2026-04-17T01:06:16Zhttps://recercat.cat/oai/request

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

00925njm 22002777a 4500 dc Quattoni, Ariadna Julieta author Ramisa Ayats, Arnau author Madhyastha, Pranava S. author Simó Serra, Edgar author Moreno-Noguer, Francesc author 2016 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) 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 Structured prediction with output embeddings for semantic image annotation