21 citations · 22 across the 6 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022
Compositional Scene Representation Learning via Reconstruction: A Survey
Jinyang Yuan, Tonglin Chen, Bin Li +1
Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is th…
cs.LG2021★ 1 cited
Knowledge-Guided Object Discovery with Acquired Deep Impressions
Jinyang Yuan, Bin Li, Xiangyang Xue
We present a framework called Acquired Deep Impressions (ADI) which continuously learns knowledge of objects as "impressions" for compositional scene understanding. In this framewo…
cs.LG2019
Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping
Jinyang Yuan, Bin Li, Xiangyang Xue
Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scene…