• Publications
  • Influence
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation
TLDR
In this paper, we propose to model structured segmentation data with graphs and apply attentive graph reasoning to propagate label information from support data to query data. Expand
  • 37
  • 10
  • PDF
Benchmarking Quasi-Steady State Cascading Outage Analysis Methodologies
TLDR
We benchmark the performance of several widely used QSS cascading outage methodologies. Expand
  • 31
  • 2
  • PDF
Multiobjective ResNet pruning by means of EMOAs for remote sensing scene classification
TLDR
We propose a random filter pruning method by means of evolutionary multiobjective optimization algorithms to accelerate the Siamese ResNet-50 for remote sensing scene classification. Expand
  • 5
  • 1
Real-Time Visual Tracking with Compact Shape and Color Feature
The colour feature is often used in the object tracking. The tracking methods extract the colour features of the object and the background, and distinguish them by the classifier. However, theseExpand
  • 13
Diverse sample generation with multi-branch conditional generative adversarial network for remote sensing objects detection
TLDR
A multi-branch conditional generative adversarial network is proposed to augment data for object detection in optical remote sensing images, which is the first GANs-based data augmentation framework proposed for this topic. Expand
  • 6
Efficient and Robust Dynamic Simulation of Power Systems With Holomorphic Embedding
TLDR
This paper proposes a novel dynamic simulation approach based on holomorphic embedding. Expand
  • 9
  • PDF
Structure-aware person search with self-attention and online instance aggregation matching
TLDR
This paper tackles the task of person search, which is a new challenging computer version task in real-world scenarios. Expand
  • 3
A Siamese Pedestrian Alignment Network for Person Re-identification
TLDR
We propose siamese pedestrian alignment networks (SPAN) for person re-identification. Expand
  • 4
An Online Search Method for Representative Risky Fault Chains Based on Reinforcement Learning and Knowledge Transfer
TLDR
An online search method for representative risky fault chains based on reinforcement learning and knowledge transfer based on Markov Decision Process and Q-learning. Expand
  • 5
  • PDF