Deep Learning Papers

一、Image Classification(Recognition)

lenet: http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf

alexnet: http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf

overfeat: http://arxiv.org/pdf/1312.6229v4.pdf

vgg: http://arxiv.org/pdf/1409.1556.pdf

googlenet: http://arxiv.org/pdf/1409.4842v1.pdf

二、Image Detection(Segmentation)

overfeat: http://arxiv.org/pdf/1312.6229v4.pdf

dnn: http://papers.nips.cc/paper/5207-deep-neural-networks-for-object-detection.pdf

rcnn: http://arxiv.org/pdf/1311.2524.pdf

spp: http://arxiv.org/pdf/1406.4729v4.pdf

fcn: http://arxiv.org/pdf/1411.4038v2.pdf

fast rcnn:  http://arxiv.org/pdf/1504.08083v1.pdf

三、Image(Visual)  Search

feature learning+hash: http://arxiv.org/pdf/1504.03410v1.pdf

triplet learning: http://arxiv.org/pdf/1412.6622v3.pdf

deep rank: http://arxiv.org/pdf/1404.4661v1.pdf

Visual Search at Pinterest: http://arxiv.org/pdf/1505.07647v1.pdf

四、Image/Video Captioning

Baidu/UCLA: http://arxiv.org/abs/1410.1090
Toronto: http://arxiv.org/abs/1411.2539
Berkeley: http://arxiv.org/abs/1411.4389
Google: http://arxiv.org/abs/1411.4555
Stanford: http://cs.stanford.edu/people/karpathy/deepimagesent/
UML/UT:  http://arxiv.org/abs/1412.4729
Microsoft/CMU:  http://arxiv.org/abs/1411.5654
Microsoft:  http://arxiv.org/abs/1411.4952