mlsanityData to 14 Oct 2026

Condensing Action Segmentation Datasets via Generative Network Inversion

arXiv 2503.14112 ↗First posted 18 Mar 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storage reduced across temporal and channel aspects. Orthogonally, we propose sampling diverse and representative action sequences to minimize video-wise redundancy. Our evaluation on standard benchmarks demonstrates consistent effectiveness in condensing TAS datasets and achieving competitive performances. Specifically, on the Breakfast dataset, our approach reduces storage by over 500× while retaining 83% of the performance compared to training with the full dataset. Furthermore, when applied to a downstream incremental learning task, it yields superior performance compared to the state-of-the-art.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

36 of 49 references.

References · 36

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2020Dataset Condensation with Gradient Matchingcited by 516
  4. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  5. 2022Dataset Distillation by Matching Training Trajectoriescited by 442
  6. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 373
  7. 2021Dataset Condensation with Distribution Matchingcited by 365
  8. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 291
  9. 2020Dataset Meta-Learning from Kernel Ridge-Regressioncited by 230
  10. 2021Dataset Distillation with Infinitely Wide Convolutional Networkscited by 218
  11. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 188
  12. 2022Scaling Up Dataset Distillation to ImageNet-1K with Constant Memorycited by 181
24 more
  1. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  2. 2021ASFormer: Transformer for Action Segmentationcited by 168
  3. 2023Dataset Distillation: A Comprehensive Reviewcited by 127
  4. 2023Generalizing Dataset Distillation via Deep Generative Priorcited by 126
  5. 2022Dataset Distillation via Factorizationcited by 115
  6. 2022Efficient Dataset Distillation Using Random Feature Approximationcited by 111
  7. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  8. 2019Unsupervised learning of action classes with continuous temporal embeddingcited by 76
  9. 2023Diffusion Action Segmentationcited by 74
  10. 2018Unsupervised Learning and Segmentation of Complex Activities from Videocited by 61
  11. 2021Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentationcited by 58
  12. 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
  13. 2016Weakly supervised learning of actions from transcriptscited by 46
  14. 2020SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentationcited by 39
  15. 2020Set-Constrained Viterbi for Set-Supervised Action Segmentationcited by 35
  16. 2022C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentationcited by 23
  17. 2023Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglementcited by 21
  18. 2021Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentationcited by 19
  19. 2022Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentationcited by 17
  20. 2021Temporal Action Segmentation with High-level Complex Activity Labelscited by 16
  21. 2023Dataset Condensation via Generative Modelcited by 15
  22. 2023Just a Glimpse: Rethinking Temporal Information for Video Continual Learningcited by 10
  23. 2024OnlineTAS: An Online Baseline for Temporal Action Segmentationcited by 7
  24. 2024Coherent Temporal Synthesis for Incremental Action Segmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillationcited by 7
  2. 2025State Diversity Matters in Offline Behavior Distillationcited by 1
  3. 2026Omnimodal Dataset Distillation via High-order Proxy Alignmentcited by 0
  4. 2026Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensationcited by 0