Research
My research interest lies at the intersection of deep learning applied to computer vision applications with a specific focus on understanding humans in motion within video sequences. More specifically, my research encompasses fine-grained human understanding such as human pose, body surface and trajectory prediction as well as coarse-grained human understanding such as comprehending human actions, interactions with other individuals (social groups) and social activities.
|
JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection
Mahsa Ehsanpour, Fatemeh Saleh, Silvio Savarese, Ian Reid, Hamid Rezatofighi
CVPR, 2022
[project page
/video /
code /
bibtex]
|
TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
Vida Adeli, Mahsa Ehsanpour, Ian Reid, Juan Carlos Niebles, Silvio Savarese, Ehsan Adeli, Hamid Rezatofighi
ICCV, 2021
[project page
/video /
code /
bibtex]
|
Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Hamid Rezatofighi
ArXiv, 2021
[project page
/video /
code /
bibtex]
|
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos
Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh, Javen Shi, Ian Reid, Hamid Rezatofighi
ECCV, 2020
[ project page
/ video /
code /
bibtex]
|
PhD, Computer Science, The University of Adelaide, [October 2018 - Present]
|
MSc, Information Technology, Sharif University of Technology, [September 2015 - September 2017]
|
BSc, Computer Software Engineering, Khajeh Nasir Toosi University of Technology, [September 2010 - February 2015]
|
|