SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.12409 · 2019

PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an encoder-decoder recurrent neural network, where the encoder learns a separable feature representation within its hidden states formed by training the model to perform prediction task. We show that according to such unsupervised training the decoder and the encoder self-organize their hidden states into a feature space which clusters similar movements into the same cluster and distinct movements into distant clusters. Current state-of-the-art methods for action recognition are strongly supervised, i.e., rely on providing labels for training. Unsupervised methods have been proposed, however, they require camera and depth inputs (RGB+D) at each time step. In contrast, our system is fully unsupervised, does not require labels of actions at any stage, and can operate with body keypoints input only. Furthermore, the method can perform on various dimensions of body keypoints (2D or 3D) and include additional cues describing movements. We evaluate our system on three extensive action recognition benchmarks with different number of actions and examples. Our results outperform prior unsupervised skeleton-based methods, unsupervised RGB+D based methods on cross-view tests and while being unsupervised have similar performance to supervised skeleton-based action recognition.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1911.12409")
get_code_for_paper("1911.12409")
have("1911.12409")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1911.12409.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1911.12409.svg)](https://syntology.ai/paper/1911.12409)

Connect an agent — have() is free.