Scholar
Silky Singh
Google Scholar ID: xkv3k4QAAAAJ
Stanford University
Citations & Impact
Citations
14
H-index
2
i10-index
0
Publications
9
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- * LEAST: "Local" text-conditioned image style transfer, CVPR workshop on AI for Content Creation (AI4CC), 2024
- * LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training, British Machine Vision Conference (BMVC), 2023
- * FODVid: Flow-guided Object Discovery in Videos, CVPR workshop on Learning with Limited Labelled Data for Image and Video Understanding (L3D-IVU), 2023
- - Patents filed:
- * Modifying digital images from text via multi-region localized style transfer, Filed: Oct 2024
- * Generating image object segmentations utilizing graph-cut partitioning in self-supervised object discovery, Filed: Sep 2023
- * Video Object Segmentation using estimated motion information and image features, Filed: Aug 2023
- * Personalized form error correction propagation, Filed: Apr 2023
- - Academic service: Reviewer/Sub-Reviewer for WACV 2025, CVPRW 2024 (L3D-IVU, AI4CC), CVPR 2024; Teaching Assistant for Linear Algebra and Applications (Spring 2022, IIT Delhi) and Introduction to Computer Science (Fall 2021, IIT Delhi); Institute Academic Mentor, Board for Student Welfare (Fall 2019, IIT Delhi)
Research Experience
- - MDSR Lab, Adobe, Research Associate, working on generative models, image editing, self-supervised learning, image and video segmentation, and style transfer
- - Adobe Research, worked with Dr. Kuldeep Kulkarni on context-aware object insertion in images
- - Max Planck Institute, worked on program synthesis with Prof. Eva Darulova
Education
- - Stanford University, Master's, Computer Science
- - IIT Delhi, Bachelor's, Mathematics and Computing, Advisor: Prof. Sivananthan Sampath
Background
- Research interests: generative models (diffusion models), image editing, self-supervised learning, image and video segmentation, style transfer. Professional field: Computer Vision and Machine Learning.
Miscellany
- Personal interests and other information not provided
