• Publications
  • Influence
Residual Attention Network for Image Classification
TLDR
In this work, we propose Residual Attention Network, a convolutional neural network using attention mechanism which can incorporate with state-of-the-art feed forward network architecture in an end-to-end training fashion. Expand
  • 1,317
  • 114
  • PDF
Deep Region and Multi-label Learning for Facial Action Unit Detection
TLDR
We propose Deep Region and Multi-label Learning (DRML), a unified deep network that simultaneously addresses these two problems. Expand
  • 164
  • 46
  • PDF
Randomized, Double-Blind, Placebo-Controlled Phase III Trial of Apatinib in Patients With Chemotherapy-Refractory Advanced or Metastatic Adenocarcinoma of the Stomach or Gastroesophageal Junction.
  • Jin Li, S. Qin, +31 authors H. Yu
  • Medicine
  • Journal of clinical oncology : official journal…
  • 27 September 2016
PURPOSE There is currently no standard treatment strategy for patients with advanced metastatic gastric cancer experiencing progression after two or more lines of chemotherapy. We assessed theExpand
  • 485
  • 35
Ecological Degradation in Protected Areas: The Case of Wolong Nature Reserve for Giant Pandas
It is generally perceived that biodiversity is better protected from human activities after an area is designated as a protected area. However, we found that this common perception was not true inExpand
  • 597
  • 32
  • PDF
Study of a bus-based disruption-tolerant network: mobility modeling and impact on routing
TLDR
We study traces taken from UMass DieselNet, a Disruption-Tolerant Network consisting of WiFi nodes attached to buses. Expand
  • 420
  • 28
  • PDF
Joint patch and multi-label learning for facial action unit detection
TLDR
The face is one of the most powerful channel of nonverbal communication. Expand
  • 136
  • 17
  • PDF
Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification
TLDR
We propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. Expand
  • 246
  • 16
  • PDF
Sketch-based image retrieval via Siamese convolutional neural network
TLDR
Sketch-based image retrieval (SBIR) is a challenging task due to the ambiguity inherent in sketches when compared with photos. Expand
  • 121
  • 16
  • PDF
Chromaticity-based separation of reflection components in a single image
TLDR
We propose a simple and effective method to separate reflections in a color image based on the error analysis of chromaticity and appropriate selection of body color for each pixel. Expand
  • 92
  • 16
  • PDF
TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks
TLDR
We propose a reinforcement learning framework based BS switching operation scheme and a transfer actor-critic algorithm to improve the strategies by taking advantage of learned knowledge from historical periods. Expand
  • 82
  • 16
  • PDF
...
1
2
3
4
5
...