Search Results for author: Anurag Mittal

Found 27 papers, 8 papers with code

Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks

1 code implementation14 Nov 2021 Arulkumar Subramaniam, Jayesh Vaidya, Muhammed Abdul Majeed Ameen, Athira Nambiar, Anurag Mittal

In this work, we propose to utilize the common rationale that a sequence of video frames capture a set of common objects and interactions between them, thus a notion of co-segmentation between the video frame features may equip the model with the ability to automatically focus on task-specific salient regions and improve the underlying task's performance in an end-to-end manner.

Action Classification Object +6

ReFIn: A Refinement Approach for Video Frame Interpolation

no code implementations NeurIPS Workshop Deep_Invers 2021 Saikat Dutta, Anurag Mittal

Video Frame Interpolation is an important video enhancement problem which aims to generate one or multiple frames between consecutive frames in video.

Optical Flow Estimation Video Enhancement +1

On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering

no code implementations28 Aug 2021 Gouthaman KV, Anurag Mittal

This paper shows that the sequence model architecture used in the question-encoder has a significant role in the generalizability of VQA models.

Graph Attention Question Answering +1

Face Age Progression With Attribute Manipulation

no code implementations14 Jun 2021 Sinzith Tatikonda, Athira Nambiar, Anurag Mittal

In this paper, we propose a novel holistic model in this regard viz., ``Face Age progression With Attribute Manipulation (FAWAM)", i. e. generating face images at different ages while simultaneously varying attributes and other subject specific characteristics.

Attribute Generative Adversarial Network +1

MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis

no code implementations2 Nov 2020 Rahul Chakwate, Arulkumar Subramaniam, Anurag Mittal

Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space.

General Classification Representation Learning +2

WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolution

no code implementations7 Oct 2020 Vikram Singh, Anurag Mittal

In this work, we propose an approach to divide the problem of image super-resolution into multiple sub-problems and then solve/conquer them with the help of a neural network.

Image Super-Resolution

Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder

no code implementations ECCV 2020 Gouthaman KV, Anurag Mittal

We demonstrate the effect of VGQE on three recent VQA models and achieve state-of-the-art results on the bias-sensitive split of the VQAv2 dataset; VQA-CPv2.

Question Answering Visual Grounding +1

Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval

no code implementations18 Jan 2020 Anubha Pandey, Ashish Mishra, Vinay Kumar Verma, Anurag Mittal, Hema A. Murthy

Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training.

Retrieval Sketch-Based Image Retrieval

Blind Deblurring Using GANs

1 code implementation27 Jul 2019 Manoj Kumar Lenka, Anubha Pandey, Anurag Mittal

Modifications to the structures is done to improve the global perception of the model.

Deblurring Generative Adversarial Network +2

A Zero-Shot Framework for Sketch based Image Retrieval

no code implementations ECCV 2018 Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal

In this paper, we propose a new bench mark for zero-shot SBIR where the model is evaluated on novel classes that are not seen during training.

Retrieval Sketch-Based Image Retrieval

A Zero-Shot Framework for Sketch-based Image Retrieval

1 code implementation31 Jul 2018 Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal

In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training.

Retrieval Sketch-Based Image Retrieval

A Generative Approach to Zero-Shot and Few-Shot Action Recognition

no code implementations27 Jan 2018 Ashish Mishra, Vinay Kumar Verma, M Shiva Krishna Reddy, Arulkumar S, Piyush Rai, Anurag Mittal

In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class.

Attribute Few-Shot action recognition +4

A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders

no code implementations3 Sep 2017 Ashish Mishra, M Shiva Krishna Reddy, Anurag Mittal, Hema A. Murthy

By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.

Attribute General Classification +2

CoMaL Tracking: Tracking Points at the Object Boundaries

no code implementations7 Jun 2017 Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal

Experiments show improvements over a simple re-detect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries.

Object Point Tracking

An Empirical Evaluation of Visual Question Answering for Novel Objects

no code implementations CVPR 2017 Santhosh K. Ramakrishnan, Ambar Pal, Gaurav Sharma, Anurag Mittal

We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data.

Question Answering Visual Question Answering

Bi-modal First Impressions Recognition using Temporally Ordered Deep Audio and Stochastic Visual Features

1 code implementation31 Oct 2016 Arulkumar Subramaniam, Vismay Patel, Ashish Mishra, Prashanth Balasubramanian, Anurag Mittal

We propose a novel approach for First Impressions Recognition in terms of the Big Five personality-traits from short videos.

CoMaL: Good Features to Match on Object Boundaries

no code implementations CVPR 2016 Swarna K. Ravindran, Anurag Mittal

In this paper, we propose a new approach for feature detection, tracking and re-detection that gives significantly improved results at the object boundaries.

Object

Sketch-based Image Retrieval from Millions of Images under Rotation, Translation and Scale Variations

no code implementations31 Oct 2015 Sarthak Parui, Anurag Mittal

The object boundaries are represented as chains of connected segments and the database images are pre-processed to obtain such chains that have a high chance of containing the object.

Object object-detection +4

Adaptive Locally Affine-Invariant Shape Matching

no code implementations25 Apr 2015 Smit Marvaniya, Raj Gupta, Anurag Mittal

The problem is difficult due to many factors such as intra-class variations, local deformations, articulations, viewpoint changes and missed and extraneous contour portions due to errors in shape extraction.

Mixture of Parts Revisited: Expressive Part Interactions for Pose Estimation

no code implementations21 Dec 2014 Anoop Katti, Anurag Mittal

Two of the most common and strong manifestations of such unhandled interactions are self-occlusion among the parts and the confusion in the localization of the non-adjacent symmetric parts.

Pose Estimation

CoMIC: Good features for detection and matching at object boundaries

no code implementations5 Dec 2014 Swarna Kamlam Ravindran, Anurag Mittal

Feature or interest points typically use information aggregation in 2D patches which does not remain stable at object boundaries when there is object motion against a significantly varying background.

Object Point Tracking

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