Learn More
In recent years, the problem of associating a sentence with an image has gained a lot of attention. This work continues to push the envelope and makes further progress in the performance of image annotation and image search by a sentence tasks. In this work, we are using the Fisher Vector as a sentence representation by pooling the word2vec embedding of(More)
In the traditional object recognition pipeline, descriptors are densely sampled over an image, pooled into a high dimensional non-linear representation and then passed to a classifier. In recent years, Fisher Vectors have proven empirically to be the leading representation for a large variety of applications. The Fisher Vector is typically taken as the(More)
Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences. We demonstrate that RNNs can be effectively used in order to encode sequences and provide effective representations. The methodology we use is based on Fisher Vectors, where the RNNs are the generative probabilistic models and the partial derivatives are(More)
The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting. Most natural language processing applications expect segmented and well-formatted texts as input, which is not available in ASR output. This paper proposes a novel technique of jointly modeling multiple correlated tasks such as(More)
OBJECTIVE To describe physical function outcomes and modes of physical therapy intervention for a cohort of patients with dysvascular lower extremity amputation (LEA) during the prosthetic training phase of rehabilitation. DESIGN A retrospective cohort study. SETTING Physical rehabilitation clinics at a Veterans Affairs medical center and a university(More)
The stream of words produced by Automatic Speech Recognition (ASR) systems is devoid of any punctuations and formatting. Most natural language processing applications usually expect segmented and well-formatted texts as input, which is not available in ASR output. This paper proposes a novel technique of jointly modelling multiple correlated tasks such as(More)
  • 1