Primitive-based 3D Human-Object Interaction Modelling and Programming
Paper • 2312.10714 • Published
TrackTrack
classroom
AI & ML interests
None defined yet.
Recent Activity
View all activity
qq456cvb
authored 20
papers 8 days ago
Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases
Paper • 2310.04189 • Published
ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly
Paper • 2409.16451 • Published
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
Paper • 2401.08140 • Published
Skeleton Merger: an Unsupervised Aligned Keypoint Detector
Paper • 2103.10814 • Published
CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame
Paper • 2303.03101 • Published
Human Correspondence Consensus for 3D Object Semantic Understanding
Paper • 1912.12577 • Published
Rodrigues Network for Learning Robot Actions
Paper • 2506.02618 • Published
Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
Paper • 2111.10817 • Published
Combinational Q-Learning for Dou Di Zhu
Paper • 1901.08925 • Published
Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
Paper • 2311.02787 • Published
DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration
Paper • 2604.27367 • Published
PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Paper • 2102.12093 • Published
Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
Paper • 2011.12001 • Published
UKPGAN: A General Self-Supervised Keypoint Detector
Paper • 2011.11974 • Published
UniPose9D: Universal Category-Agnostic Object Pose Estimation
Paper • 2607.09985 • Published
CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation
Paper • 2211.13398 • Published
CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild
Paper • 2203.03089 • Published
KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Paper • 2002.12687 • Published
Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization
Paper • 2408.01437 • Published • 2