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...
Saved in:
Main Authors: | , , |
---|---|
其他作者: | |
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!
|