Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mahsa Ehsanpour

JRDB-Act: A Large-scale Multi-modal Dataset for Spatio-temporal Action, Social Group and Activity Detection


Jun 16, 2021
Mahsa Ehsanpour, Fatemeh Saleh, Silvio Savarese, Ian Reid, Hamid Rezatofighi


  Access Paper or Ask Questions

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild


Apr 08, 2021
Vida Adeli, Mahsa Ehsanpour, Ian Reid, Juan Carlos Niebles, Silvio Savarese, Ehsan Adeli, Hamid Rezatofighi


  Access Paper or Ask Questions

Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers


Mar 27, 2021
Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Hamid Rezatofighi


  Access Paper or Ask Questions

Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors


Jul 14, 2020
Alireza Abedin, Mahsa Ehsanpour, Qinfeng Shi, Hamid Rezatofighi, Damith C. Ranasinghe

* 15 pages, 7 figures 

  Access Paper or Ask Questions

Joint learning of Social Groups, Individuals Action and Sub-group Activities in Videos


Jul 06, 2020
Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh, Javen Shi, Ian Reid, Hamid Rezatofighi

* Accepted in the European Conference On Computer Vision (ECCV) 2020 

  Access Paper or Ask Questions