• Publications
  • Influence
Deep Residual Learning for Image Recognition
TLDR
We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
We introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. Expand
Identity Mappings in Deep Residual Networks
TLDR
We analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. Expand
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TLDR
We study rectifier neural networks for image classification from two aspects. Expand
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
TLDR
We equip the CNNs with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement. Expand
Face Alignment at 3000 FPS via Regressing Local Binary Features
TLDR
This paper presents a highly efficient, very accurate regression approach for face alignment. Expand
Joint Cascade Face Detection and Alignment
TLDR
We present a new state-of-the-art approach for face detection that achieves the best accuracy on challenging datasets, where all existing solutions are either inaccurate or too slow. Expand
Instance-Sensitive Fully Convolutional Networks
TLDR
Fully convolutional networks (FCNs) have been proven very successful for semantic segmentation, but the FCN outputs are unaware of object instances. Expand
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
TLDR
We equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. Expand
Deep Residual Learning for Image Recognition Supplementary Materials
In this section we introduce our detection method based on the baseline Faster R-CNN [6] system. The models are initialized by the ImageNet classification models, and then fine-tuned on the objectExpand
...
1
2
...