# Boundary-Centric Clip-Budgeted Active Learning for Temporal Action Segmentation

arXiv: https://arxiv.org/abs/2604.15173 · HTML: https://mlsanity.com/paper/2604.15173/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 70 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation](https://mlsanity.com/paper/1901.02598/) (2019)
- [My View is the Best View: Procedure Learning from Egocentric Videos](https://mlsanity.com/paper/2207.10883/) (2022)
- [Unsupervised learning of action classes with continuous temporal embedding](https://mlsanity.com/paper/1904.04189/) (2019)
- [Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment](https://mlsanity.com/paper/1803.10699/) (2018)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [Connectionist Temporal Modeling for Weakly Supervised Action Labeling](https://mlsanity.com/paper/1607.08584/) (2016)
- [Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling](https://mlsanity.com/paper/1703.08132/) (2017)
- [Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation](https://mlsanity.com/paper/2103.11264/) (2021)
- [Weakly Supervised Energy-Based Learning for Action Segmentation](https://mlsanity.com/paper/1909.13155/) (2019)
- [Temporal Action Segmentation from Timestamp Supervision](https://mlsanity.com/paper/2103.06669/) (2021)
- [Weakly supervised learning of actions from transcripts](https://mlsanity.com/paper/1610.02237/) (2016)
- [A Perceptual Prediction Framework for Self Supervised Event Segmentation](https://mlsanity.com/paper/1811.04869/) (2018)
- [Self-Supervised Learning for Semi-Supervised Temporal Action Proposal](https://mlsanity.com/paper/2104.03214/) (2021)
- [Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers](https://mlsanity.com/paper/2108.11996/) (2021)
- [StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos](https://mlsanity.com/paper/2304.13265/) (2023)
- [Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm](https://mlsanity.com/paper/2303.14382/) (2023)
- [Learning Discriminative Prototypes with Dynamic Time Warping](https://mlsanity.com/paper/2103.09458/) (2021)

## Abstract (arXiv)

Temporal action segmentation (TAS) in untrimmed videos requires dense temporal supervision. However, most of the annotation cost is spent identifying action transitions where segmentation errors concentrate and small temporal shifts can disproportionately degrade segment-level metrics. We introduce B-ACT, a clip-budgeted active learning framework that explicitly allocates supervision to these error-prone boundary regions. B-ACT operates in a hierarchical two-stage loop: (i) it ranks and queries unlabeled videos using predictive uncertainty, and (ii) within each selected video, it detects candidate transitions from the current model predictions and selects the top-K boundaries via a novel boundary score. The boundary score fuses neighborhood uncertainty, class ambiguity, and temporal prediction dynamics to reveal the underlying importance of each frame. Importantly, our annotation protocol requests labels only at the boundary frames while still training on boundary-centered clips to exploit temporal context through the model's receptive field. Extensive experiments on GTEA, 50Salads, and Breakfast demonstrate that boundary-centric supervision delivers strong label efficiency and consistently surpasses representative TAS active learning baselines and prior state of the art under sparse budgets. Gains are largest on datasets where performance is highly sensitive to boundary placement, as measured by edit and overlap-based F1 metrics.