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: | Fang, Xiang, Arvind Easwaran, Genest, Blaise |
---|---|
Other Authors: | Interdisciplinary Graduate School (IGS) |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/178516 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Demo abstract: real-time out-of-distribution detection on a mobile robot
by: Yuhas, Michael, et al.
Published: (2023) -
Co-design of out-of-distribution detectors for autonomous emergency braking systems
by: Yuhas, Michael, et al.
Published: (2023) -
Combining facial appearance and dynamics for face recognition
by: Ye, N., et al.
Published: (2013) -
Motion planning under uncertainty for robotic tasks with long time horizons
by: Kurniawati, H., et al.
Published: (2013) -
DenseTrack : Drone-based crowd tracking via density-aware motion-appearance synergy
by: LEI, Yi, et al.
Published: (2024)