• Publications
  • Influence
Heterogeneous Network Embedding via Deep Architectures
Data embedding is used in many machine learning applications to create low-dimensional feature representations, which preserves the structure of data points in their original space. In this paper, weExpand
  • 357
  • 30
  • Open Access
Differential Recurrent Neural Networks for Action Recognition
The long short-term memory (LSTM) neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long inputExpand
  • 286
  • 21
  • Open Access
Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
  • Guo-Jun Qi
  • Computer Science
  • International Journal of Computer Vision
  • 23 January 2017
In this paper, we present the Lipschitz regularization theory and algorithms for a novel Loss-Sensitive Generative Adversarial Network (LS-GAN). Specifically, it trains a loss function to distinguishExpand
  • 175
  • 20
  • Open Access
Correlative multi-label video annotation
Automatically annotating concepts for video is a key to semantic-level video browsing, search and navigation. The research on this topic evolved through two paradigms. The first paradigm used binaryExpand
  • 441
  • 13
  • Open Access
Joint multi-label multi-instance learning for image classification
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both a multi-labelExpand
  • 233
  • 13
  • Open Access
Unified Video Annotation via Multigraph Learning
Learning-based video annotation is a promising approach to facilitating video retrieval and it can avoid the intensive labor costs of pure manual annotation. But it frequently encounters severalExpand
  • 443
  • 12
  • Open Access
AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data
The success of deep neural networks often relies on a large amount of labeled examples, which can be difficult to obtain in many real scenarios. To address this challenge, unsupervised methods areExpand
  • 52
  • 11
  • Open Access
Two-Dimensional Active Learning for image classification
In this paper, we propose a two-dimensional active learning scheme and show its application in image classification. Traditional active learning methods select samples only along the sampleExpand
  • 136
  • 9
  • Open Access
Stock Price Prediction via Discovering Multi-Frequency Trading Patterns
Stock prices are formed based on short and/or long-term commercial and trading activities that reflect different frequencies of trading patterns. However, these patterns are often elusive as they areExpand
  • 69
  • 9
  • Open Access
Supervised Quantization for Similarity Search
In this paper, we address the problem of searching for semantically similar images from a large database. We present a compact coding approach, supervised quantization. Our approach simultaneouslyExpand
  • 56
  • 9
  • Open Access