• Publications
  • Influence
Semantic Graph Construction for Weakly-Supervised Image Parsing
TLDR
We investigate weakly-supervised image parsing, i.e., how to propagate class labels from images to regions given an affinity graph of regions. Expand
  • 14
  • 2
  • PDF
Weakly-Supervised Image Parsing via Constructing Semantic Graphs and Hypergraphs
TLDR
We address the problem of weakly-supervised image parsing, whose aim is to automatically determine the class labels of image regions given image-level labels only. Expand
  • 12
  • 2
  • PDF
Learning to Update for Object Tracking
TLDR
We design the learned updater based on recurrent neural networks (RNNs) and demonstrate its application in a template-based tracker and a correlation filter-based Tracker. Expand
  • 3
  • 2
Cross-View Feature Learning for Scalable Social Image Analysis
TLDR
We propose a cross-view feature learning (CVFL) framework to handle the problem of social image analysis effectively and efficiently. Expand
  • 14
  • 1
Detect or Track: Towards Cost-Effective Video Object Detection/Tracking
TLDR
This work was done when Hao Luo was an intern at Microsoft Research Asia. Expand
  • 15
  • PDF
Learning to Update for Object Tracking With Recurrent Meta-Learner
TLDR
We design the learned updater based on recurrent neural networks and demonstrate its application in a template-based tracker and a correlation filter-based Tracker. Expand
  • 10
  • PDF
Graph-based multimodal semi-supervised image classification
TLDR
We investigate an image classification task where training images come along with tags, but only a subset being labeled, and the goal is to predict the class label of test images without tags. Expand
  • 10
  • PDF
Multimodal semi-supervised image classification by combining tag refinement, graph-based learning and support vector regression
TLDR
We investigate an image classification task where the training images come along with tags, but only a subset being labeled, and the goal is to predict the class label of test images without tags. Expand
  • 2
  • PDF
Joint Time-Frequency and Time Domain Learning for Speech Enhancement
TLDR
In this paper, we present a cross-domain framework named TFTNet, which takes time-frequency spectrogram as input and produces time-domain waveform as output. Expand
  • 1
  • PDF
Construction and evaluation of post-evaluation index system on loan projects of international financial organizations
Aiming at loan projects of international financial organizations, this paper put forward the content and framework of post-evaluation. Set the Yellow River flood control and disaster reduction systemExpand