Deep learning-based action detection in untrimmed videos: A survey

E Vahdani, Y Tian - IEEE Transactions on Pattern Analysis and …, 2022 - ieeexplore.ieee.org
Understanding human behavior and activity facilitates advancement of numerous real-world
applications, and is critical for video analysis. Despite the progress of action recognition …

Generative cooperative learning for unsupervised video anomaly detection

MZ Zaheer, A Mahmood, MH Khan… - Proceedings of the …, 2022 - openaccess.thecvf.com
Video anomaly detection is well investigated in weakly supervised and one-class
classification (OCC) settings. However, unsupervised video anomaly detection is quite …

Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100

D Damen, H Doughty, GM Farinella, A Furnari… - International Journal of …, 2022 - Springer
This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-
KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M …

Human action recognition and prediction: A survey

Y Kong, Y Fu - International Journal of Computer Vision, 2022 - Springer
Derived from rapid advances in computer vision and machine learning, video analysis tasks
have been moving from inferring the present state to predicting the future state. Vision-based …

Fine-grained temporal contrastive learning for weakly-supervised temporal action localization

J Gao, M Chen, C Xu - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
We target at the task of weakly-supervised action localization (WSAL), where only video-
level action labels are available during model training. Despite the recent progress, existing …

Cola: Weakly-supervised temporal action localization with snippet contrastive learning

C Zhang, M Cao, D Yang, J Chen… - Proceedings of the …, 2021 - openaccess.thecvf.com
Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in
untrimmed videos with only video-level labels. Most existing models follow the" localization …

Revisiting anchor mechanisms for temporal action localization

L Yang, H Peng, D Zhang, J Fu… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Most of the current action localization methods follow an anchor-based pipeline: depicting
action instances by pre-defined anchors, learning to select the anchors closest to the ground …

Overview of temporal action detection based on deep learning

K Hu, C Shen, T Wang, K Xu, Q **a, M **a… - Artificial Intelligence …, 2024 - Springer
Abstract Temporal Action Detection (TAD) aims to accurately capture each action interval in
an untrimmed video and to understand human actions. This paper comprehensively surveys …

Two-stream consensus network for weakly-supervised temporal action localization

Y Zhai, L Wang, W Tang, Q Zhang, J Yuan… - Computer Vision–ECCV …, 2020 - Springer
Abstract Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and
localize all action instances in an untrimmed video under only video-level supervision …

Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection

MZ Zaheer, A Mahmood, M Astrid, SI Lee - Computer Vision–ECCV 2020 …, 2020 - Springer
Learning to detect real-world anomalous events through video-level labels is a challenging
task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we …