• Publications
  • Influence
Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification
tl;dr
We present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching items can directly influence the computation of each other's representation. Expand
  • 175
  • 50
  • Open Access
A Survey of Model Compression and Acceleration for Deep Neural Networks
tl;dr
Deep convolutional neural networks (CNNs) have recently achieved great success in many visual recognition tasks. Expand
  • 304
  • 16
  • Open Access
Tensor Factorization for Low-Rank Tensor Completion
tl;dr
We propose a novel low-rank tensor factorization method for efficiently solving the 3-way tensor completion problem. Expand
  • 66
  • 13
  • Open Access
EnlightenGAN: Deep Light Enhancement without Paired Supervision
tl;dr
We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Expand
  • 46
  • 13
  • Open Access
Deep Adversarial Subspace Clustering
tl;dr
We propose a novel deep adversarial sub space clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning. Expand
  • 51
  • 10
  • Open Access
Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges
tl;dr
In recent years, deep neural networks (DNNs) have received increased attention, have been applied to different applications, and achieved dramatic accuracy improvements in many tasks. Expand
  • 109
  • 7
  • Open Access
Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks
tl;dr
We propose an efficient online algorithm, called OREO, which jointly optimizes dynamic service caching and task offloading to address a number of key challenges in MEC systems, including service heterogeneity, unknown system dynamics, spatial demand coupling and decentralized coordination. Expand
  • 103
  • 5
  • Open Access
Sentiment Analysis Using Convolutional Neural Network
tl;dr
In this paper, we propose a framework called Word2vec + Convolutional Neural Network (CNN) for the sentiment analysis task. Expand
  • 61
  • 4
Clinical decision support for Alzheimer's disease based on deep learning and brain network
tl;dr
We use Alzheimer's Disease as an example to show advantages of deep learning in diagnosing brain diseases and providing clinical decision support. Expand
  • 30
  • 4
Optimal Repair Layering for Erasure-Coded Data Centers
tl;dr
Repair performance in hierarchical data centers is often bottlenecked by cross-rack network transfer. Expand
  • 31
  • 4
  • Open Access