Uncertainty-guided appearance-motion association network for out-of-distribution action detection

Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance features on image datasets, and cannot handle dynamic real-w...

全面介紹

Saved in:
書目詳細資料
Main Authors: Fang, Xiang, Arvind Easwaran, Genest, Blaise
其他作者: Interdisciplinary Graduate School (IGS)
格式: Conference or Workshop Item
語言:English
出版: 2024
主題:
在線閱讀:https://hdl.handle.net/10356/178516
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!