arXiv Computer Vision
Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 27
P2P-Former: Bridging the Supervision Gap Between Point and Proposal in Temporal Action Localization
arXiv:2610.34618v1 Announce Type: new Abstract: Recently, point-supervised temporal action localization has attracted increasing attention due to its low annotation cost (only one frame per action in...
arXiv Computer Vision
Oct 15
HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
arXiv:2610.19526v1 Announce Type: new Abstract: Temporal action detection in long untrimmed videos suffers from inaccurate localization and low-quality proposals, especially with sparse annotations a...
arXiv Computer Vision
Oct 27
Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization
arXiv:2610.35516v1 Announce Type: new Abstract: Point-supervised temporal action localization (PTAL) aims to recognize and localize action instances in untrimmed videos using only point-level annotat...
arXiv Computer Vision
Aug 27
Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining
The paper introduces Skeleton-Language feature Pooling Switching, a weakly‑supervised vision‑language pretraining strategy for skeleton‑based zero‑shot spatio‑temporal action localization. It replaces video‑level pooling with instance‑level feature computation during inference, enabling the model to estimate unseen actions without costly annotations. Additionally, Scene‑Mixed Discriminative Contrastive Learning is proposed to separate actions at the instance level within mixed scenes using a MIL framework, and experiments on four public datasets confirm the method’s effectiveness.
arXiv Computer Vision
Oct 9
LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization
The paper introduces a method that uses large language models (LLMs) to expand language queries with detailed textual descriptions of action start and end boundaries, providing richer cues for video action localization. It also proposes a training strategy that models boundary probability scores by combining semantic similarity between frames and the expanded query with temporal distance to annotated boundaries, thereby offering more consistent supervision. The approach is model‑agnostic and can be integrated into existing language‑driven action localization systems, with experiments on multiple datasets showing its effectiveness.
arXiv Computer Vision
Sep 15
Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment
arXiv:2602.01257v2 Announce Type: replace Abstract: Recently, point-supervised temporal action localization has gained significant attention for its effective balance between labeling costs and local...