Perla Sai Raj Kishore

Learning to teach machines how to
SEE, LEARN and EVOLVE.


I am a Jr. Research Engineer at Staqu Technologies, working on designing and building systems that revolve around Computer Vision and Deep Learning.

I did my Bachelor's in Electronics and Communication Engineering from Institute of Engineering & Management (IEM), Kolkata. During my undergrad, I got the opportunity to work with Prof. Ujjwal Bhattacharya of Computer Vision & Pattern Recognition Unit at Indian Statistical Institute (ISI), Kolkata and Prof. Partha Pratim Roy of Indian Institute of Technology (IIT), Roorkee on various Computer Vision research problems. I also interned under Prof. A. V. Subramanyam of Indraprastha Institute of Information Technolgy (IIIT), Delhi where I worked on Image Super Resolution. I completed my bachelor's thesis on Unsupervised Pose Estimation of Pedestrians under the guidance of Prof. Ujjwal Bhattacharya and Prof. Indranil Basu of IEM.


Email  /  CV  /  Google Scholar  /  LinkedIn  /  GitHub

Profile Photo
Research Interests

I am broadly interested in the field of Computer Vision and Deep Learning. Particularly, I like to think upon Visual Scene Understanding (VSU) from images and videos, effective methods of Domain Adaptation & Transfer Learning for VSU, building systems that learn with minimal or no supervision and systems that generalize well in real and diverse scenarios. I am also open to any topic that would be interesting or fun to explore and pursue.

Publications
An End-to-End Framework for Unsupervised Pose Estimation of Occluded Pedestrians
Sudip Das*, Perla Sai Raj Kishore*, Ujjwal Bhattacharya
Under Review, 2020

ClueNet: A Deep Framework for Occluded Pedestrian Pose Estimation
Perla Sai Raj Kishore*, Sudip Das*, Partha Sarathi Mukherjee, Ujjwal Bhattacharya
British Machine Vision Conference (BMVC), 2019

Abstract / BibTex

Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning
Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Perla Sai Raj Kishore, Partha Pratim Roy
Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Abstract / Code / arXiv / BibTex

User Constrained Thumbnail Generation Using Adaptive Convolutions
Perla Sai Raj Kishore, Ayan Kumar Bhunia, Shovozit Ghose, Partha Pratim Roy
International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
(Oral Presentation)

Abstract / Code / arXiv / BibTex

Texture Synthesis Guided Deep Hashing for Texture Image Retrieval
Ayan Kumar Bhunia, Perla Sai Raj Kishore, Pranay Mukherjee, Abhirup Das, Partha Pratim Roy
Winter Conference on Applications of Computer Vision (WACV), 2019

Abstract / arXiv / BibTex

Flatten-T Swish: A thresholded ReLU-Swish-like Activation Function for Deep Learning
Hock Hung Chieng, Noorhaniza Wahid, Ong Pauline, Perla Sai Raj Kishore
International Journal of Advances in Intelligent Informatics (IJAIN), 2018  
(Best Paper Award)

Abstract / Code / arXiv / BibTex



Projects
Saliency Detection: PyTorch implementation of a CVPR 2019 Publication

PyTorch implementation of the paper "Pyramid Feature Attention Network for Saliency Detection", published at CVPR 2019.

Code / Paper

Single Image Super Resolution

Image super resolution aims to increase the resolution of an image by generating pixels which interpolate best between a given Low Resolution and the required High Resolution image. I built a deep learning based model for this purpose. A large amount of diverse data was also collected to train this model. The model was implemented in Keras and comes with an easy to use interface. This was my project as an intern under Prof. A. V. Subramanyam of IIIT, Delhi.

Code / Papers on Super Resolution

Mixture Density Networks

Mixture Density Networks (MDNs) are an interesting way to address multimodality (where the input and output hold a one-to-many relationship). In such scenarios, instead of directly predicting the output we model the probability distribution of the output as a weighed mixture of several Gaussians from which we sample the actual output. In this project, I implemented univariate and bivariate MDNs in Python using Tensorflow.

Code / Original Paper

Character Level Language Model

Auto-correct and auto-complete, which have now become a standard feature in almost all digital keyboards, make use of a language model at its core. In this project, I built a LSTM based character-level language model that aims to predict the next character from a sequence of input characters. The code for this project was written in Python using Tensorflow.

Code

Lane Detection in NFS: Underground 2

Self Driving cars are one of the fascinating technologies in this modern world. Though the entire process, from perceiving the surroundings to getting the car to move, is fairly complex, the first step usually begins with detection of lanes which guide the vehicle on the road. In this project, I attempt to do the same in one the popular games "NFS: Underground 2" using OpenCV in Python.

Code

Machine Learning Algorithms

In this project, I implemented various Machine Learning algorithms from scratch in Python using only Numpy.

Code


Template credits : Dr. Jon Barron