International Business Machines Corporation

Xiao Xia Mao

Jie Zhu

Chang Lei

Wen Wen Yang

Wei Jun Zheng

Zhen Hong Ding

Ya Qing Chen

Su Liu

Xin Feng

Chuan Le Zheng

Wenwen Yang

Jian Jun Wang

Min Huang

Qi Rong Wang

Qi Chen

Chao Zheng

Yuan Jin

Yin Qian

Xiao Feng Ji

Jing Xia

Dong Ni

Fang Liang Dong

Yidan Lei

Yi Chen Zhang

Nan Song

Shi Hui Gui

Jialei Ma

Nan Nan Li

A method, computer system, and a computer program product for text corpus concreteness modification are provided. A computer performs natural language processing to determine a concreteness level of a first individual sentence of a text corpus. The computer generates, based on the natural language processing, a proposed change of the individual sentence. The individual sentence with the proposed change includes a modified concreteness level and preserves a general meaning of the individual sentence. The computer transmits the proposed change for presentation of the proposed change.

Automated identification of sentence concreteness and concreteness conversion

A method, computer system, and a computer program product are provided for training a neural network for finding queried videos. Two pairs of video clips and associated text are obtained from a first dataset and a second dataset. The first dataset is used to train two video encoders by providing the video clips to the encoders as input and providing the outputs to a cosine similarity calculator. The second dataset is used to train a multi-mentor paradigm with two mentors. A first mentor and a second mentor are each provided the pair of textual data inputs. The first mentor provides a similarity value comparison, and the second mentor provides a word mover distance. Using the output from the multi-mentor paradigm and the encoders, a contrastive loss is calculated and used to provide contrastive learning of video features by differentiating similarity and dissimilarity of the video clips.

Video retrieval techniques using video contrastive learning

A method, computer program product and computer system to generate a spatial visualization of topics contained in messages data is provided. A processor retrieves message data associated with a user. A processor determines one or more topics represented by the message data. A processor generates a spatial visualization of one or more user interface elements, where the spatial visualization includes a size and a location for the one or more user interface elements. A processor displays one or more user interface elements corresponding to the one or more topics.

Spatial topic representation of messages

This disclosure provides a method for two-dimensional indication in viewing contents. The method comprises in one embodiment displaying a content page in a content display window, wherein at least one of length and width of the content page exceeds the size of the content display window. The method further comprises in one embodiment displaying indicators located at four corners of the content display window, wherein each of the indicators indicates the size of part of the content page that is outside the corresponding corner of the content display window. The method further comprises in one embodiment in response to detecting a user operation that moves the content page relative to the content display window, changing each of the indicators to reflect the current size of part of the content page that is outside the corresponding corner of the content display window.

Two-dimensional indication in contents

The embodiments of the present disclosure disclose a computer-implemented method, an apparatus and a computer program product for automatic control of video play mode. In the method, a prerecorded video of a demonstrator's motions is played while a real-time video of an imitator's motions is being obtained. The imitator's motions in the real-time video are compared with the demonstrator's motions in the prerecorded video. A play mode of the prerecorded video is controlled based on a comparing result.

Viewer feedback based motion video playback

A method, computer system, and computer program product for processing a media content is provided. The present invention may include receiving a request from a user to render a media content, identifying one or more features of the media content, obtaining a profile of the user, and generating a progressive rendering plan for the media content, based on the user's profile and the one or more features of the media content.

Progressive rendering

A method for interactive photography performed by a device, a device for interactive photography, and a computer program product for interactive photography are disclosed. An image is captured by a first device used by a first user to photograph a second user and the image received at a device for interactive photography. An adjustment input from the second user to adjust the image is received. An adjusted image is generated at the device for interactive photography based on the received adjustment input to the received image. The adjusted image is sent to the first device as adjustment information, for use in photographing the second user.

Interactive photography using two or more devices

Methods, computer program products, and systems, for example, for controlling display of an image on a display screen includes, for example, receiving, by one or more processor, data regarding a user selected area relative to a first portion of an image displayed on a display screen to define a second portion of the image, at least a portion of the second portion of the image being outside the first portion of the image displayed on the display screen, and automatically controlling, by the one or more processor, display of the second portion of the image on the display screen based on the user selected area of the image to generally maximize display of the second portion of the image within the display screen.

Display control of an image on a display screen

In an approach for managing a user interface a computer identifies a first user that is utilizing the user interface. The computer determines the identified first user is utilizing an aiming tool. The computer receives an input, the input including at least: an orientation of the aiming tool, wherein the orientation includes at least one of: a direction and a force to be applied upon release of the aiming tool. The computer calculates a trajectory from the aiming tool to a first location on the user interface based on the received input.

Multiple touch selection control

Growing community of inventors

Shanghai, China

Xiao Xia Mao