Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset

by   Akash Nagaraj, et al.

In this paper we present a three-stream algorithm for real-time action recognition and a new dataset of handwash videos, with the intent of aligning action recognition with real-world constraints to yield effective conclusions. A three-stream fusion algorithm is proposed, which runs both accurately and efficiently, in real-time even on low-powered systems such as a Raspberry Pi. The cornerstone of the proposed algorithm is the incorporation of both spatial and temporal information, as well as the information of the objects in a video while using an efficient architecture, and Optical Flow computation to achieve commendable results in real-time. The results achieved by this algorithm are benchmarked on the UCF-101 as well as the HMDB-51 datasets, achieving an accuracy of 92.7 the algorithm is novel in the aspect that it is also able to learn the intricate differences between extremely similar actions, which would be difficult even for the human eye. Additionally, noticing a dearth in the number of datasets for the recognition of very similar or fine-grained actions, this paper also introduces a new dataset that is made publicly available, the Hand Wash Dataset with the intent of introducing a new benchmark for fine-grained action recognition tasks in the future.


page 4

page 7


ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction

Prediction of the action outcome is a new challenge for a robot collabor...

Hand Guided High Resolution Feature Enhancement for Fine-Grained Atomic Action Segmentation within Complex Human Assemblies

Due to the rapid temporal and fine-grained nature of complex human assem...

Low-light Environment Neural Surveillance

We design and implement an end-to-end system for real-time crime detecti...

Cross-domain Variational Capsules for Information Extraction

In this paper, we present a characteristic extraction algorithm and the ...

Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection

Fine-grained action detection is an important task with numerous applica...

A real-time algorithm for human action recognition in RGB and thermal video

Monitoring the movement and actions of humans in video in real-time is a...

Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data

Action recognition is so far mainly focusing on the problem of classific...

Please sign up or login with your details

Forgot password? Click here to reset