no code implementations • 13 Jan 2020 • Georgin Jacob, Harish Katti
The Algonauts challenge is about predicting the object representations in the form of Representational Dissimilarity Matrices (RDMS) derived from visual brain regions.
no code implementations • 3 Apr 2019 • Abhinav Shukla, Shruti Shriya Gullapuram, Harish Katti, Mohan Kankanhalli, Stefan Winkler, Ramanathan Subramanian
Advertisements (ads) often contain strong affective content to capture viewer attention and convey an effective message to the audience.
no code implementations • 14 Aug 2018 • Abhinav Shukla, Harish Katti, Mohan Kankanhalli, Ramanathan Subramanian
Contrary to the popular notion that ad affect hinges on the narrative and the clever use of linguistic and social cues, we find that actively attended objects and the coarse scene structure better encode affective information as compared to individual scene objects or conspicuous background elements.
no code implementations • 23 Jul 2018 • R. T. Pramod, Harish Katti, S. P. Arun
Our vision is sharpest at the center of our gaze and becomes progressively blurry into the periphery.
no code implementations • 22 Mar 2017 • Harish Katti, S. P. Arun
We have developed a novel face database of close to 1650 diverse Indian faces labeled for fine-grained race (South vs North India) as well as for age, weight, height and gender.
1 code implementation • 22 Nov 2016 • Harish Katti, Marius V. Peelen, S. P. Arun
To measure contextual expectations, we asked human subjects to indicate the scale, location and likelihood at which cars or people might occur in scenes without these objects.