| Full text | |
| Author(s): |
Bui, Tu
;
Ribeiro, Leonardo
;
Ponti, Moacir
;
Collomosse, John
;
Jawahar, CV
;
Li, H
;
Mori, G
;
Schindler, K
Total Authors: 8
|
| Document type: | Journal article |
| Source: | COMPUTER VISION - ACCV 2018, PT III; v. 11363, p. 16-pg., 2019-01-01. |
| Abstract | |
We present an algorithm for visually searching image collections using free-hand sketched queries. Prior sketch based image retrieval (SBIR) algorithms adopt either a category-level or fine-grain (instance-level) definition of cross-domain similarity-returning images that match the sketched object class (category-level SBIR), or a specific instance of that object (fine-grain SBIR). In this paper we take the middle-ground; proposing an SBIR algorithm that returns images sharing both the object category and key visual characteristics of the sketched query without assuming photo-approximate sketches from the user. We describe a deeply learned cross-domain embedding in which 'mid-grain' sketch-image similarity may be measured, reporting on the efficacy of unsupervised and semi-supervised manifold alignment techniques to encourage better intra-category (mid-grain) discrimination within that embedding. We propose a new mid-grain sketch-image dataset (MidGrain65c) and demonstrate not only mid-grain discrimination, but also improved category-level discrimination using our approach. (AU) | |
| FAPESP's process: | 17/10068-2 - Dimensionality reduction methods for representations generated by triplet convolutional networks |
| Grantee: | Leo Sampaio Ferraz Ribeiro |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |
| FAPESP's process: | 16/16111-4 - Feature learning applied to sketch-based image retrieval and low-altitude remote sensing |
| Grantee: | Moacir Antonelli Ponti |
| Support Opportunities: | Regular Research Grants |
| FAPESP's process: | 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry |
| Grantee: | Francisco Louzada Neto |
| Support Opportunities: | Research Grants - Research, Innovation and Dissemination Centers - RIDC |