Fast and Accurate User constrained Thumbnail Generation using Adaptive Convolutions. | ICASSP 2019 [ORAL]

The codebase for Zoom Out-and-In Network with Recursive Training for Object Proposal

Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.

Region Proposal generation on images using clustering in Pointcloud - Currently only for Pedestrians

Adaptive Region Proposal for Object Tracking

Image classification svm with simple neural network.

Unsupervised region proposal and supervised patch extraction algorithms for extracting candidate 2D ROIs to train SVM/CNN classifiers, for mass detection in mammograms.

region proposal network

Deep learning project

Propose a probability function to estimate the possibility of a person appearing in a region of image