mlsanityData to 14 Oct 2026

Boundary Voting Network for Ambiguity-Aware Timestamp-Supervised Action Segmentation

arXiv 2609.08167 ↗First posted 8 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Timestamp-supervised action segmentation aims to segment and classify actions in untrimmed videos with a random frame annotated per action. Precisely localizing action boundaries from timestamp annotations is crucial for this setting, as it enables generating framewise pseudo-labels and applying the well-explored fully-supervised training. However, prevailing methods struggle with intrinsic uncertainty in boundary localization due to less discriminative features in action-transiting regions. This imprecise boundary estimation significantly reduces the stability and reliability of the generated pseudo-labels in ambiguous action-transiting regions, consequently resulting in performance deterioration of the trained segmentation models. In our paper, we introduce the boundary voting network that mitigates feature ambiguity by hierarchically propagating video-level global prior knowledge into local action-transiting regions. By generating key action representations as votes throughout the video and targeting action-transiting regions, all votes collaboratively contribute to action-transiting feature enhancement and boundary localization refinement. Extensive experiments demonstrate the effectiveness of our method on GTEA, 50Salads, and Breakfast datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

25 of 59 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  6. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 373
  7. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 298
  8. 2021ASFormer: Transformer for Action Segmentationcited by 168
  9. 2015Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videoscited by 93
  10. 2016Segmental Spatiotemporal CNNs for Fine-grained Action Segmentationcited by 78
  11. 2023Diffusion Action Segmentationcited by 74
  12. 2022Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translationcited by 55
13 more
  1. 2022Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videoscited by 50
  2. 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
  3. 2020Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detectioncited by 42
  4. 2022Timestamp-Supervised Action Segmentation with Graph Convolutional Networkscited by 18
  5. 2017TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentationcited by 14
  6. 2024Empowering Large Language Model for Continual Video Question Answering with Collaborative Promptingcited by 14
  7. 2024Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structurecited by 13
  8. 2024Efficient Temporal Action Segmentation via Boundary-aware Query Votingcited by 10
  9. 2022Weakly-Supervised Temporal Action Localization by Progressive Complementary Learningcited by 5
  10. 2022Timestamp-Supervised Action Segmentation from the Perspective of Clusteringcited by 4
  11. 2026HOI-aware Adaptive Network for Weakly-supervised Action Segmentationcited by 3
  12. 2025Hierarchical Context Transformer for Multi-level Semantic Scene Understandingcited by 2
  13. 2022Turning to a Teacher for Timestamp Supervised Temporal Action Segmentationcited by 1

Built on by

Not cited yet.