[Tue, 11 Aug 2015 ~ Mon, 17 Aug 2015] Deep Learning in arxiv

Image Representations and New Domains inNeural Image Captioning

we find that a state-of-theart neuralcaptioning algorithm is able to produce quality captions even when providedwith surprisingly poor image representations

Deep Boosting: Joint Feature Selection andAnalysis Dictionary Learning in Hierarchy

This work investigates how the traditionalimage classification pipelines can be extended into a deep architecture,inspired by recent successes of deep neural networks

Digging Deep into the layers of CNNs: InSearch of How CNNs Achieve View Invariance

watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">

A practical guide to CNNs and FisherVectors for image instance retrieval

CNN robust to scale but not robust torotation (unless your training data contains rotation samples)

FV + CNN maybe better

Submodular Reranking with Multiple FeatureModalities for Image Retrieval

Our submodularreranking framework can be easily generalized to any generic reranking problemsfor real-time search engines

Benchmarking of LSTM Networks