Projects

Course Projects

Visual Question Answering, (Computer Vision), 2016.[Proposal][Poster]
Object Recognition and Localization, (Selected Topics of Image Processing), 2016.[Presentation][Report]
Direction of Arrival Based Spatial Covariance Model For Blind Source Separation, (Speech Signal Processing), 2016.[Presentation]
Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion,(Video Processing), 2016.[Report][Demo-Input][Demo-Output]

Design and implementing Run length encoding, Barrel Shifter, floating point adder & Bus behavior using VHDL and Verilog, (VLSI Design Lab), 2011.
SENSE: Sensitive Encoding technique for Fast MRI using Back Projection, (Medical Image Processing), 2010.
An Semi-Autonomous, External Command Reading White line Follower Robot, (Embedded System-Robotics), 2010.[Report]
Adaptive Beam forming using microphone array for hands free Telephony with the help of generalized side lobe technique, (Adaptive Signal Processing), 2010.[Report]
Detection of Duplicate Forgery in Handwritten Signature using Statistical DWT & EDM, (Wavelet Transform), 2010.[Report][Poster]
Frequency Code(LFM) and Phase code(Barker code) Pulse Compression Techniques in Mono Pulse Radar, (Digital Signal Processing), 2009.[Report]

Summer School on Machine Learning using Deep Learning(optimization for DL,GAN, VAE, DL for RL and game theory), IIIT-H, July, 2017.
Summer School on Advance Computer Vision using Deep Learning(DL)(DL for vision and language(Caption, VQA), DL for videos, object detection, semantic segmenta-tion,Domain Adaption, and advances in 3D), IIIT-H, July, 2017.
Mysore Park Workshop on Vision, Language and AI(Video Caption, guided LSTM,GAN, Adversarial auto-encoders, reinforcement learning, deep contextual mod-els), VLAI 2016, Mysore, Dec, 2016.
Summer School on computer vision using Deep Learning(CNN, RNN, Auto-encoder,optimization for DL, Symbolic deep learning & face, pose and Egocentric actionrecognition, model compression), IIIT-H, July, 2016.
Audio Engineering(Acoustics, Recording, Broadcasting Technology, Surround Sound,Microphones& Speakers) & Audio Post Processing(Harman International), 2012.
Software Architecture of DaVinci Multimedia Processor-DM6437(APL, SPL, IOL) and Video Processing Subsystem(VPFE, VPBE) (IIT Bombay, India), 2011.

Multimodal Differential Network for Visual Question Generation, EMNLP 2018, Brussels, Belgium, 2018.
Learning Semantic Sentence Embeddings using Pair-wise Discriminator, COLING 2018, Santa Fe, New Mexico, USA, 2018.
Differential Attention for Visual Question Answering, CVPR , Salt Lake City, Utah, USA, 2018.
Visual Question Answering, Summer School on Advance Computer Vision, IIIT-H, July, 2017.
Visual Question Answering, (Computer Vision), 2016.

Received Student Volunteer Award from EMNLP and Conference Travel Grant from Microsoft India for EMNLP 2018.
Received Student Volunteer Award from CVF and Conference Travel Grant from Google India for CVPR 2018.
Received Conference Travel Grant from IIT Kanpur for Coling 2018.
Selected in Quiz competition in Deep learning summer school for vision, IIITH,2017
Selected in Quiz competition in Deep learning summer school for ML, IIITH,2017

MPEG-2 Transport Stream Standard(ISO/IEC-13818-1)– PAT, PMT, Descriptor, Section, TS, PES and ES information (Samsung R&D), 2014.
ATSC System Information Standard–A/53 part-1, A/65 and CEA-708,608 for Close Caption Decoder(Samsung R&D), 2014.
DVB Service Information Standard –EN 300468 and EN-300743 Subtitle Decoder (Samsung R&D), 2014.
Digital Audio Processing–Audio Representation, Compression, Microphones, and Speakers module and Audio post processing (Samsung R&D), 2013.
Forward Error Correction Techniques– Uneven Length Protection(Samsung R&D), 2013.
DSP algorithm and Filter Design– FIR/IIR digital filter and transform technique(DFT, DCT, DST, FFT and Wavelet) (Harman International) 2012.