UPMC at MediaEval 2013: Relevance by Text and Diversity by Visual Clustering

Abstract : In the diversity task, our strategy was to, first, try to improve relevance, and then to cluster similar images to improve diversity. We propose a four step framework, based on AHC clustering and different reranking strategies. A large number of tests on devset showed that most of the best strategies include text based reranking for pertinence, and visual clustering for diversity - even compared to location based descriptors. Results on expert and crowd-sourcing testset grounds truths seem to confirm these observations.
Document type :
Conference papers
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-00925153
Contributor : Christian Antonio Kuoman Mamani <>
Submitted on : Tuesday, January 7, 2014 - 4:11:35 PM
Last modification on : Thursday, March 21, 2019 - 1:13:39 PM

Identifiers

  • HAL Id : hal-00925153, version 1

Citation

Christian Antonio Kuoman Mamani, Sabrina Tollari, Marcin Detyniecki. UPMC at MediaEval 2013: Relevance by Text and Diversity by Visual Clustering. MediaEval 2013 Multimedia Benchmark Workshop, Oct 2013, Barcelona, Spain. ⟨hal-00925153⟩

Share

Metrics

Record views

130