Skip to Main content Skip to Navigation
New interface
Conference papers

Consistent Visual Words Mining with Adaptive Sampling

Pierre Letessier 1, 2 Olivier Buisson 3 Alexis Joly 1, 4 
4 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : State-of-the-art large-scale object retrieval systems usually combine efficient Bag-of-Words indexing models with a spatial verification re-ranking stage to improve query performance. In this paper we propose to directly discover spatially verified visual words as a batch process. Contrary to previous related methods based on feature sets hashing or clustering, we suggest not trading recall for efficiency by sticking on an accurate two-stage matching strategy. The problem then rather becomes a sampling issue: how to effectively and efficiently select relevant query regions while minimizing the number of tentative probes? We therefore introduce an adaptive weighted sampling scheme, starting with some prior distribution and iteratively converging to unvisited regions. Interestingly, the proposed paradigm is generalizable to any input prior distribution, including specific visual concept detectors or efficient hashing-based methods. We show in the experiments that the proposed method allows to discover highly interpretable visual words while providing excellent recall and image representativity.
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Alexis Joly Connect in order to contact the contributor
Submitted on : Thursday, November 17, 2011 - 3:34:33 PM
Last modification on : Tuesday, October 25, 2022 - 4:23:24 PM
Long-term archiving on: : Friday, November 16, 2012 - 11:21:03 AM


Files produced by the author(s)




Pierre Letessier, Olivier Buisson, Alexis Joly. Consistent Visual Words Mining with Adaptive Sampling. ICMR'11 - International Conference on Multimedia Retrieval, Apr 2011, Trento, Italy. pp.0-0, ⟨10.1145/1991996.1992045⟩. ⟨hal-00642202⟩



Record views


Files downloads