RECORD
Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
Computer Vision and Pattern Recognition · Submitted 1 May 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results demonstrate the effectiveness of C$^3$BN on top of various baselines for WTAL with video-level and point-level supervisions.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Weakly-supervised temporal action localization (WTAL) intends to detect action instances with only weak supervision, e.g., video-level labels. The current~\textit{de facto} pipeline locates action instances by thresholding and grouping continuous high-score regions on temporal class activation sequences. In this route, the capacity of the model to recognize the relationships between adjacent snippets is of vital importance which determines the quality of the action boundaries. However, it is error-prone since the variations between adjacent snippets are typically subtle, and unfortunately this is overlooked in the literature. To tackle the issue, we propose a novel WTAL approach named Convex Combination Consistency between Neighbors (C$^3$BN). C$^3$BN consists of two key ingredients: a micro data augmentation strategy that increases the diversity in-between adjacent snippets by convex combination of adjacent snippets, and a macro-micro consistency regularization that enforces the model to be invariant to the transformations~\textit{w.r.t.} video semantics, snippet predictions, and snippet representations. Consequently, fine-grained patterns in-between adjacent snippets are enforced to be explored, thereby resulting in a more robust action boundary localization. Experimental results demonstrate the effectiveness of C$^3$BN on top of various baselines for WTAL with video-level and point-level supervisions. Code is at https://github.com/Qinying-Liu/C3BN.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Weakly-supervised temporal action localization (WTAL) intends to detect action instances with only weak supervision, e.g., video-level labels. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | The current~\textit{de facto} pipeline locates action instances by thresholding and grouping continuous high-score regions on temporal class activation sequences. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s2 | In this route, the capacity of the model to recognize the relationships between adjacent snippets is of vital importance which determines the quality of the action boundaries. | background 0.96 | 0.08 | 0.03 | asserted 1.00 |
| s3 | However, it is error-prone since the variations between adjacent snippets are typically subtle, and unfortunately this is overlooked in the literature. | gap 0.97 | 0.09 | 0.03 | asserted 0.99 |
| s4 | To tackle the issue, we propose a novel WTAL approach named Convex Combination Consistency between Neighbors (C$^3$BN). | contribution 0.98 | 0.84 | 0.06 | asserted 0.99 |
| s5 | C$^3$BN consists of two key ingredients: a micro data augmentation strategy that increases the diversity in-between adjacent snippets by convex combination of adjacent snippets, and a macro-micro consistency regularization that enforces the model to be invariant to the transformations~\textit{w.r.t.} video semantics, snippet predictions, and snippet representations. | method 0.94 | 0.86 | 0.07 | asserted 0.99 |
| s6 | Consequently, fine-grained patterns in-between adjacent snippets are enforced to be explored, thereby resulting in a more robust action boundary localization. | interpretation 0.73 | 0.65 | 0.36 | asserted 0.99 |
| s7 | Experimental results demonstrate the effectiveness of C$^3$BN on top of various baselines for WTAL with video-level and point-level supervisions. | result 1.00 | 0.95 | 0.67 | asserted 1.00 |
| s8 | Code is at https://github.com/Qinying-Liu/C3BN. | contribution 0.67 | 0.36 | 0.02 | asserted 0.70 |
What was examined, and what was not
- arXiv listing abstract v3
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Weakly-supervised temporal action localization (WTAL) intends to detect action instances with only weak supervision, e.g., video-level labels. The current~\textit{de facto} pipeline locates action instances by thresholding and grouping continuous high-score regions on temporal class activation sequences. In this route, the capacity of the model to recognize the relationships between adjacent snippets is of vital importance which determines the quality of the action boundaries. However, it is error-prone since the variations between adjacent snippets are typically subtle, and unfortunately this is overlooked in the literature. To tackle the issue, we propose a novel WTAL approach named Convex Combination Consistency between Neighbors (C$^3$BN). C$^3$BN consists of two key ingredients: a micro data augmentation strategy that increases the diversity in-between adjacent snippets by convex combination of adjacent snippets, and a macro-micro consistency regularization that enforces the model to be invariant to the transformations~\textit{w.r.t.} video semantics, snippet predictions, and snippet representations. Consequently, fine-grained patterns in-between adjacent snippets are enforced to be explored, thereby resulting in a more robust action boundary localization. Experimental results demonstrate the effectiveness of C$^3$BN on top of various baselines for WTAL with video-level and point-level supervisions. Code is at https://github.com/Qinying-Liu/C3BN.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Cites as background 1 paper
-
Some recent works [ref] have incorporated the idea of MixUp with contrastive learning.
MixCo: Mix-up Contrastive Learning for Visual Representation · Related Work · 0.85
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.