Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models

Y Liu, D Yang, Y Wang, J Liu, J Liu… - ACM Computing …, 2024 - dl.acm.org
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance
systems, enabling the temporal or spatial identification of anomalous events within videos …

Data association in multiple object tracking: A survey of recent techniques

L Rakai, H Song, SJ Sun, W Zhang, Y Yang - Expert systems with …, 2022 - Elsevier
The advances of Visual object tracking tasks in computer vision have enabled a growing
value in its application to video surveillance, particularly in a traffic scenario. In recent years …

Cityflow: A city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification

Z Tang, M Naphade, MY Liu, X Yang… - Proceedings of the …, 2019 - openaccess.thecvf.com
Urban traffic optimization using traffic cameras as sensors is driving the need to advance
state-of-the-art multi-target multi-camera (MTMC) tracking. This work introduces CityFlow, a …

Single-camera and inter-camera vehicle tracking and 3D speed estimation based on fusion of visual and semantic features

Z Tang, G Wang, H Xiao, A Zheng… - Proceedings of the …, 2018 - openaccess.thecvf.com
Tracking of vehicles across multiple cameras with non-overlapping views has been a
challenging task for the intelligent transportation system (ITS). It is mainly because of high …

Back to optimization: Diffusion-based zero-shot 3d human pose estimation

Z Jiang, Z Zhou, L Li, W Chai… - Proceedings of the …, 2024 - openaccess.thecvf.com
Learning-based methods have dominated the 3D human pose estimation (HPE) tasks with
significantly better performance in most benchmarks than traditional optimization-based …

Cross-view tracking for multi-human 3d pose estimation at over 100 fps

L Chen, H Ai, R Chen, Z Zhuang… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Estimating 3D poses of multiple humans in real-time is a classic but still challenging task in
computer vision. Its major difficulty lies in the ambiguity in cross-view association of 2D …

Divotrack: A novel dataset and baseline method for cross-view multi-object tracking in diverse open scenes

S Hao, P Liu, Y Zhan, K Jin, Z Liu, M Song… - International Journal of …, 2024 - Springer
Cross-view multi-object tracking aims to link objects between frames and camera views with
substantial overlaps. Although cross-view multi-object tracking has received increased …

Moana: An online learned adaptive appearance model for robust multiple object tracking in 3d

Z Tang, JN Hwang - IEEE Access, 2019 - ieeexplore.ieee.org
Multiple object tracking has been a challenging field, mainly due to noisy detection sets an
identity switch caused by occlusion and similar appearance among nearby targets. Previous …

Kgnet: Knowledge-guided networks for category-level 6d object pose and size estimation

Q Meng, J Gu, S Zhu, J Liao, T Jin… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Despite the giant leap made in object 6D pose estimation and robotic grasping under
structured scenarios, most approaches depend heavily on the exact CAD models of target …

Multiple human association and tracking from egocentric and complementary top views

R Han, W Feng, Y Zhang, J Zhao… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Crowded scene surveillance can significantly benefit from combining egocentric-view and its
complementary top-view cameras. A typical setting is an egocentric-view camera, eg, a …