AAAI 2018 accepted papers on 3D vision
21 of the 937 papers accepted at AAAI 2018 (2.2%) are on 3D vision, compared with 0.8% at AAAI 2017. They fall into 4 topics.
See AAAI 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human pose estimation · 7 papers
- Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation (345 citations)
- A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation (45 citations)
- Unsupervised Articulated Skeleton Extraction From Point Set Sequences Captured by a Single Depth Camera (16 citations)
- An Adversarial Hierarchical Hidden Markov Model for Human Pose Modeling and Generation (14 citations)
- Cross-View Person Identification by Matching Human Poses Estimated With Confidence on Each Body Joint (10 citations)
- Human-in-the-Loop SLAM (9 citations)
- PoseHD: Boosting Human Detectors Using Human Pose Information (1 citation)
Depth and stereo · 5 papers
- UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss (548 citations)
- IONet: Learning to Cure the Curse of Drift in Inertial Odometry (390 citations)
- Unsupervised Learning of Geometry From Videos With Edge-Aware Depth-Normal Consistency (161 citations)
- Deep Stereo Matching With Explicit Cost Aggregation Sub-Architecture (60 citations)
- Multispectral Transfer Network: Unsupervised Depth Estimation for All-Day Vision (46 citations)
Face and shape · 5 papers
- Mesh-Based Autoencoders for Localized Deformation Component Analysis (59 citations)
- Learning Adversarial 3D Model Generation With 2D Image Enhancer (18 citations)
- Emphasizing 3D Properties in Recurrent Multi-View Aggregation for 3D Shape Retrieval (10 citations)
- Learning Generative Neural Networks for 3D Colorization (8 citations)
- Self-Reinforced Cascaded Regression for Face Alignment (3 citations)
3D generation · 4 papers
- Memory Fusion Network for Multi-view Sequential Learning (891 citations)
- Learning Interpretable Spatial Operations in a Rich 3D Blocks World (59 citations)
- Group-Pair Convolutional Neural Networks for Multi-View Based 3D Object Retrieval (21 citations)
- Scene-Centric Joint Parsing of Cross-View Videos (14 citations)
