The proposed MSMANet, a lightweight Multi-Scale Motion-Aware Network that combines implicit spatiotemporal learning with explicit motion decomposition, achieves competitive performance with significantly fewer parameters compared to state-of-the-art models and is suitable for resource-constrained deployment scenarios.
Video anomaly detection (VAD) is a challenging task for surveillance systems due to the scarcity and diversity of anomalous events. While semi-supervised VAD approaches have advanced the field, many rely on computationally intensive optical flow networks to capture motion dynamics. Convolutional neural networks (CNNs)...
TT-VidT leads Jester, Something-Something V2, ARID, and Diving48 fine-tuning simultaneously, improving over the strongest non-TT row by 54% ~ 121%, while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA2.
Shih-Ying Yeh, Daniel Z. Kaplan, Xue-Hai Wang et al.· arXiv.org· 0 citations
Experimental results demonstrate that STM-Net outperforms state-of-the-art methods in both objective metrics and subjective visual quality, providing a robust solution for screen content artifacts.
An Event-guided Neural Video Codec (ENVC) is proposed that uses events shared by the encoder and decoder to improve RGB compression efficiency and demonstrates the potential of events as a complementary modality for reducing the RGB coding rate.
Ji-Yun Kong, Jungwoo Kim, Enes Eray Demirtas et al.· 0 citations
Dynamic Vision Sensors (DVS) encode visual information as asynchronous brightness change events, enabling microsecond-level temporal resolution, high-dynamic range and power efficiency, making them particularly attractive for computationally constrained embedded systems. The prior art shows that most works tackle the p...
V. Nagamani, K. M. Krishna, P. Menon et al.· 2026 6th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.