2026-04-17T23:27:32Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/1050042025-07-17T10:59:37Zcom_2072_1033col_2072_452950

Structured prediction with output embeddings for semantic image annotation Quattoni, Ariadna Julieta Ramisa Ayats, Arnau Madhyastha, Pranava S. Simó Serra, Edgar Moreno-Noguer, Francesc Institut de Robòtica i Informàtica Industrial Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI Àrees temàtiques de la UPC::Informàtica::Automàtica i control Computational linguistics Linguistics Regression analysis Data sparsity Embeddings Feature representation Loglinear model Semantic imatge annotations Structured prediction computer vision natural language processing Classificació INSPEC::Control theory::Predictive control We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model. Peer Reviewed Postprint (author's final draft) 2016 Conference report Quattoni, A.J., Ramisa , A., Madhyastha, P.S., Simo, E., Moreno-Noguer, F. Structured prediction with output embeddings for semantic image annotation. A: Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies. "2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference". San Diego, CA: 2016, p. 552-557. 9781941643914 https://hdl.handle.net/2117/105004 eng https://aclweb.org/anthology/N/N16/N16-1068.pdf http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Open Access Attribution-NonCommercial-NoDerivs 3.0 Spain 6 p. application/pdf