• Publications
  • Influence
Time-aware point-of-interest recommendation
This paper defines a new problem, namely, the time-aware POI recommendation, to recommend POIs for a given user at a specified time in a day, and develops a collaborative recommendation model that is able to incorporate temporal information.
Collision Detection for Deformable Objects
Various approaches based on bounding volume hierarchies, distance fields and spatial partitioning, image‐space techniques and stochastic methods are considered, and applications in cloth modeling and surgical simulation are presented.
Joint-dependent local deformations for hand animation and object grasping
Algorithms and methods are presented for animating the hands of a synthetic actor. The algorithms allow the land to move and grasp objects; they also compute deformations of the hand as it moves. The
A global human walking model with real-time kinematic personification
This paper presents a human walking model built from experimental data based on a wide range of normalized velocities that allows a personification of the walking action in an interactive real-time context in most cases.
Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks
A novel graph-based method to tackle the problem of 3D human body and 3D hand pose estimation from a short sequence of 2D joint detections, where domain knowledge about the human hand (body) configurations is explicitly incorporated into the graph convolutional operations to meet the specific demand of the 3D pose estimation.
Dirichlet free-form deformations and their application to hand simulation
Presents a generalized method for free-form deformations (FFDs) that combines the traditional FFD model with techniques of scattered data interpolation based on Delaunay and Dirichlet/Voronoi
Versatile and efficient techniques for simulating cloth and other deformable objects
The main goal is to be able to simulate any kind of surface without imposing restrictions on shape or geometrical environment, and has enhanced existing algorithms in order to cope with any possible situation.
Efficient Self-Collision Detection on Smoothly Discretized Surface Animations using Geometrical Shape Regularity
We present a new algorithm for detecting self-collisions on highly discretized moving polygonal surfaces. It is based on geometrical shape regularity properties that permit avoiding many useless
Who, where, when and what: discover spatio-temporal topics for twitter users
Experimental results on two real-world datasets show that the proposed model is effective in discovering users' spatial-temporal topics, and outperforms state-of-the-art baselines significantly for the task of location prediction for tweets.
Implementing fast cloth simulation with collision response
Emphasis is put on the efficient implementation of implicit numerical methods with many improvements toward better realism, as well as computation simplicity in the area of cloth simulation.