Papers by Shengping Song
CMHKF: Cross-Modality Heterogeneous Knowledge Fusion for Weakly Supervised Video Anomaly Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods focus mainly on visual modalities, neglecting rich multi-modality information. |
| Approach: | They propose a framework that integrates cross-modality knowledge from video, audio and text to improve anomaly detection and localization. |
| Outcome: | The proposed framework improves detection and localization of anomalies using video-level labels. |