Semisupervised autoencoder for sentiment analysis
(57) ABSTRACT A method of modelling data, comprising: training an objec tive function of a
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
Deep learning for semantic parsing including semantic utterance classification
BACKGROUND 0001 Conversational machine understanding systems aim to automatically
classify a spoken user utterance into one of a set of predefined semantic categories and …
classify a spoken user utterance into one of a set of predefined semantic categories and …
Generating video summaries for a video using video summary templates
DA Newman, BG Schunck - US Patent 9,792,502, 2017 - Google Patents
Video and corresponding metadata is accessed. Events of interest within the video are
identified based on the corre sponding metadata, and best scenes are identified based on …
identified based on the corre sponding metadata, and best scenes are identified based on …
Activity identification in video
N Hodulik, J Taylor - US Patent App. 14/513,153, 2016 - Google Patents
Video and corresponding metadata is accessed. Events of interest within the video are
identified based on the corresponding metadata, and best scenes are identified based on …
identified based on the corresponding metadata, and best scenes are identified based on …
Video access system and method based on action type detection
BACKGROUND Manual searching through video data can be very time consuming. In its
simplest form, searching involves viewing Video segments and jumping from one segment …
simplest form, searching involves viewing Video segments and jumping from one segment …
Scene and activity identification in video summary generation
DA Newman, A Silver - US Patent 10,074,013, 2018 - Google Patents
Video and corresponding metadata is accessed. Events of interest within the video are
identified based on the corresponding metadata, and best scenes are identified based on …
identified based on the corresponding metadata, and best scenes are identified based on …
Multi-dimensional realization of visual content of an image collection
A computing system for realizing visual content of an image collection executes feature
detection algorithms and semantic reasoning techniques on the images in the collection to …
detection algorithms and semantic reasoning techniques on the images in the collection to …
Multi-dimensional realization of visual content of an image collection
A computing system for realizing visual content of an image collection executes feature
detection algorithms and semantic reasoning techniques on the images in the collection to …
detection algorithms and semantic reasoning techniques on the images in the collection to …
Real-time content immersion system
M Sanders, K Libreri, NG Rasmussen… - US Patent 9,779,538, 2017 - Google Patents
US9779538B2 - Real-time content immersion system - Google Patents US9779538B2 -
Real-time content immersion system - Google Patents Real-time content immersion system …
Real-time content immersion system - Google Patents Real-time content immersion system …
Systems and methods for identifying media portions of interest
SM White, C Beard, I McCarthy… - US Patent 9,626,103, 2017 - Google Patents
Systems and methods for video editing and playback are provided. In one implementation, a
selected portion of a timeline for navigating media content can be repositioned and resized …
selected portion of a timeline for navigating media content can be repositioned and resized …