# Transformers in Action: Weakly Supervised Action Segmentation

arXiv: https://arxiv.org/abs/2201.05675 · HTML: https://mlsanity.com/paper/2201.05675/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## 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)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation](https://mlsanity.com/paper/1901.02598/) (2019)
- [Unsupervised learning of action classes with continuous temporal embedding](https://mlsanity.com/paper/1904.04189/) (2019)
- [Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment](https://mlsanity.com/paper/1803.10699/) (2018)
- [Connectionist Temporal Modeling for Weakly Supervised Action Labeling](https://mlsanity.com/paper/1607.08584/) (2016)
- [Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling](https://mlsanity.com/paper/1703.08132/) (2017)
- [SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition](https://mlsanity.com/paper/2106.03849/) (2021)
- [NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning](https://mlsanity.com/paper/1805.06875/) (2018)
- [Unsupervised Learning and Segmentation of Complex Activities from Video](https://mlsanity.com/paper/1803.09490/) (2018)
- [Weakly Supervised Energy-Based Learning for Action Segmentation](https://mlsanity.com/paper/1909.13155/) (2019)
- [Weakly Supervised Action Labeling in Videos Under Ordering Constraints](https://mlsanity.com/paper/1407.1208/) (2014)

## Built on by (most cited first, 4 of 4)

- [Vision Transformers for Action Recognition: A Survey](https://mlsanity.com/paper/2209.05700/) (2022)
- [Causal Temporal Representation Learning with Nonstationary Sparse Transition](https://mlsanity.com/paper/2409.03142/) (2024)
- [Timestamp-supervised Wearable-based Activity Segmentation and Recognition with Contrastive Learning and Order-Preserving Optimal Transport](https://mlsanity.com/paper/2310.09114/) (2023)
- [Temporal Segment Transformer for Action Segmentation](https://mlsanity.com/paper/2302.13074/) (2023)

## Abstract (arXiv)

The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents various challenges for sequence modeling approaches due to the emphasis on action transition points, long sequence lengths, and frame contextualization, making the task well-posed for transformers. Given developments enabling transformers to scale linearly, we demonstrate through our architecture how they can be applied to improve action alignment accuracy over the equivalent RNN-based models with the attention mechanism focusing around salient action transition regions. Additionally, given the recent focus on inference-time transcript selection, we propose a supplemental transcript embedding approach to select transcripts more quickly at inference-time. Furthermore, we subsequently demonstrate how this approach can also improve the overall segmentation performance. Finally, we evaluate our proposed methods across the benchmark datasets to better understand the applicability of transformers and the importance of transcript selection on this video-driven weakly-supervised task.