International Business Machines Corporation

Kun Yan Yin

He Li

Zhong Fang Yuan

Tong Liu

Hong Bing Zhang

Yuan Lin Yang

Sheng Hui Zhan

Xin Tang

Lu Yu

Wen Jie Wang

Xin Xu

Qi Rong Wang

Xue Ping Liu

Yi Chen Zhong

Hai Ji

Qi Ruan

Yi Ming Wang

Yun Jing Zhao

Yan Feng Han

Jian Hui Chen

Guang Qing Zhong

Guan Chao Li

Yan Bin Hu

Xueliang Zhao

Wan Wan Miao

Shu Zhang

Lei Mei

Ming Jin Chen

Hao Kai Zhang

Xue Ying Zhang

Yuan Yuan Zhang

Yue Liu

Fan Li

Yi Zhi Yao

De Shuo Kong

Yan Nan Hu

Chao Yu

Quan Yuan

Xiao Bo Li

Miao Guo

Yu Luo

Yujia Wang

Teng Sun

Tian Tian Chai

Rui W W Wang

Yu Tao Wu

Gang Ning

Lian Na Wang

Zhe Xue

Jian Hui Bj Chen

Qia Wang

Shun Sp Wen

Xun Wu

Zi Yang Yu

Qi Y Wang

Wang Xiao

Jian Gong Wang

Fei Wang

A system and method for adaptive color assignments to image labels during annotation of datasets includes preparing a dataset for image labeling by an annotator by: leveraging a global color analyzer to perform a global color distribution of a plurality of images to identify one or more overall colors present in the plurality of images, and a local color analyzer to perform a local color distribution for each image to identify one or more colors present in an area of interest of the image, and selecting a plurality of candidate colors to be used as image labels by the annotator, based on an output of the global color analyzer and an output of the local color analyzer.

Selection of image label color based on image understanding

A computer-implemented method includes receiving a viewer request for playing a video summary of a video, wherein the viewer request includes a length of the video summary, generating the video summary of the viewer-requested length comprising a set of frames selected from the video based on audience reviews of the video, and playing a video stream of the video summary.

Generating video summary

A method, a computing system and a computer program product for collecting and labelling images includes capturing a video of an object with a camera. A movement trace of a pointer is recorded that outlines the object while capturing the video of the object. Further included is generating a labeled image based at least on the captured video of the object and the recorded movement trace of the pointer. The labeled image includes the object and a line that surrounds the object.

Image collection and labelling using computer system and analysis

Methods, computer program products, and/or systems are provided that perform the following operations: obtaining video data; dividing the video data into a plurality of video fragments based, at least in part, on page detection; extracting one or more elements from each of the plurality of video fragments; determining element type data for each of the one or more extracted elements; generating element style data for the one or more extracted elements; determining page flow for the plurality of video fragments; and generating one or more pages based, at least in part, on the one or more elements extracted from the plurality of video fragments, the element type data, the element style data, and the page flow.

Cognitive generation of HTML pages based on video content

An example operation may include one or more of generating a three-dimensional (3D) model of an object via execution of a machine learning model on one or more images of the object, capturing a plurality of snapshots of the 3D model of the object at different angles to generate a plurality of snapshot images of the object, fusing a feature into each of the plurality of snapshots to generate a plurality of fused snapshots of the 3D model of the object, and storing the plurality of fused snapshots of the 3D model of the object in memory.

Generating training data through image augmentation

A user input in a source language is received. A set of contextual data is received. The user input is encoded into a user input feature vector. The set of contextual data is encoded into a context feature vector. The user input feature vector and the context feature vector are used to generate a fusion vector. An adaptive neural network is trained to identify a second context feature vector, based on the fusion vector. A second user input in the source language is received for translation into a target language. The adaptive neural network is used to determine, based on the second context feature vector, a second user input feature vector. The second user input feature vector is decoded, based on the source language and the target language, into a target language output. A user is notified of the target language output.

Adaptive language translation using context features

Embodiments of the present invention relate to methods, systems, and computer program products for managing a plurality of live comments. A plurality of live comments is obtained for a video, the plurality of live comments being associated with a plurality of fragments in the video, respectively. A plurality of features are extracted from the plurality of live comments, respectively. A knowledge base is generated for the plurality of live comments based on the plurality of features. With these embodiments, the live comments may be managed in an effective way. Further, the knowledge base may provide answers to a user query.

Live comment management

A cognitive well log analysis using a computer includes receiving, by one or more processors, well log data from a plurality of well logs. One or more processors identify geometric features, specific values, and well attributes from the received well log data and embed the identified features to generate a plurality of intermediate vectors arranged based on a relevance for identifying petrophysical properties. The intermediate vectors are combined to create a fusion vector based on which the one or more processors identify reservoir layers.

Multimodal well log interpretation using deep learning models

A system, method, and computer program product for implementing video action recognition is provided. The method includes receiving a video stream comprising user movement actions. Skeleton points associated with a video representation of a user executing the user movement actions are extracted and categorized with respect to multiple digital levels. Initial visual windows points are generated within video frames and an average movement distance for the group of skeleton points are determined with respect to the video frames. In response, sizes for the visual windows are adjusted and feature vectors are extracted from the group of skeleton points. Point coordinates of the skeleton points are extracted and linked with the feature vectors. A convolutional neural network associated with linking the feature vectors with the point coordinates is generated and the video stream is enabled with respect to video action recognition associated with accurate presentation of the video stream.

Video action recognition and modification

A well log is scanned for one or more dimensions that describe one or more features of a well. Each dimension includes a plurality of values in a numerical format that represents each dimension. A missing value is detected in a first plurality of values of a first dimension of the well log. The first dimension of the well log is transformed, in response to the missing value, into a first image that visually depicts the first dimension including the first plurality of values and the missing value. Based on the first image and based on an image analysis algorithm a second image is created that visually depicts the first plurality of values and includes a found depiction visually depicting a found value in place of the missing value. The found depiction is converted, based on the second image, into a first value in the numerical format.

Image analysis well log data generation

A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

Automatic image annotations

A method, system and computer program product for speech recognition using multiple languages includes receiving, by one or more processors, an input from a user, the input includes a sentence in a first language. The one or more processors translate the sentence to a plurality of languages different than the first language, and create vectors associated with the plurality of languages, each vector includes a representation of the sentence in each of the plurality of languages. The one or more processors calculate eigenvectors for each vector associated with a language in the plurality of languages, and based on the calculated eigenvectors, a score is assigned to each of the plurality of languages according to a relevance for determining a meaning of the sentence.

Cognitive analysis for speech recognition using multi-language vector representations

A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.

Intent recognition model creation from randomized intent vector proximities

A plurality of documents is received. From one or more documents within the plurality, a set of image features is extracted. A document feature repository is generated by storing one or more sets of image features, by document. A document search query is received. The document search query is pre-processed to generate a set of variable document search queries. The document feature repository is searched using the set of variable document search queries. The search results are presented to a user.

Document feature repository management

Embodiments of the present disclosure relate to environment monitoring and associated monitoring device, in which region-level environmental conditions are obtained and are detected by a plurality of sensors installed in a plurality of regions of a space enclosing electronic devices. Additionally, respective region priorities of the plurality of regions are determined based at least in part on the region-level environmental conditions, a region priority indicating a probability of occurrence of a risk event within a corresponding region. Furthermore, a movement path of a moveable monitoring device through the plurality of regions is determined based on the region priorities for detecting device-level environmental conditions associated with the electronic devices, and a moveable monitoring device and a system are disclosed.

Environment monitoring and associated monitoring device

Growing community of inventors

Ningbo, China

Kun Yan Yin