Training-Free VLM-Based Pseudo Label Generation for Video Anomaly Detection
Video anomaly detection in weakly supervised settings remains a challenging task due to the absence of frame-level annotations. To address this, we propose a novel training-free pseudo-label generation module (TFPLG) for Weakly Supervised Video Anomaly Detection (WSVAD), which leverages the vision-l...
Saved in:
| Main Authors: | Moshira Abdalla, Sajid Javed |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11015429/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhancing Weakly-Supervised Video Anomaly Detection With Temporal Constraints
by: Francisco Caetano, et al.
Published: (2025-01-01) -
RelVid: Relational Learning with Vision-Language Models for Weakly Video Anomaly Detection
by: Jingxin Wang, et al.
Published: (2025-03-01) -
A Self-Paced Multiple Instance Learning Framework for Weakly Supervised Video Anomaly Detection
by: Ping He, et al.
Published: (2025-01-01) -
An Image Grid Can Be Worth a Video: Zero-Shot Video Question Answering Using a VLM
by: Wonkyun Kim, et al.
Published: (2024-01-01) -
Unsupervised Video Anomaly Detection Using Video Vision Transformer and Adversarial Training
by: Shimpei Kobayashi, et al.
Published: (2025-01-01)