no code implementations • 28 Feb 2023 • Aakansha Mishra, Ashish Anand, Prithwijit Guha
The use of complex attention modules has improved the performance of the Visual Question Answering (VQA) task.
no code implementations • 2 Nov 2020 • Prateek Manocha, Prithwijit Guha
To the best of our knowledge, this is the first work that proposes an audio-keypoint dataset and learns a model to output the plausible keypoint sequence to go with audio of any arbitrary length.
1 code implementation • 8 Jul 2020 • Vatsal Goel, Mohit Chandak, Ashish Anand, Prithwijit Guha
As a part of the cyclic framework, we propose a novel implication generator which can generate implied questions from any question-answer pair.
no code implementations • 17 Feb 2020 • Aakansha Mishra, Ashish Anand, Prithwijit Guha
The second level, referred to as answer predictor (AP), comprises of a set of distinct classifiers corresponding to each question category.
1 code implementation • 9 Jan 2017 • Tanmay Shankar, Santosha K. Dwivedy, Prithwijit Guha
Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks.
no code implementations • 2 Apr 2016 • Raghvendra Kannao, Prithwijit Guha
In this paper, we present a contrast enhancement based preprocessing stage for overlay text detection and a parameter free edge density based scheme for efficient text band detection.
no code implementations • 5 Jul 2015 • Raghvendra Kannao, Prithwijit Guha
We adopt a intermediate fusion approach where, a SVM is trained with a weighted linear combination of different kernel functions instead of single kernel function.
no code implementations • 25 Jan 2015 • Sourav Garg, Swagat Kumar, Rajesh Ratnakaram, Prithwijit Guha
This paper looks into the problem of pedestrian tracking using a monocular, potentially moving, uncalibrated camera.