Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)
Network embedding has been increasingly employed in network analysis as it can learn node representations that encode the network structure resulting from node interactions. In this paper, besides the network structure, the interaction content within which each interaction arises is also embedded because it reveals interaction preferences of the two nodes involved, and interaction preferences are essential characteristics that nodes expose in the network environment. Specifically, we propose interaction content aware network embedding (ICANE) via co-embedding of nodes and edges. The embedding of edges is to learn edge representations that preserve the interaction content. Then the interaction content can be incorporated into node representations through edge representations. Comprehensive evaluation demonstrates ICANE outperforms five recent network embedding models in applications including visualization, link prediction and classification.
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Bilge Acun, Benjamin Lee, Fiodar Kazhamiaka, Kiwan Maeng, Manoj Chakkaravarthy, Udit Gupta, David Brooks, Carole-Jean Wu
Harjasleen Malvai, Lefteris Kokoris-Kogias, Alberto Sonnino, Esha Ghosh, Ercan Ozturk, Kevin Lewi, Sean Lawlor