DigInPix: Visual Named-Entities Identification in Images and Videos

Pierre Letessier 1 Nicolas Hervé 1 Alexis Joly 2 Hakim Nabi 1 Mathieu Derval 1 Olivier Buisson 3
2 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper presents an automatic system able to identify visual named-entities appearing in images and videos, among a list of 25,000 entities, aggregated from Wikipedia lists, and more specific websites. DigInPix is a generic application designed to identify different kinds of entities. In this first attempt , we only focus on logo identification (more generally on legal persons). The identification process mainly relies on an efficient CBIR system, searching in an indexed image database composed of 600,000 weak-labelled images crawled from Google Images. DigInPix proposes a responsive-design html5 interface 1 for testing purposes.
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-01182780
Contributor : Alexis Joly <>
Submitted on : Tuesday, August 11, 2015 - 3:57:20 PM
Last modification on : Thursday, October 10, 2019 - 11:46:03 AM
Long-term archiving on: Thursday, November 12, 2015 - 10:11:39 AM

File

main.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Pierre Letessier, Nicolas Hervé, Alexis Joly, Hakim Nabi, Mathieu Derval, et al.. DigInPix: Visual Named-Entities Identification in Images and Videos. ICMR: International Conference on Multimedia Retrieval, Jun 2015, Shanghai, China. pp.661-664, ⟨10.1145/2671188.2749369⟩. ⟨hal-01182780⟩

Share

Metrics

Record views

490

Files downloads

754