Abstract: A system and method for natural language processing for document sequences comprises a computing device configured to train a neural network as a function of a corpus of documents, wherein training comprises receiving the corpus of documents, identifying significant terms, and tuning, as a function of the corpus of documents, the neural network to generate a plurality of vectors for each significant term of the plurality of significant terms, a vector in a vector space representing semantic relationships between the significant terms and semantic units in the corpus of documents, receive a current document sequence including a plurality of documents in a sequential order, map a plurality of mapped terms of the plurality of significant terms to the plurality of documents as a function of the neural network and the plurality of vectors, and generate a plurality of timelines as a function of the sequential order and the mapped terms.

Abstract: A system and method for natural language processing for document sequences comprises a computing device configured to train a neural network as a function of a corpus of documents, wherein training comprises receiving the corpus of documents, identifying significant terms, and tuning, as a function of the corpus of documents, the neural network to generate a plurality of vectors for each significant term of the plurality of significant terms, a vector in a vector space representing semantic relationships between the significant terms and semantic units in the corpus of documents, receive a current document sequence including a plurality of documents in a sequential order, map a plurality of mapped terms of the plurality of significant terms to the plurality of documents as a function of the neural network and the plurality of vectors, and generate a plurality of timelines as a function of the sequential order and the mapped terms.

Abstract: A method, a system, and a computer readable recording medium are disclosed for performing object recognition. The method includes receiving image data from an image; performing a multilayer feature extraction on the image data; generating current feature maps from the multilayer feature extraction; generating a region of proposal network map from at least the current feature maps, the region of proposal network map having one or more regions of interest; inputting previously generated feature maps and the current feature maps into a classifier with the region of proposed network map; and classifying the one or more regions of interest in the region of proposal network map.

Abstract: A method, a system, and a computer readable recording medium are disclosed for performing object recognition. The method includes receiving image data from an image; performing a multilayer feature extraction on the image data; generating current feature maps from the multilayer feature extraction; generating a region of proposal network map from at least the current feature maps, the region of proposal network map having one or more regions of interest; inputting previously generated feature maps and the current feature maps into a classifier with the region of proposed network map; and classifying the one or more regions of interest in the region of proposal network map.

Abstract: A system and method that identifies an object and a viewpoint from an image with a probability that satisfies a predefined criterion is described. An active view planning application receives a first image, performs recognition on the first image to determine an object, a viewpoint and a probability of recognition, determines a first expected gain in the probability of recognition when a first action is taken and a second expected gain in the probability of recognition when a second action is taken, and identifies a next action from the first action and the second action based on an increase in expected gains.

Abstract: The disclosure includes a system and method for identifying an object and a viewpoint from an image with a probability that satisfies a predefined criterion based on deep network learning. An active view planning application receives a first image, performs recognition on the first image to determine an object, a viewpoint and a probability of recognition, determines a first expected gain in the probability of recognition when a first action is taken and a second expected gain in the probability of recognition when a second action is taken, and identifies a next action from the first action and the second action based on an increase in expected gains.