# Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion

arXiv: https://arxiv.org/abs/2305.19480 · HTML: https://mlsanity.com/paper/2305.19480/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 85 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 30 of 61)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Spatiotemporal Contrastive Video Representation Learning](https://mlsanity.com/paper/2008.03800/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [Learning Representations for Automatic Colorization](https://mlsanity.com/paper/1603.06668/) (2016)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [Colorization as a Proxy Task for Visual Understanding](https://mlsanity.com/paper/1703.04044/) (2017)
- [SpeedNet: Learning the Speediness in Videos](https://mlsanity.com/paper/2004.06130/) (2020)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)

## Built on by (most cited first, 3 of 3)

- [Joint Self-Supervised Video Alignment and Action Segmentation](https://mlsanity.com/paper/2503.16832/) (2025)
- [Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport](https://mlsanity.com/paper/2507.15540/) (2025)
- [Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization](https://mlsanity.com/paper/2604.15196/) (2026)

## Abstract (arXiv)

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment. Our code and dataset are available on our research website: https://retrocausal.ai/research/.