NIPS Proceedingsβ

Jiajun Wu

14 Papers

  • Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations (2019)
  • Visual Concept-Metaconcept Learning (2019)
  • 3D-Aware Scene Manipulation via Inverse Graphics (2018)
  • Learning to Exploit Stability for 3D Scene Parsing (2018)
  • Learning to Reconstruct Shapes from Unseen Classes (2018)
  • Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (2018)
  • Visual Object Networks: Image Generation with Disentangled 3D Representations (2018)
  • Learning to See Physics via Visual De-animation (2017)
  • MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017)
  • Self-Supervised Intrinsic Image Decomposition (2017)
  • Shape and Material from Sound (2017)
  • Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (2016)
  • Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks (2016)
  • Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning (2015)