Enhancing Single-Frame Supervision for Better Temporal Action Localization

December 08, 2023 Β· Declared Dead Β· πŸ› IEEE Transactions on Visualization and Computer Graphics

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Changjian Chen, Jiashu Chen, Weikai Yang, Haoze Wang, Johannes Knittel, Xibin Zhao, Steffen Koch, Thomas Ertl, Shixia Liu arXiv ID 2312.05178 Category cs.HC: Human-Computer Interaction Citations 9 Venue IEEE Transactions on Visualization and Computer Graphics Last Checked 4 months ago
Abstract
Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it requires only one annotated frame per action. However, it often suffers from poor performance due to the lack of precise boundary annotations. To address this issue, we propose a visual analysis method that aligns similar actions and then propagates a few user-provided annotations (e.g. , boundaries, category labels) to similar actions via the generated alignments. Our method models the alignment between actions as a heaviest path problem and the annotation propagation as a quadratic optimization problem. As the automatically generated alignments may not accurately match the associated actions and could produce inaccurate localization results, we develop a storyline visualization to explain the localization results of actions and their alignments. This visualization facilitates users in correcting wrong localization results and misalignments. The corrections are then used to improve the localization results of other actions. The effectiveness of our method in improving localization performance is demonstrated through quantitative evaluation and a case study.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted