Search Results for author: Debaditya Roy

Found 7 papers, 1 papers with code

ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition

1 code implementation2 Jul 2023 Debaditya Roy, Dhruv Verma, Basura Fernando

Situation Recognition is the task of generating a structured summary of what is happening in an image using an activity verb and the semantic roles played by actors and objects.

Grounded Situation Recognition

Interaction Region Visual Transformer for Egocentric Action Anticipation

no code implementations25 Nov 2022 Debaditya Roy, Ramanathan Rajendiran, Basura Fernando

On the EK100 evaluation server, InAViT is the top-performing method on the public leaderboard (at the time of submission) where it outperforms the second-best model by 3. 3% on mean-top5 recall.

Action Anticipation Human-Object Interaction Detection +1

Predicting the Next Action by Modeling the Abstract Goal

no code implementations12 Sep 2022 Debaditya Roy, Basura Fernando

It is through the submission of this paper that our method is currently the new state-of-the-art for action anticipation in EK55 and EGTEA Gaze+ https://competitions. codalab. org/competitions/20071#results Code available at https://github. com/debadityaroy/Abstract_Goal

Action Anticipation

FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

no code implementations8 Nov 2020 Vinoj Jayasundara, Debaditya Roy, Basura Fernando

Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks, especially pertaining to scene understanding.

Action Recognition Optical Flow Estimation +1

Defining Traffic States using Spatio-temporal Traffic Graphs

no code implementations27 Jul 2020 Debaditya Roy, K. Naveen Kumar, C. Krishna Mohan

Intersections are one of the main sources of congestion and hence, it is important to understand traffic behavior at intersections.

Cannot find the paper you are looking for? You can Submit a new open access paper.