VL2G @ IITJ

Multimodal Deep Learning, Knowledge-intensive visual tasks

Chart Image Parsing and ChartQA

Deep Learning, Video Understanding

Deep Learning, Computer Vision, Handwritten Image Analysis

	Research Area
MTech
Ritu Singh	Document Intelligence
Kranti Prakash	Video Understanding
BTech
Arvind Kumar Sharma	Visual Translation
Shreyas Vaidya	Visual Translation
Harshiv Shah	Scene Text Understanding
Aditya Rathor	Scene Text Understanding
RA
Anik De	Document Intelligence, Indian Language Scene Text Understanding
Uday Agarwal	Video Understanding

	Research Area	First Employment
MTech
Apoorv Shekhar	Visual Relationships	TuningBill
Dhriti Prasanna Paul	Computer Vision	Rakuten Mobile Japan
Deepti Gupta	Indic Scene Text Detection	Spanidea
Gaurav Pilankar	-	CDAC Pune
Pratik Vilasrao Somwanshi	-	Spanidea Systems
Kena Hemnani	-	Valeo India
Megha kumari	Math-based QA	CDAC Mohali
Rahul Kumar Chaudhary	-	Spanidea
Parsa Revanth	Multimodal Knowledge Graphs	-
Stuti Pathak	Flow2code	-
Rati Kumari	-	-
Ambikesh Kumar Singh	-	-
Btech
Nakul Sharma	Graphical Elements Interpretation, LLMs	SpreeAI
Shreya Shukla	Graphical Elements Interpretation, LLMs, Code Generation	Mercedes Benz R&D
Abu Shahid	Video Understanding, Handwritten Recognition	Decimal Point Analytics
Maniyar Suyash	Document AI	Decimal Point Analytics
Ayush Anand	Object Detection, Document Intelligence	-
Mayank Maheshwari	Visual Relationships	Wadhawani AI
Vaibhav Mishra	-	Jio Platforms
RA
Prajwal Gatti	-	Ph.D. at University of Bristol
Revant Teotia	-	MS at Columbia University → PhD student at NYU