MT-CMVAD: A Multi-Modal Transformer Framework for Cross-Modal Video Anomaly Detection
Video anomaly detection (VAD) faces significant challenges in multimodal semantic alignment and long-term temporal modeling within open surveillance scenarios. Existing methods are often plagued by modality discrepancies and fragmented temporal reasoning. To address these issues, we introduce MT-CMV...
Saved in:
| Main Authors: | Hantao Ding, Shengfeng Lou, Hairong Ye, Yanbing Chen |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6773 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Video anomaly detection via cross-modal fusion and hyperbolic graph attention mechanism
by: JIANG Di, et al.
Published: (2025-06-01) -
LoRaBB: An Algorithm for Parameter Selection in LoRa-Based Communication for the Amazon Rainforest
by: Diogo Soares Moreira, et al.
Published: (2025-02-01) -
Enhancing Fast Network Recovery in LoRaWAN: Implementing Bidirectional Forwarding Detection in OMNeT++
by: Jozef Papan, et al.
Published: (2025-01-01) -
LoRA Fusion: Enhancing Image Generation
by: Dooho Choi, et al.
Published: (2024-11-01) -
Compliant and Seamless Hybrid (Star and Mesh) Network Topology Coexistence for LoRaWAN: A Proof of Concept
by: Laura García, et al.
Published: (2025-03-01)