DeepAI AI Chat
Log In Sign Up

Towards Improving Spatiotemporal Action Recognition in Videos

12/15/2020
by   Shentong Mo, et al.
0

Spatiotemporal action recognition deals with locating and classifying actions in videos. Motivated by the latest state-of-the-art real-time object detector You Only Watch Once (YOWO), we aim to modify its structure to increase action detection precision and reduce computational time. Specifically, we propose four novel approaches in attempts to improve YOWO and address the imbalanced class issue in videos by modifying the loss function. We consider two moderate-sized datasets to apply our modification of YOWO - the popular Joint-annotated Human Motion Data Base (J-HMDB-21) and a private dataset of restaurant video footage provided by a Carnegie Mellon University-based startup, Agot.AI. The latter involves fast-moving actions with small objects as well as unbalanced data classes, making the task of action localization more challenging. We implement our proposed methods in the GitHub repository https://github.com/stoneMo/YOWOv2.

READ FULL TEXT

page 5

page 12

08/25/2020

Spatiotemporal Action Recognition in Restaurant Videos

Spatiotemporal action recognition is the task of locating and classifyin...
02/15/2021

Win-Fail Action Recognition

Current video/action understanding systems have demonstrated impressive ...
08/27/2022

Actor-identified Spatiotemporal Action Detection – Detecting Who Is Doing What in Videos

The success of deep learning on video Action Recognition (AR) has motiva...
06/23/2021

Vision-based Behavioral Recognition of Novelty Preference in Pigs

Behavioral scoring of research data is crucial for extracting domain-spe...
07/12/2022

Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling

Adaptive sampling that exploits the spatiotemporal redundancy in videos ...
11/10/2018

Near Real-Time Data Labeling Using a Depth Sensor for EMG Based Prosthetic Arms

Recognizing sEMG (Surface Electromyography) signals belonging to a parti...
08/15/2023

Action Class Relation Detection and Classification Across Multiple Video Datasets

The Meta Video Dataset (MetaVD) provides annotated relations between act...