1 |
Result diversification in social image retrieval: a benchmarking framework
|
|
|
|
In: ISSN: 1380-7501 ; EISSN: 1573-7721 ; Multimedia Tools and Applications ; https://hal.archives-ouvertes.fr/hal-01845528 ; Multimedia Tools and Applications, Springer Verlag, 2016, 75 (2), pp.1301-1331. ⟨10.1007/s11042-014-2369-4⟩ (2016)
|
|
BASE
|
|
Show details
|
|
2 |
Placing images with refined language models and similarity search with PCA-reduced VGG features
|
|
|
|
In: 2016 Multimedia Benchmark Workshop, MediaEval 2016 ; https://hal-cea.archives-ouvertes.fr/cea-01843183 ; 2016 Multimedia Benchmark Workshop, MediaEval 2016, Oct 2016, Hilversum, Netherlands (2016)
|
|
BASE
|
|
Show details
|
|
3 |
Handwritten word recognition using Web resources and recurrent neural networks
|
|
|
|
In: International Journal on Document Analysis and Recognition ; https://hal.archives-ouvertes.fr/hal-01845537 ; International Journal on Document Analysis and Recognition, 2015, 18 (4), pp.287-301. ⟨10.1007/s10032-015-0251-1⟩ (2015)
|
|
BASE
|
|
Show details
|
|
4 |
BLSTM-based handwritten text recognition using Web resources
|
|
|
|
In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR) ; https://hal-cea.archives-ouvertes.fr/cea-01841169 ; 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Aug 2015, Tunis, Tunisia. pp.466-470, ⟨10.1109/ICDAR.2015.7333805⟩ (2015)
|
|
BASE
|
|
Show details
|
|
5 |
Benchmarking result diversification in social image retrieval
|
|
|
|
In: 2014 IEEE International Conference on Image Processing (ICIP) ; https://hal-cea.archives-ouvertes.fr/cea-01841686 ; 2014 IEEE International Conference on Image Processing (ICIP), Oct 2014, Paris, France. pp.3072-3076, ⟨10.1109/ICIP.2014.7025621⟩ (2014)
|
|
BASE
|
|
Show details
|
|
6 |
Retrieving Diverse Social Images at MediaEval 2014: Challenge, dataset and evaluation
|
|
|
|
In: Multimedia Benchmark Workshop, MediaEval 2014 ; https://hal-cea.archives-ouvertes.fr/cea-01844453 ; Multimedia Benchmark Workshop, MediaEval 2014, Oct 2014, Barcelona, Spain ; http://ceur-ws.org/Vol-1263/ (2014)
|
|
BASE
|
|
Show details
|
|
7 |
Building specialized bilingual lexicons using large-scale background knowledge
|
|
|
|
In: 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013 ; https://hal-cea.archives-ouvertes.fr/cea-01844695 ; 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Oct 2013, Seattle, United States. pp.479-489 (2013)
|
|
BASE
|
|
Show details
|
|
8 |
CEA LIST's participation at the CLEF CHiC 2013
|
|
|
|
In: 2013 Cross Language Evaluation Forum Conference, CLEF 2013 ; https://hal-cea.archives-ouvertes.fr/cea-01844707 ; 2013 Cross Language Evaluation Forum Conference, CLEF 2013, Sep 2013, Valencia, Spain (2013)
|
|
Abstract:
Conference of 2013 Cross Language Evaluation Forum Conference, CLEF 2013 ; Conference Date: 23 September 2013 Through 26 September 2013; Conference Code:110354 ; International audience ; For our first participation to the CLEF CHiC Lab, we submitted runs to the mul tilingual ad-hoc and multilingual semantic enrichment tasks. Given the strong mul tilingual character of the evaluation corpus, the main objectives of the experiments were to test the efficiency of semantic topic expansion and consolidation based on Explicit Semantic Analysis (ESA) versions in different languages. Another objective was multilingual fusion of results obtained in the different languages of the corpus. ESA was adapted for the 10 languages that are best represented in the Europeana corpus. Wikipedia dumps from March 2012 were used for French and English and from March 2013 for the other languages. One problem that arises when model ing short documents, such as queries, with classical ESA vectors no information is available whether the concept is related to the entire topic only to a part of it. To overcome this problem, two adaptations of ESA (ESA-C) are Wikipedia concepts that are linked to the highest number of concepts from the original topic. In the ad-hoc task, ESA and ESA-C have two roles: to expand the topic with related con cepts and to create consolidated topic models which contain the original topic words along with other related keywords. We submitted both monolingual and multilingual runs without topic expansion and using topic expansion and consolidation with clas sical ESA and ESA-C. The best results are obtained in a multilingual setting with no expansion and ESA-C topic consolidation. For the semantic enrichment task, we propose lists of related Wikipedia concepts using either a monolingual ranking or a voting scheme that surfaces related concepts that appear in the largest number of languages. Here, the best results are obtained in a monolingual ranking configuration that exploits ESA-C.
|
|
Keyword:
[INFO]Computer Science [cs]; Ad hoc tasks; Computational linguistics; Europeana; Expansion; Explicit semantic analysis; Multi-lingual information retrieval; Semantic enrichment; Semantics; Topic model; Topic words; Voting schemes
|
|
URL: https://hal-cea.archives-ouvertes.fr/cea-01844707
|
|
BASE
|
|
Hide details
|
|
9 |
Retrieving diverse social images at MediaEval 2013: Objectives, dataset and evaluation
|
|
|
|
In: 2013 Multimedia Benchmark Workshop, MediaEval 2013 ; https://hal-cea.archives-ouvertes.fr/cea-01844699 ; 2013 Multimedia Benchmark Workshop, MediaEval 2013, Oct 2013, Barcelona, Spain ; http://ceur-ws.org/Vol-1043/ (2013)
|
|
BASE
|
|
Show details
|
|
10 |
CEA LIST's participation at MediaEval 2013 placing task
|
|
|
|
In: 2013 Multimedia Benchmark Workshop, MediaEval 2013 ; https://hal-cea.archives-ouvertes.fr/cea-01844702 ; 2013 Multimedia Benchmark Workshop, MediaEval 2013, Oct 2013, Barcelona, Spain ; http://ceur-ws.org/Vol-1043/ (2013)
|
|
BASE
|
|
Show details
|
|
11 |
Second Language/Bilingualism at An Early Age with Emphasis on Its Impact on Early Socio-Cognitive and Socio-Emotional Development
|
|
|
|
In: http://www.child-encyclopedia.com/Pages/PDF/Nicoladis-Charbonnier-PopescuANGxp.pdf (2006)
|
|
BASE
|
|
Show details
|
|
|
|