LIRIS - Imagine at Image CLEF 2012 Photo Annotation Task - Archive ouverte HAL Access content directly
Poster Communications Year : 2012

LIRIS - Imagine at Image CLEF 2012 Photo Annotation Task

Abstract

In this paper, we present the methods we have proposed and evaluated through the ImageCLEF 2012 Photo Annotation task. More precisely, we have proposed the Histogram of Textual Concepts (HTC) textual feature to capture the relatedness of semantic concepts. In contrast to term frequency-based text representations mostly used for visual concept detection and annotation, HTC relies on the semantic similarity between the user tags and a concept dictionary. Moreover, a Selective Weighted Late Fusion (SWLF) is introduced to combine multiple sources of information which by iteratively selecting and weighting the best features for each concept at hand to be classified. The results have shown that the combination of our HTC feature with visual features through SWLF can improve the performance significantly. Our best model, which is a late fusion of textual and visual features, achieved a MiAP (Mean interpolated Average Precision) of 43.67 % and ranked first out of the 80 submitted runs.
No file

Dates and versions

hal-01353174 , version 1 (10-08-2016)

Identifiers

  • HAL Id : hal-01353174 , version 1

Cite

Ningning Liu, Emmanuel Dellandréa, Liming Chen, Aliaksandr Trus, Chao Zhu, et al.. LIRIS - Imagine at Image CLEF 2012 Photo Annotation Task. CLEF 2012 Conference, Sep 2012, Rome, Italy. pp.20-25, 2012. ⟨hal-01353174⟩
81 View
0 Download

Share

Gmail Facebook X LinkedIn More