clarkatsau-CSDN博客

原创 PS: Deformable Part Models are Convolutional Neural Networks_CVPR2015

Deformable Part Models are Convolutional Neural Networks 链接 Ross Girshick, Forrest Iandola, Trevor Darrell, Jitendra Malik IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015这篇文章

2015-12-12 07:58:07 799

原创 CVPR2015 interesting paper(Part 1)

还没仔细看，以下是我感兴趣的文章。从标题和摘要看的。非常想看：4 Expanding Object Detector’s Horizon: Incremental Learning Framework for Object Detection in Videos [full paper] [ext. abstract] Alina Kuznetsova, Sung Ju Hwang, Bodo

2015-12-01 23:01:38 1872

原创 PS: DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers__ICCV2015

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool link精华尽在于此。 We generate hypotheses in a sliding-wi

2015-11-30 13:19:47 894

原创 PS: Deep Neural Networks Are Easily Fooled___CVPR2015

Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images full paper Anh Nguyen, Jason Yosinski, Jeff Clune这篇paper的idea我很喜欢，不久的将来基于这篇paper还会产生一些工作。这篇文章针对的问题是这样的。虽然现

2015-11-30 12:04:43 778

原创 PS:mproving Object Detection With Deep Convolutional Networks via Bayesian Optimization..___CVPR2015

Improving Object Detection With Deep Convolutional Networks via Bayesian Optimization and Structured Prediction [full paper] (http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zhang_Impr

2015-11-30 11:49:11 636

原创 PS:Hypercolumns for Object Segmentation and Fine-Grained Localization__CVPR2015

Hypercolumns for Object Segmentation and Fine-Grained Localization [full paper] (http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Hariharan_Hypercolumns_for_Object_2015_CVPR_paper.pdf)

2015-11-30 11:42:43 1434

原创 PS:Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution...___CVPR2015

Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution, Multiple Instance Learning, and Sliding Window Detection [full paper] (http://www.cv-foundation.org/openaccess/content_c

2015-11-30 11:33:09 435

原创 PS: Going Deeper With Convolutions___CVPR2015

Going Deeper With Convolutions [full paper] (http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf) Christian Szegedy, Wei Liu, Yangqing Jia,

2015-11-29 20:59:18 410

原创 PS: Unsupervised Learning of Visual Representations Using Videos___ICCV2015

Unsupervised Learning of Visual Representations Using Videos Xiaolong Wang, Abhinav Gupta 文章链接目前成功的CNN均使用大量标记的图片序列来进行训练，大量的标注对。本文采用了一种无监督方法，使用了无标记的视频作为训练数据。论文采用通过对视频tracking得到的标记作为监督标记。

2015-11-26 20:15:49 627

原创 PS: Understanding deep features with computer-generated imagery___ICCV2015

Understanding Deep Features With Computer-Generated Imagery Mathieu Aubry, Bryan C. Russellhttp://imagine.enpc.fr/~aubrym/projects/features_analysis/texts/understanding_deep_features_with_CG.pdf

2015-11-26 19:56:54 720

原创学海明码，就来看看海明的演讲吧--你和你的研究(You and Your Research)

英文版，请直接点这里：http://www.cs.virginia.edu/~robins/YouAndYourResearch.html看翻译的，请点击这里：http://www.rangang.com/archives/9 你和你的研究Ihttp://www.rangang.com/archives/13 你和你的研究IIhttp://www.rangang.c

2015-09-21 15:05:29 905

clarkatsau的博客