Microsoft Technology Licensing, LLC

Other

Microsoft Corporate

Hong-Jiang Zhang

Mingjing Li

Lie Lu

Lei Zhang

Xian-Sheng Hua

Wen-Yin Liu

Yu-Fei Ma

Wei-Ying Ma

Jie Yan

Xiangrong Chen

Yudong Yang

Yuxiao Hu

John Carlton Platt

Tong-Xian Chen

Zheng Chen

Zhong Su

Xingquan Zhu

Yong Rui

Xing Xie

Ji-Rong Wen

Tsuhan Chen

Fu Jie Huang

Tianming Liu

Wei Qi

Guo-Jun Qi

Ye Lu

Yufei Ma

Shipeng Li

Tie-Yan Liu

Hao Jiang

Dong Zhang

Linjun Yang

Hao Fang Wu

Yanfeng Sun

Po Yuan

Yan-Feng Sun

Zhike Kong

Jin-Lin Chen

Jian-Yun Nie

Liu Wenyin

Dalong Jiang

Shuicheng Yan

Lie Gu

Liqun Chen

Ya-Qin Zhang

Yu Chen

Meng Wang

Dong Hui Liu

Bo Feng

Zhen Chen

Yi Zhou

Rong Xiao

Bin Lin

David R Parlin

Ming Li

Gu Xu

Xin Fan

Kuiyuan Yang

Long Zhu

Tong Lin

Ming-Yu Wang

Xinli Zou

Ming-Jing Li

Yongmei Wang

Ma Yong

Ruoyu Roy Wang

Darui Li

Wen-Jun Zhou

Liu Hao

Dongjun Lan

Longbin Chen

Li Ziqing

Yijin Wang

A system and process for video characterization that facilitates video classification and retrieval, as well as motion detection, applications. This involves characterizing a video sequence with a gray scale image having pixel levels that reflect the intensity of motion associated with a corresponding region in the sequence of video frames. The intensity of motion is defined using any of three characterizing processes. Namely, a perceived motion energy spectrum (PMES) characterizing process that represents object-based motion intensity over the sequence of frames, a spatio-temporal entropy (STE) characterizing process that represents the intensity of motion based on color variation at each pixel location, a motion vector angle entropy (MVAE) characterizing process which represents the intensity of motion based on the variation of motion vector angles.

Content-based characterization of video frame sequences

A large web page is analyzed and partitioned into smaller sub-pages so that a user can navigate the web page on a small form factor device. The user can browse the sub-pages to find and read information in the content of the large web page. The partitioning can be performed at a web server, an edge server, at the small form factor device, or can be distributed across one or more such devices. The analysis leverages design habits of a web page author to extract a representation structure of an authored web page. The extracted representation structure includes high level structure using several markup language tag selection rules and low level structure using visual boundary detection in which visual units of the low level structure are provided by clustering markup language tags. User viewing habits can be learned to display favorite parts of a web page.

Small form factor web browsing

A computing device configured to determine that one or more regions of an image are associated with a tag of the image is described herein. The computing device is further configured to determine one or more attribute tags describing at least one of the content or context of the one or more regions. Upon determining the attribute tags, the computing device associates the attribute tags with the tag to enable image searching based on the tag and attribute tags.

Tag association with image regions

Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

Head pose assessment methods and systems

Techniques for construction of a visual codebook are described herein. Feature points may be extracted from large numbers of images. In one example, images providing N feature points may be used to construct a codebook of K words. The centers of each of K clusters of feature points may be initialized. In a looping or iterative manner, an assignment step assigns each feature point to a cluster and an update step locates a center of each cluster. The feature points may be assigned to a cluster based on a lesser of a distance to a center of a previously assigned cluster and a distance to a center derived by operation of an approximate nearest neighbor algorithm having aspects of randomization. The loop terminates when the feature points have sufficiently converged to their respective clusters. Centers of the clusters represent visual words, which may be used to construct the visual codebook.

Robust large-scale visual codebook construction

Technologies for generating a boosted tag ranking for a media instance, the boosted tag ranking based on probabilistic relevance estimation computed by a probabilistic relevance estimator and tag correlation refining performed by a tag correlation refiner. Such boosted tag rankings may be used for search result ranking, tag recommendation, and group recommendation.

Tag ranking

Various embodiments provide methods and systems for streaming data that can facilitate streaming during bandwidth fluctuations in a manner that can enhance the user experience. In one aspect, a forward-shifting technique is utilized to buffer data that is to be streamed, e.g. an enhancement layer in a FGS stream. Various techniques can drop layers actively when bandwidth is constant. The saved bandwidth can then be used to pre-stream enhancement layer portions. In another aspect, a content-aware decision can be made as to how to drop enhancement layers when bandwidth decreases. During periods of decreasing bandwidth, if a video segment does not contain important content, the enhancement layers will be dropped to keep the forward-shifting of the enhancement layer unchanged. If the enhancement layer does contain important content, it will be transmitted later when bandwidth increases.

Streaming methods and systems

Kernelized spatial-contextual image classification is disclosed. One embodiment comprises generating a first spatial-contextual model to represent a first image, the first spatial-contextual model having a plurality of interconnected nodes arranged in a first pattern of connections with each node connected to at least one other node, generating a second spatial-contextual model to represent a second image using the first pattern of connections, and estimating the distance between corresponding nodes in the first spatial-contextual model and the second spatial-contextual model based on a relationship with adjacent connected nodes to determine a distance between the first image and the second image.

Kernelized spatial-contextual image classification

By understanding a website author's intention through an analysis of the function of a website, website content can be adapted for presentation or rendering in a manner that more closely appreciates and respects the function behind the website. Various inventive systems and methods analyze a website's function so that its content can be adapted to different client environments, e.g. devices, network conditions, or user preferences. A novel function-based object model automatically identifies objects associated with a website, and analyzes those objects in terms of their functions. The function-based object model permits consistent, informed decisions to be made in the adaptation process, so that web content is displayed not only in an organized manner, but in a manner that reflects the author's intention.

Function-based object model for use in WebSite adaptation

Systems and methods to generate a motion attention model of a video data sequence are described. In one aspect, a motion saliency map B is generated to precisely indicate motion attention areas for each frame in the video data sequence. The motion saliency maps are each based on intensity I, spatial coherence Cs, and temporal coherence Ct values. These values are extracted from each block or pixel in motion fields that are extracted from the video data sequence. Brightness values of detected motion attention areas in each frame are accumulated to generate, with respect to time, the motion attention model.

Generating a motion attention model

Multi-label active learning may entail training a classifier with a set of training samples having multiple labels per sample. In an example embodiment, a method includes accepting a set of training samples, with the set of training samples having multiple respective samples that are each respectively associated with multiple labels. The set of training samples is analyzed to select a sample-label pair responsive to at least one error parameter. The selected sample-label pair is then submitted to an oracle for labeling.

Multi-label active learning

Disclosed herein are systems methods and devices related to region detection of an image. Detected regions include pixels of a particular one or more colors without requiring faces within the image to be previously detected. Region detection may include receiving information that a flash was used to capture the image or that return light was detected in the image.

Region detection

Correlative multi-label image annotation may entail annotating an image by indicating respective labels for respective concepts. In an example embodiment, a classifier is to annotate an image by implementing a labeling function that maps an input feature space and a label space to a combination feature vector. The combination feature vector models both features of individual ones of the concepts and correlations among the concepts.

Correlative multi-label image annotation

Growing community of inventors

Beijing, China

Hong-Jiang Zhang