Soumyadeep Banik

AI Researcher

Mumbai, Maharashtra, India4 yrs 5 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

3+ years of experience in Computer Vision and Deep Learning.
Expertise in Human Activity Recognition and object detection.
Passionate about leveraging technology for real-world challenges.

Stackforce AI infers this person is a Computer Vision and Deep Learning specialist in the SaaS industry.

Contact

soumya.d.banik@gmail.com LinkedIn

Skills

Core Skills

Computer VisionDeep Learning

Other Skills

Algorithm DesignAlgorithm DevelopmentAmazon Web Services (AWS)Approximation AlgorithmsArtificial Intelligence (AI)C (Programming Language)CSS SpritesCUDACryptographyData StructuresDatabase Management System (DBMS)Dataset DevelopmentDockerFastAPIGit

About

Hi there, thanks for visiting! I'm a data Scientist with over 3+ years of extensive experience in Computer Vision and Deep Learning. My interests lies in Human Activity Recognition(HAR), object detection, object tracking etc. Passionate about leveraging cutting-edge technology to solve real-world challenges for video surveillance. - Developed an end-to-end pipeline for building, inferencing, deploying SlowFast models for HAR into edges efficiently. - Exploring intricate spatio-temporal deep learning models(Slowfast, ViT, 3d-CNN, ConvLSTM etc.) - Experienced on building, preprocessing, cleaning large scale dataset. - Additionally built Space Utilization algorithms, implementing image processing techniques to optimize inventory spaces. - Collaborated on various projects like face detection, object counting, emotion recognition, and fire-smoke detection. Research interests - Graph Representation Learning, GNNs and ST-GCN

Experience

Quidich innovation labs

Computer Vision Engineer

Apr 2024 – Present · 1 yr 11 mos · Mumbai, Maharashtra, India · On-site

Ai lens

Computer Vision Developer

Jan 2024 – Present · 2 yrs 2 mos · Remote

Building Virtual Try-On platform and recommendation system

Happymonk.ai

Junior Data Scientist

Dec 2022 – Jan 2024 · 1 yr 1 mo · Bengaluru, Karnataka, India · On-site

Worked on Human Activity Recognition.
Led the entire project lifecycle from data collection, preparation, preprocessing, model development to deployment on edge devices
Leveraged SLOWFAST network to develop a spatio-temporal deep learning model to accurately detect human activities within a scene
Automated the entire pipeline to streamline the production processes
Space Utilization
Employed image processing techniques to implement an algorithm to show the empty spaces within an extensive inventory area
Object detection
Collaborated in multiple projects on developing the dataset, object detection models(e.g. YOLO V5, YOLO v8) across different domains, addressing business problems such as face detection, object counting, emotion recognition, and fire-smoke detection etc.
Collaborated with the team to efficiently deploy these models on edge devices

Human Activity RecognitionSLOWFAST networkImage ProcessingObject DetectionComputer VisionDeep Learning

Indian statistical institute, kolkata

3 roles

Teaching Assistant

Aug 2022 – Sep 2022 · 1 mo · Kolkata, West Bengal, India

Machine Learning- I

Teaching Assistant

Feb 2022 – Jul 2022 · 5 mos · Kolkata, West Bengal, India

M.Tech Computer Science
Course name: Advanced Image Processing

Project Linked Junior Research Fellow

Oct 2021 – Dec 2022 · 1 yr 2 mos · Kolkata, West Bengal, India

Worked on a project entitled "Distributed Cognitive System for Healthcare" which was focused on recognizing the anomalous human activities for elderly people, targated to old age homes.