Research interest

My current research focus is on Human Centered Signal Processing, which seeks an understanding of human emotion, perception and behavior by leveraging the rich theory of signal/image processing, pattern recognition and machine learning.


I am an Assistant Professor in the department of Electrical Engineering at IIT Kanpur, India, where I lead the Signal and Multimedia Processing Lab (SiMPL). I am also a part of the Computer Vision Group at IITK. Prior to joining IITK, I was a Postdoctoral Fellow at the Signal Analysis and Interpretation Lab (SAIL), University of Southern California (USC) from 2013 - 2015. I have received my PhD degree in Electrical and Computer Engineering from the University of British Columbia (UBC), Vancouver, Canada in 2013.


I thankfully acknowledge these grants, awards and scholarships I have received to support my research, education, and to travel to conferences.


I am often involved in various professional activities. I am a member of IEEE and ACM.

Tanaya Guha

Assistant Professor

Electrical Engineering

Indian Institute of Technology Kanpur

tanaya[at] | 512 259 6823 | office: ACES 305D

CV | Google Scholar 


  1. [Dec 2016] Our paper titled “On the role of head motion in affective expression” accepted in ICASSP 2017, New Orleans.

  1. [Oct 2016] Code released for our paper “A trajectory clustering approach to crowd flow segmentation in videos”, ICIP 2016, Phoenix.

  1. [Sep 2016] Our research on gender in media at USC is featured in New York Times and Washington Post. Also read an excerpt of our research, my blog post and the related paper on this topic.

  1. [Aug 2016] NVIDIA Corporation has donated a TitanX to support my research. Thanks to NVIDIA’s academic GPU grant program.

  1. [Jul 2016] Invited talk at TCS Innovation Lab Kolkata.

  1. [Jul 2016] Paper on Novel affective features for multiscale prediction of emotion in music accepted in MMSP 2016.

  1. [Jun 2016] Invited talk at IISc Bangalore.

  1. [Jun 2016] Paper on A computational_study of expressive facial dynamics in children with autism accepted in IEEE Transaction on Affective Computing (TAFFC).

  1. [May 2016] Paper on A trajectory clustering approach to crowd flow segmentation in videos is accepted for publication in ICIP 2016.

  1. [Dec 2015] Two papers accepted in ICASSP 2016 to be held in Shanghai, China.

  1. [Aug 2015] Paper on Gender representation in cinematic content: A multimodal approach is accepted in ICMI 2015, Seattle. See a quick demo here.