Search Results for author: Snehasis Mukherjee

Found 19 papers, 10 papers with code

WSD: Wild Selfie Dataset for Face Recognition in Selfie Images

no code implementations14 Feb 2023 Laxman Kumarapu, Shiv Ram Dubey, Snehasis Mukherjee, Parkhi Mohan, Sree Pragna Vinnakoti, Subhash Karthikeya

In order to alleviate this problem and to facilitate the research on selfie face images, we develop a challenging Wild Selfie Dataset (WSD) where the images are captured from the selfie cameras of different smart phones, unlike existing datasets where most of the images are captured in controlled environment.

Face Recognition

DFW-PP: Dynamic Feature Weighting based Popularity Prediction for Social Media Content

1 code implementation16 Oct 2021 Viswanatha Reddy G, Chaitanya B S N V, Prathyush P, Sumanth M, Mrinalini C, Dileep Kumar P, Snehasis Mukherjee

The over-saturation of content on social media platforms has persuaded us to identify the important factors that affect content popularity.


MERANet: Facial Micro-Expression Recognition using 3D Residual Attention Network

no code implementations7 Dec 2020 Viswanatha Reddy Gajjala, Sai Prasanna Teja Reddy, Snehasis Mukherjee, Shiv Ram Dubey

The proposed model takes advantage of spatial-temporal attention and channel attention together, to learn deeper fine-grained subtle features for classification of emotions.

Micro Expression Recognition Micro-Expression Recognition

AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning

1 code implementation25 Apr 2020 S. H. Shabbeer Basha, Sravan Kumar Vinakota, Viswanath Pulabaigari, Snehasis Mukherjee, Shiv Ram Dubey

The experimental results obtained in this study depict that tuning of the pre-trained CNN layers with the knowledge from the target dataset confesses better transfer learning ability.

Bayesian Optimization Transfer Learning

An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos

no code implementations6 Feb 2020 S. H. Shabbeer Basha, Viswanath Pulabaigari, Snehasis Mukherjee

Traditionally in deep learning based human activity recognition approaches, either a few random frames or every $k^{th}$ frame of the video is considered for training the 3D CNN, where $k$ is a small positive integer, like 4, 5, or 6.

Action Recognition In Videos General Classification +2

AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small Dataset

no code implementations22 Jan 2020 S. H. Shabbeer Basha, Sravan Kumar Vinakota, Shiv Ram Dubey, Viswanath Pulabaigari, Snehasis Mukherjee

Fine-tuning the newly learned (target-dependent) FC layers leads to state-of-the-art performance, according to the experiments carried out in this research.

Bayesian Optimization Image Classification +1

diffGrad: An Optimization Method for Convolutional Neural Networks

1 code implementation12 Sep 2019 Shiv Ram Dubey, Soumendu Chakraborty, Swalpa Kumar Roy, Snehasis Mukherjee, Satish Kumar Singh, Bidyut Baran Chaudhuri

In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i. e., diffGrad).

Image Categorization

Visual Question Answering using Deep Learning: A Survey and Performance Analysis

1 code implementation27 Aug 2019 Yash Srivastava, Vaishnav Murali, Shiv Ram Dubey, Snehasis Mukherjee

The Visual Question Answering (VQA) task combines challenges for processing data with both Visual and Linguistic processing, to answer basic `common sense' questions about given images.

Common Sense Reasoning Question Answering +1

A Conditional Adversarial Network for Scene Flow Estimation

1 code implementation25 Apr 2019 Ravi Kumar Thakur, Snehasis Mukherjee

The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics.

Optical Flow Estimation Scene Flow Estimation

Spontaneous Facial Micro-Expression Recognition using 3D Spatiotemporal Convolutional Neural Networks

1 code implementation27 Mar 2019 Sai Prasanna Teja Reddy, Surya Teja Karri, Shiv Ram Dubey, Snehasis Mukherjee

This paper proposes two 3D-CNN methods: MicroExpSTCNN and MicroExpFuseNet, for spontaneous facial micro-expression recognition by exploiting the spatiotemporal information in CNN framework.

Facial Expression Recognition Micro Expression Recognition +1

Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification

1 code implementation21 Jan 2019 S. H. Shabbeer Basha, Shiv Ram Dubey, Viswanath Pulabaigari, Snehasis Mukherjee

To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets.

General Classification Image Classification

A Multi-Face Challenging Dataset for Robust Face Recognition

no code implementations30 Sep 2018 Shiv Ram Dubey, Snehasis Mukherjee

Multiple face recognition in unconstrained environment is a challenging task, due to the variation of view-point, scale, pose, illumination and expression of the face images.

Face Recognition Robust Face Recognition

SceneEDNet: A Deep Learning Approach for Scene Flow Estimation

1 code implementation10 Jul 2018 Ravi Kumar Thakur, Snehasis Mukherjee

This paper introduces a first effort to apply a deep learning method for direct estimation of scene flow by presenting a fully convolutional neural network with an encoder-decoder (ED) architecture.

Decoder Scene Flow Estimation

Human Activity Recognition in RGB-D Videos by Dynamic Images

no code implementations9 Jul 2018 Snehasis Mukherjee, Leburu Anvitha, T. Mohana Lahari

The proposed method aims in capturing the motion information of the whole video by producing a dynamic image corresponding to the input video.

Human Activity Recognition

Automatic Assessment of Artistic Quality of Photos

1 code implementation17 Apr 2018 Ashish Verma, Kranthi Koukuntla, Rohit Varma, Snehasis Mukherjee

The dataset contains some images captured by professional photographers and the rest of the images captured by common people.

LDOP: Local Directional Order Pattern for Robust Face Retrieval

no code implementations28 Feb 2018 Shiv Ram Dubey, Snehasis Mukherjee

The proposed local directional order pattern (LDOP) for a particular pixel is computed by finding the relationship between the center pixel and local directional order indexes.

Image Retrieval Retrieval

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