Identifying words to accurately describe, with a range of specificity, an image is provided. A vector space corresponding to the image is generated using a convolutional neural network to extract a hierarchy of features ranging from broad to specific from the image. Closest vocabulary ranging from broad to specific are identified for the image using Huffman coding on the vector space. Accurate words ranging from broad to specific are identified that describe the image based on vocabulary output of the Huffman coding on the vector space. The accurate words ranging from broad to specific describing the image are output.

A real-time end-to-end system for capturing ink strokes written with ordinary pen and paper using a commodity video camera is described. Compare to traditional camera-based approaches, which typically separate out the pen tip localization and pen up/down motion detection, described is a unified approach that integrates these two steps using a deep neural network. Furthermore, the described system does not require manual initialization to locate the pen tip. A preliminary evaluation demonstrates the effectiveness of the described system on handwriting recognition for English and Japanese phrases.

A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.

An electronic whiteboard system and an operation method thereof are provided. The electronic whiteboard system includes an electronic device and a display. The electronic device includes a whiteboard module. The whiteboard module is configured to perform a writing operation. The whiteboard module is configured to generate a writing data according to a writing event, and recognize the writing data to determine a text information, and determine a corresponding computer text according to the text information. The display is connected to the whiteboard module. The display is configured to display the corresponding computer text or a preset writing picture according to the corresponding computer text.

A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.

The present specification discloses a model training method and apparatus, a service processing method and apparatus, a storage medium, and a device. The model training method includes: obtaining a historical conversation; determining a target conversation content from the historical conversation; inputting the historical conversation into a to-be-trained feature extraction model for the feature extraction model to determine a conversation content feature corresponding to the target conversation content as a first feature based on a conversation content other than the target conversation content in the historical conversation, and to determine a conversation content feature corresponding to the target conversation content as a second feature based on the target conversation content; and training the feature extraction model with an optimization goal of reducing a deviation between the first feature and the second feature, where the trained feature extraction model is used to determine an output conversation content feature corresponding to each input conversation content, and send the output conversation content feature for a receiving end to perform service processing based on the received output conversation content feature.

A system and method that transforms data formats into contour metrics and further transforms each contour of that mapping into contours pattern metric sets so that each metric created has a representation of one level of contour presentation, at each iteration of the learning contour identification system defined herein. This transformation of data instance to contour metrics permits a user to take relevant data of a data set, as determined by a learning contour identification system, to machines of other types and function, for the purpose of further analysis of the patterns found and labeled by said system. The invention performs with data format representations, not limited to, signals, images, or waveform embodiments so as to identify, track, or detect patterns of, amplitudes, frequencies, phases, and density functions, within the data case and then by way of using combinations of statistical, feedback adaptive, classification, training algorithm metrics stored in hardware, identifies patterns in past data cases that repeat in future, or present data cases, so that high-percentage labeling and identification is a achieved.

A system for indexing animated content receives detections extracted from a media file, where each one of the detections includes an image extracted from a corresponding frame of the media file that corresponds to a detected instance of an animated character. The system determines, for each of the received detections, an embedding defining a set of characteristics for the detected instance. The embedding associated with each detection is provided to a grouping engine that is configured to dynamically configure at least one grouping parameter based on a total number of the detections received. The grouping engine is also configured to sort the detections into groups using the grouping parameter and the embedding for each detection. A character ID is assigned to each one of the groups of detections, and the system indexes the groups of detections in a database in association with the character ID assigned to each group.