@InProceedings{Schirmer:2021:SeGrAt,
               author = "Schirmer, Luiz",
          affiliation = "PUC-Rio",
                title = "SGAT: Semantic Graph Attention for 3D human pose estimation",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Graph Neural Networks, Pose estimation, Animation, Motion 
                         Capture.",
             abstract = "We propose a novel gating mechanism applied to Semantic Graph 
                         Convolutions for 3D applications, named Semantic Graph Attention. 
                         Semantic Graph Convolutions learn to capture semantic information 
                         such as local and global node relationships, not explicitly 
                         represented in graphs. We improve their performance by proposing 
                         an attention block to explore channel-wise inter-dependencies. The 
                         proposed method performs the unprojection of the points 2d (image) 
                         in their 3D version (3d scene). We use it to estimate 3d human 
                         pose from 2d images. Both 2D and 3D human poses can be represented 
                         as structured graphs, and we explore their particularities in this 
                         context. The attention layer improves skeleton estimation accuracy 
                         using 58\% fewer parameters than state-of-the-art.",
  conference-location = "Gramado, RS, Brazil (virtual)",
      conference-year = "18-22 Oct. 2021",
                  doi = "10.1109/SIBGRAPI54419.2021.00042",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00042",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/45CUNP8",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CUNP8",
           targetfile = "Sibgrapi21_final.pdf",
        urlaccessdate = "2024, May 06"
}