• Publications
  • Influence
Semi-Supervised City-Wide Parking Availability Prediction via Hierarchical Recurrent Graph Neural Network
TLDR
We propose Semi-supervised Hierarchical Recurrent Graph Neural Network-X(SHARE-X) for predicting city-wide parking availability, which outperforms eight state-of-the-art baselines. Expand
  • 2
  • 1
Robust attitude controller design for miniature quadrotors
Summary This paper addresses the robust attitude control problem of miniature quadrotors. A simplified linear dynamical model is obtained for each attitude angle, whereas nonlinear dynamics,Expand
  • 42
Robust attitude control for quadrotors with input time delays
TLDR
Robust attitude controller design problem for uncertain quadrotors with input delays. Expand
  • 17
Learning spatial-temporal deformable networks for unconstrained face alignment and tracking in videos
TLDR
We propose a spatial-temporal deformable networks approach to investigate both problems of face alignment in static images and face tracking in videos under unconstrained environments. Expand
  • 3
A modified particle swarm optimization for multimodal multi-objective optimization
TLDR
A modified particle swarm optimization (AMPSO) is proposed to solve the multimodal multi-objective problems. Expand
  • 5
Multi-Modal Transportation Recommendation with Unified Route Representation Learning
TLDR
We study multi-modal transportation recommendation with unified route representation learning by exploiting both spatio-temporal dependencies in transportation networks and the semantic coherence of historical routes. Expand
  • 2
  • PDF
Robust Formation Control for Cooperative Underactuated Quadrotors via Reinforcement Learning.
TLDR
In this article, the model-free robust formation control problem is addressed for cooperative underactuated quadrotors involving unknown nonlinear dynamics and disturbances. Expand
  • 4
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
TLDR
We propose a unified-modal pre-training architecture, namely UNIMO, which can effectively adapt to both single- modal and multi-Modal understanding and generation tasks. Expand
  • 2
  • PDF
...
1
2
3
4
...