Search Results for author: Parth Shah

Found 8 papers, 7 papers with code

Image Captioning using Deep Neural Architectures

1 code implementation17 Jan 2018 Parth Shah, Vishvajit Bakarola, Supriya Pati

We have also discussed about how the advancement in the task of object recognition and machine translation has greatly improved the performance of image captioning model in recent years.

Image Captioning Machine Translation +3

Motion-based Object Segmentation based on Dense RGB-D Scene Flow

1 code implementation14 Apr 2018 Lin Shao, Parth Shah, Vikranth Dwaracherla, Jeannette Bohg

Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow.

Motion Segmentation Object +3

Optimal Approach for Image Recognition using Deep Convolutional Architecture

no code implementations25 Apr 2019 Parth Shah, Vishvajit Bakrola, Supriya Pati

In the recent time deep learning has achieved huge popularity due to its performance in various machine learning algorithms.

Nonlinear Semi-Parametric Models for Survival Analysis

1 code implementation14 May 2019 Chirag Nagpal, Rohan Sangave, Amit Chahar, Parth Shah, Artur Dubrawski, Bhiksha Raj

Semi-parametric survival analysis methods like the Cox Proportional Hazards (CPH) regression (Cox, 1972) are a popular approach for survival analysis.

regression Survival Analysis

Neural Machine Translation System of Indic Languages -- An Attention based Approach

1 code implementation2 Feb 2020 Parth Shah, Vishvajit Bakrola

Neural machine translation (NMT) is a recent and effective technique which led to remarkable improvements in comparison of conventional machine translation techniques.

Machine Translation NMT +1

Adaptive Fine-Grained Sketch-Based Image Retrieval

1 code implementation4 Jul 2022 Ayan Kumar Bhunia, Aneeshan Sain, Parth Shah, Animesh Gupta, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

To solve this new problem, we introduce a novel model-agnostic meta-learning (MAML) based framework with several key modifications: (1) As a retrieval task with a margin-based contrastive loss, we simplify the MAML training in the inner loop to make it more stable and tractable.

Meta-Learning Retrieval +1

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