mlsanityData to 7 Oct 2026

SFGANS Self-supervised Future Generator for human ActioN Segmentation

arXiv 2401.00438 ↗First posted 31 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The ability to locate and classify action segments in long untrimmed video is of particular interest to many applications such as autonomous cars, robotics and healthcare applications. Today, the most popular pipeline for action segmentation is composed of encoding the frames into feature vectors, which are then processed by a temporal model for segmentation. In this paper we present a self-supervised method that comes in the middle of the standard pipeline and generated refined representations of the original feature vectors. Experiments show that this method improves the performance of existing models on different sub-tasks of action segmentation, even without additional hyper parameter tuning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 31 Dec 2023.

Builds on

31 of 46 references.

References · 31

  1. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  2. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  5. 2017Mixed Precision Trainingcited by 1,135
  6. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  7. 2014Show and Tell: A Neural Image Caption Generatorcited by 877
  8. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  9. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
  10. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  11. 2015Unsupervised Learning of Video Representations using LSTMscited by 434
  12. 2016Generating Videos with Scene Dynamicscited by 376
19 more
  1. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
  2. 2016EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videoscited by 366
  3. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  4. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  5. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  6. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
  7. 2021Anticipative Video Transformercited by 197
  8. 2021ASFormer: Transformer for Action Segmentationcited by 166
  9. 2017Learning to Generate Long-term Future via Hierarchical Predictioncited by 88
  10. 2020Action Segmentation with Joint Self-Supervised Temporal Domain Adaptationcited by 74
  11. 2017Dual Motion GAN for Future-Flow Embedded Video Predictioncited by 69
  12. 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
  13. 2020Towards Practical Lipreading with Distilled and Efficient Modelscited by 44
  14. 2019Action Recognition from Single Timestamp Supervision in Untrimmed Videoscited by 31
  15. 2020Temporal Relational Modeling with Self-Supervision for Action Segmentationcited by 29
  16. 2021Video-based fully automatic assessment of open surgery suturing skillscited by 12
  17. 2021Future Frame Prediction for Robot-assisted Surgerycited by 11
  18. 2022Bounded Future MS-TCN++ for surgical gesture recognitioncited by 5
  19. 2019Inception-inspired LSTM for Next-frame Video Predictioncited by 1

Built on by

Not cited yet.