Sayan Nag
Scholar

Sayan Nag

Google Scholar ID: K8w4dj4AAAAJ
Research Scientist, Adobe Research
Multimodal LearningDeep LearningComputer VisionVision+LanguageAI for Climate Change
Citations & Impact
All-time
Citations
895
 
H-index
18
 
i10-index
25
 
Publications
20
 
Co-authors
29
list available
Resume (English only)
Academic Achievements
  • Paper 'Localizing Knowledge in DiTs and MAGNET' accepted at NeurIPS 2025.
  • Papers 'AVTrustBench, Aurelia and EgoAdapt' accepted at ICCV 2025.
  • Recognized as an outstanding reviewer at CVPR 2025.
  • Papers 'SafaRi and Meerkat' accepted at ECCV 2024.
  • EgoVLPv2 awarded as an EgoVis 2022/2023 Distinguished Paper.
  • Papers 'VistaLLM and MelFusion' selected as Highlights (Top 2.8% of submitted papers) and accepted at CVPR 2024.
  • Paper 'ApoLLo' accepted at EMNLP 2023.
  • Paper 'VoLTA' accepted at TMLR 2023.
  • Paper 'EgoVLPv2' accepted at ICCV 2023.
  • Paper 'BeAts' accepted at Interspeech 2023 as an Oral presentation.
  • Paper 'DeCAtt' accepted at CVPRw 2023 as an Oral presentation.
  • Paper 'IDEAL' accepted at ICASSP 2023.
  • Paper on 'SERF: Towards better training of deep neural networks using log-Softplus ERror activation Function' accepted at WACV 2023.
  • Paper on 'Deciphering Environmental Air Pollution with Large Scale City Data' accepted at IJCAI 2022 as an Oral Presentation.
  • Abstract on 'Fast and scalable estimation of effective connectivity using Neural Network aided P-DCM' accepted at OHBM 2022.
  • Paper on 'Graph Self Supervised Learning: the BT, the HSIC, and the VICReg' presented at IJCAI Weakly Supervised Representation Learning Workshop 2021.
  • Paper on 'CDF-Net: Cross-Domain Fusion Network for Accelerated MRI Reconstruction' presented at MICCAI 2020.
Research Experience
  • Worked as a research intern at Adobe Research.
Education
  • PhD from University of Toronto; Bachelor's degree in Electrical Engineering from Jadavpur University, India.
Background
  • Currently a Research Scientist at Adobe Research. Research interests include Computer Vision, Self-supervised Learning, Multimodal Learning, Time-series Modeling, and Natural Language Understanding.
Miscellany
  • Personal interests not mentioned.