首页 > 代码库 > [3 Jun 2015 ~ 9 Jun 2015] Deep Learning in arxiv

[3 Jun 2015 ~ 9 Jun 2015] Deep Learning in arxiv

arXiv is an e-print service in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance and statistics. There‘ll be lots of papers in advance. Here‘s some recent papers which is important or interesting.


1. Object Detection

even faster than fast rcnn, more end to end for detection, more accurate

You Only Look Once: Unified, Real-Time Object Detection


技术分享

 

Faster R-CNN: Towards Real-Time Object Detection with RegionProposal Network


技术分享


2. cnn itself

more faster over cnn

Fast ConvNets Using Group-wise Brain Damage

技术分享


more fine-grained visual recognition

Bilinear CNN Models for Fine-grained Visual Recognition


技术分享


new post process for classify

Classify Images with Conceptor Network


技术分享


SVM and ELM: Who Wins? Object Recognitionwith Deep Convolutional Features from ImageNet


技术分享

how to combine multiple cnn?

Learning to Select Pre-Trained Deep Representations withBayesian Evidence Framework


技术分享


3. image captioning

attributes/word layer

Image Captioning with an Intermediate Attributes Layer


技术分享

4. OCR

Boosting Optical Character Recognition: ASuper-Resolution Approach


技术分享

5. interesting work

Visual Learning of Arithmetic Operations


技术分享


EventNet: A Large Scale Structured ConceptLibrary for
Complex Event Detection in Video


技术分享

[3 Jun 2015 ~ 9 Jun 2015] Deep Learning in arxiv