Mar 16, 2017 · In this paper, we speed up SBIR by introducing a novel binary coding method, named \textbf{Deep Sketch Hashing} (DSH), where a semi-heterogeneous deep ...

In this paper, we speed up SBIR by introducing a novel binary coding method, named Deep Sketch Hashing (DSH), where a semi-heterogeneous deep architecture is ...

Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval; by Li Liu ... This work focuses on fast sketch-based image retrieval (SBIR) using binary codes.

This work proposes a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset.

Speeds up SBIR by embedding sketches and natural images into two sets of compact binary codes. ○ In Large-scale SBIR, heavy continuous-valued.

In this paper, we speed up SBIR by introducing a novel binary coding method, named \textbf{Deep Sketch Hashing} (DSH), where a semi-heterogeneous deep ...

Meanwhile, Liu et al. [2] introduced a new binary coding method to speed up retrieval speed, named deep sketch hashing (DSH), where a semi-heterogeneous ...

Free-hand sketch-based image retrieval (SBIR) is a specific cross-view retrieval task, in which queries are abstract and ambiguous sketches while the retrieval ...

Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval, CVPR 2017, [code] ; Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image ...

In FG-SBIR, free-hand human sketch images are used as queries to retrieve photo images containing the same object instances.