MPSC_MV

Citation Author(s):
Masud
Ahmed
University Of Maryland Baltimore County
Zahid
Hasan
University Of Maryland Baltimore County
Submitted by:
Masud Ahmed
Last updated:
Wed, 01/25/2023 - 12:17
DOI:
10.21227/khwg-kj52
License:
171 Views
Categories:
0
0 ratings - Please login to submit your rating.

Abstract 

Deep video representation learning has recently attained state-of-the-art performance in video action recognition. However, when used with video clips from varied perspectives, the performance of these models degrades significantly. Existing VAR models frequently simultaneously contain both view information and action attributes, making it difficult to learn a view-invariant representation. Therefore, to study the attribute of multiview representation, we collected a large-scale time synchronous multiview video dataset from 10 subjects in both indoor and outdoor settings performing 10 different actions with three horizontal and vertical viewpoints using a smartphone, an action camera, and a drone camera. We provide the multiview video dataset with various meta-data information to facilitate further research for robust VAR systems.

Instructions: 

This is a partial Dataset, we will upload the full dataset soon including data loader

Funding Agency: 
DEVCOM Army Research Laboratory (ARL) and U.S. Army
Grant Number: 
Grant No. W911NF21-20076