Fatemeh Saleh

Room 3.02, Brian Anderson Building (115), The Australian National University, Canberra ACT 2600 Australia fatemehsadat.saleh@anu.edu.au

I am a Research Fellow of the Australian Centre for Robotic Vision (ACRV) and the Australian National University (ANU), where I am honoured to work with Professor Stephen Gould. Prior to that, I was a PhD student at Australian National University and Data61-CSIRO, working on weakly-supervised semantic segmentation of images and videos under supervisions of Lars Petersson, Mathieu Salzmann, Jose M. Alvarez, and Stephen Gould. I was also a deep learning research engineering intern at Qualcomm AI Research, Amsterdam, working on self-supervised video representation learning.

My research interests are in the fields of computer vision and machine learning, with a focus on video representation learning and sequence modeling. More recently, I'm working on finding efficient and effective solutions for problems that are grounded in applications such as multiple object tracking, human motion prediction, diverse sequence generation, and action recognition.


(Recent) Experience

Research Fellow

Australian Centre for Robotic Vision, Australian National University
Jan 2019 - Current

Research Intern

Qualcomm AI Research
May 2018 - Sep 2018

Research Assitant

Data61-CSIRO and NICTA
Jul 2015 - Dec 2018

Lecturer

Payam Nour University (PNU)
Sep 2014 - Feb 2015

Education

Australian National University

PhD | Computer Science
2015 - 2018

Sharif University of Technology

MSc | Artificial Intelligence
2011 - 2013

Isfahan University of Technology

BSc | Software Engineering
2007 - 2011

(Recent) Publications

  • Cristian Rodriguez Opazo, Edison Marrese-Taylor, Fatemeh Saleh, Hongdong Li, Stephen Gould, "Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention", Winter Conference on Applications of Computer Vision (WACV), Colorado, USA, 2020 [PDF]

  • Fatemeh Saleh, Sadegh Aliakbarian, Matheiu Salzmann, Lars Petersson, Jose Alvarez, "Effective Use of Synthetic Data for Urban Scene Semantic Segmentation", European Conference on Computer Vision (ECCV), Munich, Germany, 2018 [PDF]

  • Sadegh Aliakbarian, Fatemeh Saleh, Matheiu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson, "VIENA2: A Driving Anticipation Dataset", Asian Conference on Computer Vision (ACCV), Perth, Australia, 2018 [PDF]

  • Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M Alvarez, Stephen Gould, "Incorporating network built-in priors in weakly-supervised semantic segmentation", IEEE transactions on pattern analysis and machine intelligence (TPAMI), 2018 [PDF]

  • Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M Alvarez, "Bringing background into the foreground: Making all classes equal in weakly-supervised video semantic segmentation", International Conference on Computer Vision (ICCV), Venice, Italy, 2018 [PDF]

  • Sadegh Aliakbarian, Fatemeh Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, "Encouraging LSTMs to Anticipate Actions Very Early", International Conference on Computer Vision (ICCV), Venice, Italy 2017 [PDF]

  • Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Stephen Gould, Jose M Alvarez, "Built-in foreground/background prior for weakly-supervised semantic segmentation", European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, 2016 [PDF]


News and Highlights

  • One paper accepted in WACV'20. Congradulations to Cristian Rodriguez.
  • The VIENA2 (Virtual Environment for Action Anticipation) dataset is now publicly available.
  • I joined ANU/ACRV as a Research Fellow under supervision of Stephen Gould [January 2019]
  • After wonderful 3.5 years, I just finished my PhD at ANU!
  • The VEIS Dataset (Virtual Environment for Instance Segmentation) is now publicly available!
  • I joined Qualcomm AI Research, Amsterdam, Netherlands, as an Deep Learning Research Engineering Intern [May 2018]
  • One paper accepted at ECCV 2018, one paper accepted at ACCV 2018, and one paper accepted at TPAMI 2018
  • Two papers accepted at ICCV 2017, one paper accepted at ECCV 2016