Publications

* indicates submitted and pending review

We present PECNet -- A Predicted Endpoint Conditioned trajectory prediction network for forecasting multimodal human trajectories respecting social norms in multi-agent scenarios
European Conference on Computer Vision 2020 (Oral)

A Multi Stream convultional-deconvolutional framework for predicting future positions of pedestrians in egocentric videos using pose, location and egomotion features.
European Conference on Computer Vision 2020 (Oral)

A Robust Encoder-recurrent-Decoder framework for egocentric human locomotion forecasting based on disentangling concurrent human motion
Winter Conference on Applications of Computer Vision 2020 (Oral)

A Multi Stream convultional-deconvolutional framework for predicting future positions of pedestrians in egocentric videos using pose, location and egomotion features.
Computer Vision and Pattern Recognition 2018 (Spotlight)

A Multitask framework that utilizes the spontaneity information present in speech to improve the performance at emotion recognition tasks.
Interspeech 2018 (Oral)

We show that learning in Deep Networks is a two stage process. First, it rapidly learns 'shallow learnable' ('easier') examples and then slowly learns to generalize to other 'harder' examples.
Workshop on Identifying and Understanding Deep Learning Phenomena (ICML 2020) (Oral)

An algorithm to extend the use of Cellular Automata from the confined space of binary images to Grayscale images with minimal time and space overheads.
28th Irish Signals and Systems Conference 2017

Selected Projects

For a complete list, kindly see my CV

Future Person Localization in First-Person Videos

Developed a novel deep architecture for predicting future locations of people observed in first-person videos. Released a new dataset on human locomotion seen in FPV. Paper under review at CVPR’18.

Automated Modelling for Course Recommendation (C.R.A.M)

Web-app for course recommendation using recommendation engine and text analysis. Won OVERALL BEST PROJECT in Google DevFest 2016. See project page for details.

Cellular Automata for Image Processing

Designed a novel algorithm to extend application of cellular automaton based image processing methods to grayscale images. Paper published at 28th Irish Signal and Systems Conference 2017

Compressing U-net using Knowledge Distillation

Designed a knowledge distillation procedure aimed for compressing Fully Convolutional Network (FCN) with skip connections such as U-net and Stacked Hourglass Network. Achieved ~100x model compression.

Emotion Recognition from Static Human facial Images

Implemented various classfiers for human emotion detection in the Emotion Recognition in the Wild Challenge 2016 dataset to compare against results from CNN based approaches. Details on project page.

Image Prcessing for Autonomous Underwater Vehicle, Robotics Club, IIT Kanpur

Deisgned and developed early prototypes of an onboard image processing pipeline capable of underwater object recognition and autonomous manoeuvre. The current updated code is available here.

Solutions To Non-Causal Difference Equations

Designed an algorithm for finding solutions to Non-Causal discrete difference equations (in context of discrete time systems) efficiently optimizing MATLAB in-built methods for the same. Applied spline interploation and sampling techniques for faster algoithm.

Speech based synchrony measuerement in dyadic interaction

We aimed to develop a measure for synchrony measurement between speakers in one on one conversations. It was ndergraduate Research project for junior year under Prof. Tanaya Guha IIT Kanpur

Hybrid Recommender Systems using feature selection by Markov Blanket

Implemented a recommendation engine pipeline for e-commerce products. For pre-processing, designed a PGM based procedure for feature selection based on IAMB algorithm and for recommendations, trained a Collaborative filtering based Restricted Boltzmann Machine on Amazon datasets. The corresponding code is confidential being a product of my work as Research intern at Busigence in winters 2016.

Teaching

I have worked as a Academic mentor in Counselling Service, IITK for

PHY102 : Introduction to Mechanics

in my sophomore year (2015 - 2016) in IIT Kanpur. I was responsible for providing academic support to freshmen in terms of one-on-one mentoring and remedial classes for concept strengtening, problem solving and revision.

Contact

Please feel free to reach to me for any query