DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fatima, Mishal | ko |
dc.contributor.author | Khan, Muhammad Umar Karim | ko |
dc.contributor.author | Kyung, Chong-Min | ko |
dc.date.accessioned | 2021-10-29T01:50:28Z | - |
dc.date.available | 2021-10-29T01:50:28Z | - |
dc.date.created | 2021-10-27 | - |
dc.date.issued | 2021-01 | - |
dc.identifier.citation | 25th International Conference on Pattern Recognition (ICPR), pp.2809 - 2816 | - |
dc.identifier.issn | 1051-4651 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288433 | - |
dc.description.abstract | Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance. In order to recognize abnormal events such as traffic accidents in a video sequence, it is important that the network takes into account interactions of objects in a given frame. We propose a novel Feature Aggregation (FA) block that refines each object's features by computing a weighted sum of the features of all objects in a frame. We use FA block along with Long Short Term Memory (LSTM) network to anticipate accidents in the video sequences. We report mean Average Precision (mAP) and Average Time-to-Accident (ATTA) on Street Accident (SA) dataset. Our proposed method achieves the highest score for risk anticipation by predicting accidents 0.32 sec and 0.75 sec earlier compared to the best results with Adaptive Loss and dynamic parameter prediction based methods respectively. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Global Feature Aggregation for Accident Anticipation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000678409202120 | - |
dc.identifier.scopusid | 2-s2.0-85110506171 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 2809 | - |
dc.citation.endingpage | 2816 | - |
dc.citation.publicationname | 25th International Conference on Pattern Recognition (ICPR) | - |
dc.identifier.conferencecountry | IT | - |
dc.identifier.conferencelocation | Milan | - |
dc.identifier.doi | 10.1109/ICPR48806.2021.9412338 | - |
dc.contributor.localauthor | Kyung, Chong-Min | - |
dc.contributor.nonIdAuthor | Fatima, Mishal | - |
dc.contributor.nonIdAuthor | Khan, Muhammad Umar Karim | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.