesis, we designed and implemented a crowdsourcing system to annotatemouse behaviors in videos; this involves the development of a novel clip-based video labeling tools, that is more efficient than traditional labeling tools in crowdsourcing platform, as well as the design of probabilistic inference algorithms that predict the true labels and the workers' expertise from multiple workers' responses. Our algorithms are shown to perform better than majority vote heuristic. We also carried out extensive experiments to determine the effectiveness of our labeling tool, inference algorithms and the overall system. 2013-09-19T22:30:06Z 2013-09-19T22:30:06Z 2013-09-19 2013-09-19T22:30:06Z http://hdl.handle.net/1721.1/80815 MIT-CSAIL-TR-2013-023 CBCL-314 69 p. application/pdf |
| spellingShingle | crowdsourcing video labeling human computation mouse phenotyping action recognition Ni, Yuzhao Frogner, Charles A. Poggio, Tomaso A. Mouse Behavior Recognition with The Wisdom of Crowd |
| title | Mouse Behavior Recognition with The Wisdom of Crowd |
| title_full | Mouse Behavior Recognition with The Wisdom of Crowd |
| title_fullStr | Mouse Behavior Recognition with The Wisdom of Crowd |
| title_full_unstemmed | Mouse Behavior Recognition with The Wisdom of Crowd |
| title_short | Mouse Behavior Recognition with The Wisdom of Crowd |
| title_sort | mouse behavior recognition with the wisdom of crowd |
| topic | crowdsourcing video labeling human computation mouse phenotyping action recognition |
| url | http://hdl.handle.net/1721.1/80815 |
| work_keys_str_mv | AT niyuzhao mousebehaviorrecognitionwiththewisdomofcrowd AT frognercharlesa mousebehaviorrecognitionwiththewisdomofcrowd AT poggiotomasoa mousebehaviorrecognitionwiththewisdomofcrowd |