Papers › PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection...

PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization

27 Aug 2024arXiv:2408.15185archive 2025-07-28

Ghazal Alinezhad Noghre, Armin Danesh Pazho, Hamed Tabkhi

Video Anomaly Detection (VAD) presents a significant challenge in computer vision, particularly due to the unpredictable and infrequent nature of anomalous events, coupled with the diverse and dynamic environments in which they occur. Human-centric VAD, a specialized area within this domain, faces additional complexities, including variations in human behavior, potential biases in data, and substantial privacy concerns related to human subjects. These issues complicate the development of models that are both robust and generalizable. To address these challenges, recent advancements have focused on pose-based VAD, which leverages human pose as a high-level feature to mitigate privacy concerns, reduce appearance biases, and minimize background interference. In this paper, we introduce PoseWatch, a novel transformer-based architecture designed specifically for human-centric pose-based VAD. PoseWatch features an innovative Spatio-Temporal Pose and Relative Pose (ST-PRP) tokenization method that enhances the representation of human motion over time, which is also beneficial for broader human behavior analysis tasks. The architecture's core, a Unified Encoder Twin Decoders (UETD) transformer, significantly improves the detection of anomalous behaviors in video data. Extensive evaluations across multiple benchmark datasets demonstrate that PoseWatch consistently outperforms existing methods, establishing a new state-of-the-art in pose-based VAD. This work not only demonstrates the efficacy of PoseWatch but also highlights the potential of integrating Natural Language Processing techniques with computer vision to advance human behavior analysis.

PaperPDFCode

Code

TeCSAR-UNCC/SPARTA mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionVideo Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Anomaly Detection CHAD PoseWatch-H AUC 67.04 #1 of 1 Archive leaderboard report
Video Anomaly Detection HR-ShanghaiTech PoseWatch-H AUC 87.23 #1 of 14 Archive leaderboard report
Video Anomaly Detection ShanghaiTech Campus PoseWatch-H AUC 85.75 #1 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections