Adobe, Inc.

Microsoft Technology Licensing, LLC

Xerox Corporation

Quanzeng You

Hailin Jin

Zhaowen Wang

Chen Fang

Zhengyou Zhang

Hao Jiang

Sumit Bhatia

The discussion relates to 4D tracking. One example can utilize multiple 3D cameras positioned relative to an environment to sense depth data of the environment from different viewpoints over time. The example can process the depth data to construct 3D solid volume representations of the environment, select subjects from the 3D solid volume representations, and recognize actions of the selected subjects.

4D tracking utilizing depth data from multiple 3D cameras

Techniques for image captioning with weak supervision are described herein. In implementations, weak supervision data regarding a target image is obtained and utilized to provide detail information that supplements global image concepts derived for image captioning. Weak supervision data refers to noisy data that is not closely curated and may include errors. Given a target image, weak supervision data for visually similar images may be collected from sources of weakly annotated images, such as online social networks. Generally, images posted online include 'weak' annotations in the form of tags, titles, labels, and short descriptions added by users. Weak supervision data for the target image is generated by extracting keywords for visually similar images discovered in the different sources. The keywords included in the weak supervision data are then employed to modulate weights applied for probabilistic classifications during image captioning analysis.

Image captioning with weak supervision

Techniques for image captioning with word vector representations are described. In implementations, instead of outputting results of caption analysis directly, the framework is adapted to output points in a semantic word vector space. These word vector representations reflect distance values in the context of the semantic word vector space. In this approach, words are mapped into a vector space and the results of caption analysis are expressed as points in the vector space that capture semantics between words. In the vector space, similar concepts with have small distance values. The word vectors are not tied to particular words or a single dictionary. A post-processing step is employed to map the points to words and convert the word vector representations to captions. Accordingly, conversion is delayed to a later stage in the process.

Semantic natural language vector space

Methods and systems provide electronic instructions to a non-transitory electronic storage hardware device to record images uploaded by a user over a computerized network to a social networking site, and to record categories of network site locations to which the images are uploaded by the user. These methods and systems also provide electronic instructions to a computerized electronic image processor hardware device to analyze features within the images to identify content of each of the images, and to determine the user characteristics based on the categories of network site locations to which the images are uploaded by the user and on the content of the images uploaded by the user. Also, such methods and systems provide electronic instructions to the computerized electronic image processor hardware device to output the user characteristics on a graphic user interface hardware device.

Growing community of inventors

Rochester, NY, United States of America

Quanzeng You