Kanchana Ranasinghe

Intriguing Properties of Vision Transformers

Muzammal Naseer, Kanchana Ranasinghe, Salman Khan et al. · arXiv (Cornell University) · 2021 · 301 citations · Full text

Convolutional Neural Network, Machine Vision, Machine Learning +15

Self-supervised Video Transformer

Kanchana Ranasinghe, Muzammal Naseer, Salman Khan et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 106 citations

Engineering, Machine Learning, Self-supervised Training +16

Perceptual Grouping in Contrastive Vision-Language Models

Kanchana Ranasinghe, Brandon McKinzie, Sachin Ravi et al. · 2023 · 28 citations

Perceptual Grouping, Few-shot Learning, Engineering +20

Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs

Kanchana Ranasinghe, Satya Narayan Shukla, Omid Poursaeed et al. · 2024 · 17 citations

Combined Static and Motion Features for Deep-Networks-Based Activity Recognition in Videos

Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara et al. · IEEE Transactions on Circuits and Systems for Video Technology · 2017 · 15 citations · Full text

Motion Tubes, Motion Components, Engineering +21