Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385373867> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4385373867 abstract "Identifying traffic accidents in driving videos is crucial to ensuring the safety of autonomous driving and driver assistance systems. To address the potential danger caused by the long-tailed distribution of driving events, existing traffic accident detection (TAD) methods mainly rely on unsupervised learning. However, TAD is still challenging due to the rapid movement of cameras and dynamic scenes in driving scenarios. Existing unsupervised TAD methods mainly rely on a single pretext task, i.e., an appearance-based or future object localization task, to detect accidents. However, appearance-based approaches are easily disturbed by the rapid movement of the camera and changes in illumination, which significantly reduce the performance of traffic accident detection. Methods based on future object localization may fail to capture appearance changes in video frames, making it difficult to detect ego-involved accidents (e.g., out of control of the ego-vehicle). In this paper, we propose a novel memory-augmented multi-task collaborative framework (MAMTCF) for unsupervised traffic accident detection in driving videos. Different from previous approaches, our method can more accurately detect both ego-involved and non-ego accidents by simultaneously modeling appearance changes and object motions in video frames through the collaboration of optical flow reconstruction and future object localization tasks. Further, we introduce a memory-augmented motion representation mechanism to fully explore the interrelation between different types of motion representations and exploit the high-level features of normal traffic patterns stored in memory to augment motion representations, thus enlarging the difference from anomalies. Experimental results on recently published large-scale dataset demonstrate that our method achieves better performance compared to previous state-of-the-art approaches." @default.
- W4385373867 created "2023-07-29" @default.
- W4385373867 creator A5016956860 @default.
- W4385373867 creator A5017214204 @default.
- W4385373867 creator A5037979193 @default.
- W4385373867 creator A5064113913 @default.
- W4385373867 creator A5079738340 @default.
- W4385373867 date "2023-07-26" @default.
- W4385373867 modified "2023-09-23" @default.
- W4385373867 title "A Memory-Augmented Multi-Task Collaborative Framework for Unsupervised Traffic Accident Detection in Driving Videos" @default.
- W4385373867 doi "https://doi.org/10.48550/arxiv.2307.14575" @default.
- W4385373867 hasPublicationYear "2023" @default.
- W4385373867 type Work @default.
- W4385373867 citedByCount "0" @default.
- W4385373867 crossrefType "posted-content" @default.
- W4385373867 hasAuthorship W4385373867A5016956860 @default.
- W4385373867 hasAuthorship W4385373867A5017214204 @default.
- W4385373867 hasAuthorship W4385373867A5037979193 @default.
- W4385373867 hasAuthorship W4385373867A5064113913 @default.
- W4385373867 hasAuthorship W4385373867A5079738340 @default.
- W4385373867 hasBestOaLocation W43853738671 @default.
- W4385373867 hasConcept C104114177 @default.
- W4385373867 hasConcept C115961682 @default.
- W4385373867 hasConcept C127413603 @default.
- W4385373867 hasConcept C153180895 @default.
- W4385373867 hasConcept C154945302 @default.
- W4385373867 hasConcept C155542232 @default.
- W4385373867 hasConcept C165696696 @default.
- W4385373867 hasConcept C201995342 @default.
- W4385373867 hasConcept C2776151529 @default.
- W4385373867 hasConcept C2780451532 @default.
- W4385373867 hasConcept C2781238097 @default.
- W4385373867 hasConcept C31972630 @default.
- W4385373867 hasConcept C38652104 @default.
- W4385373867 hasConcept C41008148 @default.
- W4385373867 hasConceptScore W4385373867C104114177 @default.
- W4385373867 hasConceptScore W4385373867C115961682 @default.
- W4385373867 hasConceptScore W4385373867C127413603 @default.
- W4385373867 hasConceptScore W4385373867C153180895 @default.
- W4385373867 hasConceptScore W4385373867C154945302 @default.
- W4385373867 hasConceptScore W4385373867C155542232 @default.
- W4385373867 hasConceptScore W4385373867C165696696 @default.
- W4385373867 hasConceptScore W4385373867C201995342 @default.
- W4385373867 hasConceptScore W4385373867C2776151529 @default.
- W4385373867 hasConceptScore W4385373867C2780451532 @default.
- W4385373867 hasConceptScore W4385373867C2781238097 @default.
- W4385373867 hasConceptScore W4385373867C31972630 @default.
- W4385373867 hasConceptScore W4385373867C38652104 @default.
- W4385373867 hasConceptScore W4385373867C41008148 @default.
- W4385373867 hasLocation W43853738671 @default.
- W4385373867 hasOpenAccess W4385373867 @default.
- W4385373867 hasPrimaryLocation W43853738671 @default.
- W4385373867 hasRelatedWork W1988485990 @default.
- W4385373867 hasRelatedWork W2007544051 @default.
- W4385373867 hasRelatedWork W2095705906 @default.
- W4385373867 hasRelatedWork W2511137960 @default.
- W4385373867 hasRelatedWork W2732308154 @default.
- W4385373867 hasRelatedWork W2975200075 @default.
- W4385373867 hasRelatedWork W3084370450 @default.
- W4385373867 hasRelatedWork W3088631390 @default.
- W4385373867 hasRelatedWork W3177406559 @default.
- W4385373867 hasRelatedWork W4281560450 @default.
- W4385373867 isParatext "false" @default.
- W4385373867 isRetracted "false" @default.
- W4385373867 workType "article" @default.