Sketch-based image retrieval @ ACMMM’16 & ICPR’16

Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci and Nicu Sebe

In the last few years, the query-by-visual-example paradigm gained popularity, specially for content based retrieval systems. As sketches represent a natural way of expressing a synthetic query, recent research efforts focused on developing algorithmic solutions to address the sketch-based image retrieval (SBIR) problem. Within this context, we propose a novel approach for SBIR that, unlike previous methods, is able to exploit the visual complexity inherently present in sketches and images. We introduce academic learning, a paradigm in which the sample learning order is constructed both from the data, as in self-paced learning, and from partial curricula. We propose an instantiation of this paradigm within the framework of coupled dictionary learning to address the SBIR task. We also present an efficient algorithm to learn the dictionaries and the codes, and to pace the learning combining the reconstruction error, the prior knowledge suggested by the partial curricula and the cross-domain code coherence. In order to evaluate the proposed approach, we report an extensive experimental validation showing that the proposed method outperforms the state-of-the-art in coupled dictionary learning and in SBIR on three different publicly available datasets.

We have published two studies in this direction one at ACM MM’16 [1] and another in IEEE ICPR’16 [2].


  1. D. Xu, X. Alameda-Pineda, J. Song, E. Ricci, and N. Sebe, “Academic Coupled Dictionary Learning for Sketch-based Image Retrieval,” in ACM International Conference on Multimedia, Amsterdam, The Netherlands, 2016. [ bib pdf ]
        title={Academic Coupled Dictionary Learning for Sketch-based Image Retrieval},
        author={Dan Xu and Xavier Alameda-Pineda and Jingkuan Song and Elisa Ricci and Nicu Sebe},
        booktitle={ACM International Conference on Multimedia},
        address={Amsterdam, The Netherlands},
  2. D. Xu, J. Song, X. Alameda-Pineda, E. Ricci, and N. Sebe, “Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition,” in IEEE International Conference on Pattern Recognition, Cancun, Mexico, 2016. [ bib pdf ] Award Best Intel Scientific Award
        title={Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition},
        author={Dan Xu and Jingkuan Song and Xavier Alameda-Pineda and Elisa Ricci and Nicu Sebe},
        booktitle={IEEE International Conference on Pattern Recognition},
        address={Cancun, Mexico},
        award={Best Intel Scientific Award},

Leave a Reply

Your email address will not be published. Required fields are marked *