FuseMamba-VD introduces efficient dual-branch architecture for video violence detection

Researchers have introduced FuseMamba-VD, a novel dual-branch architecture for efficient video violence detection. This model combines a State Space Model (SSM) backbone with a gating mechanism to fuse spatial and temporal features, enhancing accuracy in challenging surveillance scenarios. The proposed method also introduces a new benchmark by merging several existing datasets, demonstrating state-of-the-art performance and a favorable balance between accuracy and computational efficiency. AI

IMPACT This research advances efficient video analysis techniques, potentially improving surveillance systems and other video processing applications.

RANK_REASON The cluster contains a research paper detailing a new model architecture and benchmark for video violence detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CNNS
• Damith Chamalke Senadeera
• DVD
• FuseMamba-VD
• Gated Class Token Fusion
• RLVS
• RWF-2000
• State Space Model
• transformers
• VideoMamba
• VioPeru

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →