MS2CAST is a semi‑supervised video anomaly detection framework that fuses multi‑scale cross‑attention between a vision transformer (MViTv2‑S) and a CNN (ConvNeXt‑T) for spatial encoding, and replaces optical flow with two interchangeable spatiotemporal modules—SwinLSTM and VMRNN—operating in latent space. The training objective combines L1 loss, Gradient Difference Loss, and Multi‑Scale SSIM to enforce pixel‑level accuracy, sharpness, and structural fidelity. Experiments on UCSD Ped2, CUHK Avenue, and ShanghaiTech show competitive ROC‑AUC scores while using less than 1 GB of GPU memory.
By Ali Safaei, Mohammad Kazemi
The paper introduces TITAnD, a Trajectory Image Transformer that converts dense and sparse GPS trajectories into a Hyperspectral Trajectory Image (HTI) and applies vision-based classification and segmentation for anomaly detection. It employs a Cyclic Factorized Transformer (CFT) that splits attention along within-day and across-day axes, drastically reducing computational cost and enabling multi-month analysis. Empirical results show TITAnD outperforms existing sparse and dense benchmarks, achieving higher AUC-PR and faster inference than comparable Transformers.
By Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath
arXiv:2510. 08073v2 Announce Type: replace-cross Abstract: AI-generated videos have achieved near-perfect visual realism (e.
By Shuhai Zhang, ZiHao Lian, Jiahao Yang, Daiyuan Li, Guoxuan Pang, Feng Liu, Bo Han, Shutao Li, Mingkui Tan
arXiv:2608.20770v1 Announce Type: new
Abstract: Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does...
By Haojin He, Hao Tan, Zichang Tan, Ajian Liu, Jun Wan
arXiv:2605. 23045v2 Announce Type: replace-cross Abstract: Video representation learning has seen tremendous progress in recent years.
By Mantas Skackauskas, Xinyue Hao, Laura Sevilla-Lara
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.
By Changqing Zhou, Yueru Luo, Zeyu Jiang, Changhao Chen
arXiv:2607. 09114v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos.
By Peipei Zhu, Yueqing Niu, Lin Zhu, Guanchong Niu, Yang Yu, Zheng Li
arXiv:2608. 11260v1 Announce Type: new Abstract: Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals.
By Shibo Gao, Peipei Yang, Xu-Yao Zhang, Linlin Huang
MoG-VLM is a motion‑guided vision‑language model designed for efficient video anomaly detection. It uses a lightweight motion signal, Temporal Gradient Magnitude, to perform content‑aware sampling and activates dense multi‑frame VLM reasoning only around frames with high anomaly likelihood via a hierarchical dual‑stream design. The method achieves state‑of‑the‑art AUC‑ROC scores on four benchmarks and delivers a 1.31× inference speedup on XD‑Violence.
By Khaled Waleed Dawoud, Muhammad Zaigham Zaheer, Khan Muhammad, Muhammad Haris Khan
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
By Jewon Yeom, Hanseul Kim, Jeongjae Park, Sungmok Jung, Jaejin Lee, Taesup Kim
arXiv:2608.31025v1 Announce Type: new
Abstract: Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remain...
By Jailing Lin, Jikuan Zhang, Jianhua Sun
Video Anomaly Detection (VAD) is inherently challenging due to the scarcity of anomalies and the large visual variability in surveillance footage, including changes in lighting, viewpoint, and human appearance. To mitigate visual noise and address privacy concerns, recent work has shifted to pose-based VAD, which focuses on motion dynamics rather than raw video data.