computer-vision-5

One-Shot 3D Action Recognition

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in one-shot-3d-action-recognition-5

Trend

Dataset

Best Model

Actions

NTU RGB+D 120

Libraries

i

Use these libraries to find one-shot-3d-action-recognition-5 models and implementations

Datasets

NTU RGB+D

NTU RGB+D 120

Subtasks

No subtasks available.

Most implemented papers

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

G. Wang, Amir Shahroudy, Jun Liu, Mauricio Perez, Ling-yu Duan, A. Kot•Sat May 11 2019

This work introduces a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames, and investigates a novel one-shot 3D activity recognition problem on this dataset.

1555

Content

0

Paper Graph

Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition

Raphael Memmesheimer, D. Paulus, Nick Theisen, Simon Häring•Fri Dec 25 2020

This work forms the one-shot action recognition problem as a deep metric learning problem and proposes a novel image-based skeleton representation that performs well in a metric learning setting and trains a model that projects the image representations into an embedding space.

43 0

Paper Graph

SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition

Raphael Memmesheimer, D. Paulus, Nick Theisen•Wed Apr 22 2020

This work proposes a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space, which generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data.

46 0

Paper Graph

MotionBERT: A Unified Perspective on Learning Human Motion Representations

Wenjie Zhu, Wayne Wu, Xiaoxuan Ma, Zhaoyang Liu, Libin Liu•Tue Oct 11 2022

A pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations is proposed, which achieves state-of-the-art performance on all three downstream tasks by simply finetuning the pretrained motion encoding with a simple regression head, which demonstrates the versatility of the learned motion representations.

271 0

Paper Graph

One-shot action recognition in challenging therapy scenarios

A. C. Murillo, J. Santos-Victor, Alberto Sabater, Laura Santos, Alexandre Bernardino, L. Montesano•Tue Feb 16 2021

This work presents a novel approach for one-shot action recognition in the wild that computes motion representations robust to variable kinematic conditions and develops a set of complementary steps that boost the action recognition performance in the most challenging scenarios.

40 0

Paper Graph

Adding a benchmark result helps the community track progress.