Home

j.png

 

PhD candidate

Human-Centred Computing Lab
Building 11, Faculty of Information Sciences & Engineering
University of Canberra, University Drive, Bruce, ACT 2617 Australia

Office : 11B31

Email : Jyoti[dot]Dhall[at]canberra[dot]edu[dot]au

 

 

UPDATE : Joined the University of Waterloo as Postdoc!

Hello! I am a PhD student at Human-Centred Computing lab at University of Canberra (UC), Australia. I am supervised by Prof. Roland Goecke and Prof. Michael Wagner. Before starting my PhD, I worked as a research assistant with Vision and Sensing Group, University of Canberra. I also worked as a consultant at a leading EDA company Cadence Design Systems, India prior to coming to Australia. My current research revolves around application of pattern recognition, computer vision and machine learning techniques with a focus on affect based multimedia analysis.

 

NEWS

 

MEDIA COVERAGE

  • An article in the magazine NewScientist covering ‘Automatic Depression Analysis’ research from various groups around the world (feat. my work). [NewScientist] [28 Mar, 2013]
  • Some media attention to our Depression project (feat. Dr. Roland Goecke). [SMH] [27 Feb, 2013]
  • Girl Geek Coffees (GGC) at University of Canberra story. [GGC@UC] [13 July, 2012]

 

PROJECTS

  • Multimodal Approach for Depression Analysis – The objective is to devise a novel multimodal framework for depression detection by integrating information from single-modal channels. The project explore facial dynamics analysis, head movements, upper body gestures, EEG measures and speech characteristics related to affect, in patients with major depressive disorders.
  • Group Expression Analysis – This project explores the scene emotion based on modelling the social features of a scene. Further group expression method is used to solve the problem of candid shot selection and event summarization based on emotion.
  • Pose Estimation & Self Occlusion Detection in Human Body – The objective of this project is to detect self occluded parts in human body and rectify the pictorial structure and hence improve pose estimation.
  • Sports Player Tracking – This project investigate applicability of Active Appearance Models (AAM) for tracking player’s body in video sequences captured using low resolution camera.

 

PUBLICATIONS

Google Scholar Profile

  • The More the Merrier: Analysing the Affect of a Group of People In Images [PDF]
    Abhinav Dhall, Jyoti Joshi, Karan Sikka, Roland Goecke and Nicu Sebe, IEEE International Confernce on Automated Faces & Gesture Recognition (FG) 2015. (Oral)

 

  • Emotion Recognition In The Wild Challenge 2014: Baseline, Data and Protocol [PDF]
    Abhinav Dhall, Roland Goecke, Jyoti Joshi, Karan Sikka and Tom Gedeon, ACM International Conference on Multimodal Interaction (ICMI) 2014.

 

  • Automatic Prediction of Perceived Traits using Visual Cues under Varied Situational Context [PDF]
    Jyoti Joshi, Hatice Gunes, Roland Goecke, International Conference on Pattern Recognition (ICPR), 2014. (Oral)

 

  • Emotion Recognition In The Wild Challenge 2013 [PDF]
    Abhinav Dhall, Roland Goecke, Jyoti Joshi, Michael Wagner, Tom Gedeon, International Conference on Multimodal Interaction (ICMI), 2013.

 

  • Diagnosis of Depression by Behavioural Signals: A Multimodal Approach [PDF]
    Nick Cummins, Jyoti Joshi, Abhinav Dhall, Vidhyasaharan Sethu, Roland Goecke and Julien Epps, Audio Video Emotion Recognition Challenge (AVEC), ACM Multimedia 2013.

 

  • Relative Body Parts Movement for Automatic Depression Analysis [PDF]
    Jyoti Joshi, Abhinav Dhall, Roland Goecke, Jeff Cohn, Proc. of International Conference on Affective Computing and Intelligent Interaction (ACII) 2013. (Oral)

 

  • An Automated Framework for Depression Analysis [PDF]
    Jyoti Joshi
    , Doctoral Consortium, Proc. of International Conference on Affective Computing and Intelligent Interaction(ACII) 2013.

 

  • Multimodal Assistive Technologies for Depression Diagnosis and Monitoring [PDF]
    Jyoti Joshi, Roland Goecke, Abhinav Dhall, Sharifa Alghowinem, Michael Wagner, Michael Breakspear, Julien Epps, Gordon Parker, Journal on MultiModal User Interfaces, Springer (Accepted).

 

  • Can body expressions contribute to automatic depression analysis? [PDF]
    Jyoti Joshi, Roland Goecke, Michael Breakspear and Gordon Parker, IEEE International Confernce on Automated Faces & Gesture Recognition (FG) 2013. (Oral)

 

  • Finding Happiest Moments in a Social Context [PDF]
    Abhinav Dhall, Jyoti Joshi, Ibrahim Radwan and Roland Goecke, Proc. of Asian Conference on Computer Vision (ACCV), 2012.

 

  • Neural-Net Classification For Spatio-Temporal Descriptor Based Depression Analysis [PDF]
    Jyoti Joshi, Abhinav Dhall, Roland Goecke, Michael Breakspear and Gordon Parker, IAPR International Conference on Pattern Recognition (ICPR), 2012 (Oral).

 

  • Regression Based Pose Estimation with Automatic Occlusion Detection and Rectification [PDF]
    Ibrahim Radwan, Abhinav Dhall, Jyoti Joshi and Roland Goecke, IEEE International Conference on Multimedia & Expo.(ICME), 2012 [Nominated for the best paper award] (Oral)

 

  • Depression Analysis : A Multimodal Approach [PDF]
    Jyoti Joshi, Doctoral Consortium at ACM International Conference on Multimodal Interaction (ICMI), 2012.