no code implementations • 9 Apr 2024 • Rohan Sarkar, Avinash Kak
We believe that this dataset will facilitate research in fine-grained object recognition and retrieval of objects that are capable of state changes.
no code implementations • 1 Mar 2024 • Rohan Sarkar, Avinash Kak
This paper presents an attention-based dual-encoder architecture with specially designed loss functions that optimize the inter- and intra-class distances simultaneously in two different embedding spaces, one for the category embeddings and the other for the object-level embeddings.
no code implementations • 14 Apr 2023 • Rohan Sarkar, Achal Dave, Gerard Medioni, Benjamin Biggs
This paper presents Shape of You (SoY), an approach to improve the accuracy of 3D body shape estimation for vision-based clothing recommendation systems.
Ranked #4 on 3D Human Shape Estimation on SSP-3D
no code implementations • 25 Aug 2022 • Rohan Sarkar, Sreelekshmi R, Abhijit Nayek, Anirban Bhowmick, Poushali Chakraborty, Rituparna Sonowal, Debsruti Dasgupta, Rounak Banerjee, Aritra Roy, Amartya Baran Mandal, Anindita Bhadra
The current experiment was carried out on groups of dogs with the same set up to see the change in foraging strategies, if any, under the influence of social cost like intra-group competition.
1 code implementation • 11 Apr 2022 • Rohan Sarkar, Navaneeth Bodla, Mariya I. Vasileva, Yen-Liang Lin, Anurag Beniwal, Alan Lu, Gerard Medioni
For compatibility prediction, we design an outfit token to capture a global outfit representation and train the framework using a classification loss.
no code implementations • 21 Feb 2021 • Rohan Sarkar, Avinash C. Kak
We present CheckSoft, a scalable event-driven software architecture for keeping track of people-object interactions in people-centric applications such as airport checkpoint security areas, automated retail stores, smart libraries, and so on.