# CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps

arXiv: https://arxiv.org/abs/1806.09078 · HTML: https://mlsanity.com/paper/1806.09078/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2018.

## Built on by (most cited first, 13 of 13)

- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Meta-Learning for Multi-Label Few-Shot Classification](https://mlsanity.com/paper/2110.13494/) (2021)
- [Uncertainty-DTW for Time Series and Sequences](https://mlsanity.com/paper/2211.00005/) (2022)
- [Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring](https://mlsanity.com/paper/2302.07689/) (2023)
- [3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ive](https://mlsanity.com/paper/2112.12668/) (2021)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [From Big to Small: Adaptive Learning to Partial-Set Domains](https://mlsanity.com/paper/2203.07375/) (2022)
- [Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition](https://mlsanity.com/paper/2207.08095/) (2022)
- [Simple Dialogue System with AUDITED](https://mlsanity.com/paper/2110.11881/) (2021)
- [Multivariate Prototype Representation for Domain-Generalized Incremental Learning](https://mlsanity.com/paper/2309.13563/) (2023)
- [From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks](https://mlsanity.com/paper/2211.17045/) (2022)
- [TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition](https://mlsanity.com/paper/2512.11503/) (2025)
- [SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition](https://mlsanity.com/paper/2606.03610/) (2026)

## Abstract (arXiv)

Deep learning is ubiquitous across many areas areas of computer vision. It often requires large scale datasets for training before being fine-tuned on small-to-medium scale problems. Activity, or, in other words, action recognition, is one of many application areas of deep learning. While there exist many Convolutional Neural Network architectures that work with the RGB and optical flow frames, training on the time sequences of 3D body skeleton joints is often performed via recurrent networks such as LSTM. In this paper, we propose a new representation which encodes sequences of 3D body skeleton joints in texture-like representations derived from mathematically rigorous kernel methods. Such a representation becomes the first layer in a standard CNN network e.g., ResNet-50, which is then used in the supervised domain adaptation pipeline to transfer information from the source to target dataset. This lets us leverage the available Kinect-based data beyond training on a single dataset and outperform simple fine-tuning on any two datasets combined in a naive manner. More specifically, in this paper we utilize the overlapping classes between datasets. We associate datapoints of the same class via so-called commonality, known from the supervised domain adaptation. We demonstrate state-of-the-art results on three publicly available benchmarks.