Name: Muralikrishna SN
Type: User
Company: @Manipal Institute of Technology
Bio: I am a researcher, working in the area of Computer Vision and AI. I am currently pursuing my post-doctoral study at Chosun University, Gwangju, S. Korea.
Blog: https://manipal.edu/mit/department-faculty/faculty-list/muralikrishna-sn.html
Muralikrishna SN's Projects
3D Dense Connected Convolutional Network (3D-DenseNet for action recognition)
Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder
Action Recognition using SVM, BoW pipeline
CS676 course project
Tools to participate in the ActivityNet Challenge 2016
Information about activity recognition
A curated list of action recognition and related area resources
A curated list of background subtraction related papers and resources
A curated list of resources dedicated to optical flow algorithms. Feel free to make PRs to contribute.
This is a BoW implementation for action recognition problem in Matlab.
A MATLAB toolbox for classifier: Version 1.0.7
Project for CS 231N
Code repository for Convolutional Pose Machines, CVPR'16
Cryptographic toolkit for searchable encryption.
Basic Cuda tutorial
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 200 universities.
Semantic Text Similarity Dataset Hub
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Simple Online Realtime Tracking with a Deep Association Metric
Dynamic Searchable Symmetric Encryption
Face Detection with Python using OpenCV
Efficient feature extraction, aggregation and classification for action recognition (CVPR 2014)
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding
GloVe model for distributed word representation
Human action recognition based on joint dynamics
Source code for the paper "Learning features combination for human action recognition from skeleton sequences".