mlsanityData to 14 Oct 2026

FIFA: Fast Inference Approximation for Action Segmentation

arXiv 2108.03894 ↗First posted 9 Aug 2021cs.CV cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

We introduce FIFA, a fast approximate inference method for action segmentation and alignment. Unlike previous approaches, FIFA does not rely on expensive dynamic programming for inference. Instead, it uses an approximate differentiable energy function that can be minimized using gradient-descent. FIFA is a general approach that can replace exact inference improving its speed by more than 5 times while maintaining its performance. FIFA is an anytime inference algorithm that provides a better speed vs. accuracy trade-off compared to exact inference. We apply FIFA on top of state-of-the-art approaches for weakly supervised action segmentation and alignment as well as fully supervised action segmentation. FIFA achieves state-of-the-art results on most metrics on two action segmentation datasets.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

27 of 38 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2014Distributed Representations of Sentences and Documentscited by 678
  6. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  7. 2015A Neural Algorithm of Artistic Stylecited by 483
  8. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 373
  9. 2020Alleviating Over-segmentation Errors by Detecting Action Boundariescited by 87
  10. 2019D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentationcited by 83
  11. 2016Segmental Spatiotemporal CNNs for Fine-grained Action Segmentationcited by 78
  12. 2018Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignmentcited by 74
15 more
  1. 2016Connectionist Temporal Modeling for Weakly Supervised Action Labelingcited by 70
  2. 2017Weakly Supervised Action Learning with RNN based Fine-to-coarse Modelingcited by 70
  3. 2018NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learningcited by 67
  4. 2015An end-to-end generative framework for video segmentation and recognitioncited by 61
  5. 2015Structured Prediction Energy Networkscited by 59
  6. 2019Weakly Supervised Energy-Based Learning for Action Segmentationcited by 53
  7. 2014Weakly Supervised Action Labeling in Videos Under Ordering Constraintscited by 48
  8. 2016Weakly supervised learning of actions from transcriptscited by 46
  9. 2019A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentationcited by 36
  10. 2017End-to-End Learning for Structured Prediction Energy Networkscited by 33
  11. 2019Action Recognition from Single Timestamp Supervision in Untrimmed Videoscited by 31
  12. 2019Fast Weakly Supervised Action Segmentation Using Mutual Consistencycited by 30
  13. 2017Towards Decoding as Continuous Optimization in Neural Machine Translationcited by 15
  14. 2020On Evaluating Weakly Supervised Action Segmentation Methodscited by 4
  15. 2020Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videoscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 3; 2024: 4; 2025: 1; 2026: 1.

16 papers.

Sort:

By area:

  1. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  2. 2023Diffusion Action Segmentationcited by 74
  3. 2022Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translationcited by 55
  4. 2023How Much Temporal Long-Term Context is Needed for Action Segmentation?cited by 36
  5. 2024Hierarchical Vector Quantization for Unsupervised Action Segmentationcited by 19
  6. 2024Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignmentcited by 13
  7. 2024Causal Temporal Representation Learning with Nonstationary Sparse Transitioncited by 13
  8. 2022Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videoscited by 12
  9. 2021Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videoscited by 11
  10. 2023Activity Grammars for Temporal Action Segmentationcited by 8
  11. 2022Robust Action Segmentation from Timestamp Supervisioncited by 6
  12. 2022Transformers in Action: Weakly Supervised Action Segmentationcited by 4
4 more
  1. 2024ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipationcited by 4
  2. 2025Improving action segmentation via explicit similarity measurementcited by 1
  3. 2022Distill and Collect for Semi-Supervised Temporal Action Segmentationcited by 0
  4. 2026Learning Action Hierarchies via Hybrid Geometric Diffusioncited by 0