Efficient test-time model adaptation without forgetting

S Niu, J Wu, Y Zhang, Y Chen… - International …, 2022 - proceedings.mlr.press
Test-time adaptation provides an effective means of tackling the potential distribution shift
between model training and inference, by dynamically updating the model at test time. This …

Learning to refactor action and co-occurrence features for temporal action localization

K **a, L Wang, S Zhou, N Zheng… - Proceedings of the …, 2022 - openaccess.thecvf.com
The main challenge of Temporal Action Localization is to retrieve subtle human actions from
various co-occurring ingredients, eg, context and background, in an untrimmed video. While …

Colar: Effective and efficient online action detection by consulting exemplars

L Yang, J Han, D Zhang - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Online action detection has attracted increasing research interests in recent years. Current
works model historical dependencies and anticipate the future to perceive the action …

Video action segmentation via contextually refined temporal keypoints

B Jiang, Y **, Z Tan, Y Mu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Video action segmentation refers to the task of densely casting each video frame or short
segment in an untrimmed video into some pre-specified action categories. Although recent …

Semantic and relation modulation for audio-visual event localization

H Wang, ZJ Zha, L Li, X Chen… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
We study the problem of localizing audio-visual events that are both audible and visible in a
video. Existing works focus on encoding and aligning audio and visual features at the …

Learning from noisy pseudo labels for semi-supervised temporal action localization

K **a, L Wang, S Zhou, G Hua… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Semi-Supervised Temporal Action Localization (SS-TAL) aims to improve the
generalization ability of action detectors with large-scale unlabeled videos. Albeit the recent …

Temporal action localization in the deep learning era: A survey

B Wang, Y Zhao, L Yang, T Long… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The temporal action localization research aims to discover action instances from untrimmed
videos, representing a fundamental step in the field of intelligent video understanding. With …

Compact representation and reliable classification learning for point-level weakly-supervised action localization

J Fu, J Gao, C Xu - IEEE Transactions on Image Processing, 2022 - ieeexplore.ieee.org
Point-level weakly-supervised temporal action localization (P-WSTAL) aims to localize
temporal extents of action instances and identify the corresponding categories with only a …

Videocot: A video chain-of-thought dataset with active annotation tool

Y Wang, Y Zeng, J Zheng, X **ng, J Xu, X Xu - arxiv preprint arxiv …, 2024 - arxiv.org
Multimodal large language models (MLLMs) are flourishing, but mainly focus on images with
less attention than videos, especially in sub-fields such as prompt engineering, video chain …

Uncertainty guided collaborative training for weakly supervised and unsupervised temporal action localization

W Yang, T Zhang, Y Zhang, F Wu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In weakly supervised (WSAL) and unsupervised temporal action localization (UAL), the
target is to simultaneously localize temporal boundaries and identify category labels of …