# ASFormer: Transformer for Action Segmentation

arXiv: https://arxiv.org/abs/2110.08568 · HTML: https://mlsanity.com/paper/2110.08568/

## Key facts

- Cited by 168 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 16 Oct 2021.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [Single Shot Temporal Action Detection](https://mlsanity.com/paper/1710.06236/) (2017)
- [Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos](https://mlsanity.com/paper/1507.05738/) (2015)
- [Timeception for Complex Action Recognition](https://mlsanity.com/paper/1812.01289/) (2018)
- [Alleviating Over-segmentation Errors by Detecting Action Boundaries](https://mlsanity.com/paper/2007.06866/) (2020)
- [Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation](https://mlsanity.com/paper/1602.02995/) (2016)
- [Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment](https://mlsanity.com/paper/1803.10699/) (2018)

## Built on by (most cited first, 30 of 168)

- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding](https://mlsanity.com/paper/2403.09626/) (2024)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2407.04689/) (2024)
- [SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge](https://mlsanity.com/paper/2401.00496/) (2023)
- [Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation](https://mlsanity.com/paper/2209.00638/) (2022)
- [Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos](https://mlsanity.com/paper/2203.14104/) (2022)
- [STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition](https://mlsanity.com/paper/2210.07503/) (2022)
- [Spotting Temporally Precise, Fine-Grained Events in Video](https://mlsanity.com/paper/2207.10213/) (2022)
- [MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection](https://mlsanity.com/paper/2403.19888/) (2024)
- [Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2404.01518/) (2024)
- [How Much Temporal Long-Term Context is Needed for Action Segmentation?](https://mlsanity.com/paper/2308.11358/) (2023)
- [Action Quality Assessment with Temporal Parsing Transformer](https://mlsanity.com/paper/2207.09270/) (2022)
- [LOGO: A Long-Form Video Dataset for Group Action Quality Assessment](https://mlsanity.com/paper/2404.05029/) (2024)
- [Learning to Ground Instructional Articles in Videos through Narrations](https://mlsanity.com/paper/2306.03802/) (2023)
- [Vision Transformers for Action Recognition: A Survey](https://mlsanity.com/paper/2209.05700/) (2022)
- [Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression](https://mlsanity.com/paper/2501.03674/) (2025)
- [Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning](https://mlsanity.com/paper/2503.00986/) (2025)
- [On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis](https://mlsanity.com/paper/2203.07976/) (2022)
- [Hierarchical Vector Quantization for Unsupervised Action Segmentation](https://mlsanity.com/paper/2412.17640/) (2024)
- [Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment](https://mlsanity.com/paper/2305.19478/) (2023)
- [SVIP: Sequence VerIfication for Procedures in Videos](https://mlsanity.com/paper/2112.06447/) (2021)
- [Cross-Enhancement Transformer for Action Segmentation](https://mlsanity.com/paper/2205.09445/) (2022)
- [Metrics Matter in Surgical Phase Recognition](https://mlsanity.com/paper/2305.13961/) (2023)
- [Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment](https://mlsanity.com/paper/2403.19225/) (2024)
- [Context-Enhanced Memory-Refined Transformer for Online Action Detection](https://mlsanity.com/paper/2503.18359/) (2025)
- [FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation](https://mlsanity.com/paper/2402.00293/) (2024)

## Abstract (arXiv)

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action segments to refine the initial predictions. To address these concerns, we design an efficient Transformer-based model for action segmentation task, named ASFormer, with three distinctive characteristics: (i) We explicitly bring in the local connectivity inductive priors because of the high locality of features. It constrains the hypothesis space within a reliable scope, and is beneficial for the action segmentation task to learn a proper target function with small training sets. (ii) We apply a pre-defined hierarchical representation pattern that efficiently handles long input sequences. (iii) We carefully design the decoder to refine the initial predictions from the encoder. Extensive experiments on three public datasets demonstrate that effectiveness of our methods. Code is available at urlhttps://github.com/ChinaYi/ASFormer.