# LiveSketch: Query Perturbations for Guided Sketch-based Visual Search

## TL;DR

LiveSketch introduces an interactive sketch-based image search system that iteratively refines user queries through perturbations, improving search accuracy and efficiency in large image datasets.

## Contribution

It presents a novel triplet convnet with RNN-based variational autoencoder and real-time query perturbation for guided sketch-based visual search.

## Key findings

- Improves search accuracy over baselines.
- Reduces time-to-task in image retrieval.
- Effective in large-scale image datasets.

## Abstract

LiveSketch is a novel algorithm for searching large image collections using hand-sketched queries. LiveSketch tackles the inherent ambiguity of sketch search by creating visual suggestions that augment the query as it is drawn, making query specification an iterative rather than one-shot process that helps disambiguate users' search intent. Our technical contributions are: a triplet convnet architecture that incorporates an RNN based variational autoencoder to search for images using vector (stroke-based) queries; real-time clustering to identify likely search intents (and so, targets within the search embedding); and the use of backpropagation from those targets to perturb the input stroke sequence, so suggesting alterations to the query in order to guide the search. We show improvements in accuracy and time-to-task over contemporary baselines using a 67M image corpus.