ArXiv is a e-print service in the fields of physics, mathematics, Computer science, quantitative biology, quantitative fi Nance and statistics. There ' ll is lots of papers in advance. Here's some recent papers which is important or interesting.
1. Object Detectioneven faster than fast rcnn, more end-to-end for detection, more accurate
You have look once:unified, real-time Object Detection
Faster r-cnn:towards Real-time Object Detection with Regionproposal Network
2. CNN Itselfmore faster over CNN
Fast convnets Using group-wise Brain Damage
More fine-grained visual recognition
Bilinear CNN Models for fine-grained Visual recognition
New post process for classify
Classify Images with Conceptor Network
SVM and elm:who Wins? Object Recognitionwith deep convolutional Features from ImageNet
How to combine multiple CNN?
Learning to Select pre-trained deep representations Withbayesian Evidence Framework
3. Image Captioningattributes/word Layer
Image captioning with an intermediate Attributes Layer
4. OCR
Boosting Optical Character recognition:asuper-resolution approach
5. Interesting work
Visual Learning of Arithmetic Operations
EVENTNET:A Large scale Structured conceptlibrary for
Complex Event Detection in Video
[3 June ~ 9 June 2015] Deep Learning in arxiv