Dolby Laboratories Licensing Corporation

Facebook, Inc.

Meta Platforms, Inc.

Thomson Licensing

Zhen Li

Alexandros Michael Tourapis

Guan-Ming Su

Xiaoan Lu

Walter Christian Gish

Christopher J Vogt

Li Ju

Yuan Liang

David Ruhoff

Hyung-Suk Kim

Eric Hsin-Chun Huang

Donald Pian

Cassidy Jake Beeve-Morris

Chang Su

Yun Liu

Sheng Qu

Kelly Leanne MacLean

Rachel Barrie Tucker

Brendan M Sullivan

Hongji Yang

Sylvain Marc Robert Friquet

Ritika Prasad

Alkarim Nasser

Nikila Srinivasan Sarang

Adeel Abbas

Christina Gomila

A social networking system allows users to create and join groups in the social networking system, in which each group is associated with one or more interests shared by members of the group. To select content for presentation to a viewing user of the social networking system who is a member of a group, the social networking system may determine one or more topics associated with the group based at least in part on a classification system and on information associated with objects maintained in the social networking system that are similar to the group. The topic(s) associated with the group also may be determined based on information associated with the group, with members of the group, and/or with objects associated with the group. The social networking system may then select one or more content items associated with the topic(s) for presentation to the viewing user via a group page.

Selecting content for presentation to a user of a social networking system based on a topic associated with a group of which the user is a member

Systems, methods, and non-transitory computer readable media configured to receive an initial targeting for an advertisement. The advertisement can promote a group of a social networking system. A refined targeting for the advertisement can be generated. The advertisement based on the refined targeting can be delivered.

Systems and methods for promoting groups

An online system receives an advertisement request ('ad request') including an advertisement from a user and allows the user to create an alternative advertisement for the ad request comprising images presented in an order specified by the user. The online system may identify images from video data included in the ad request or from additional content associated with an object associated with the ad request. Based on selections of identified images by the user and an order in which to present the selected images from the user, the online system generates the alternative advertisement and associates the alternative advertisement with the ad request. One or more criteria are associated with the alternative advertisement, and the online system communicates the alternative advertisement to client devices having characteristics satisfying the criteria rather than video data in the advertisement.

Creating a sequence of images for presentation in a content item presented by an online system from content associated with the content item

In layered Visual Dynamic range (VDR) coding, inter-layer prediction requires several color-format transformations between the input VDR and Standard Dynamic Range (SDR) signals. Coding and decoding architectures are presented wherein inter-layer prediction is performed in the SDR-based color format, thus reducing computational complexity in both the encoder and the decoder, without compromising coding efficiency or coding quality.

Efficient architecture for layered VDR coding

Enhancing image dynamic range is described. An input video signal that is represented in a first color space with a first color gamut, which is related to a first dynamic range, is converted to a video signal that is represented in a second color space with a second color gamut. The second color space is associated with a second dynamic range. At least two (e.g., three) color-related components of the converted video signal are mapped over the second dynamic range.

Extending image dynamic range

A first image stream has a first dynamic range and a first color space. First and the second image streams are received in a layered codec. The second image stream has a second dynamic range, which is higher than the first dynamic range. The first image stream is in the codec's base layer; the second image stream is in its enhancement layer. The first image stream is encoded to obtain an encoded image stream, which is decoded to obtain a decoded image stream. The decoded image stream is converted from the first non-linear or linear color space to a second, different color space to obtain a color converted image stream. A higher dynamic range image representation of the color converted image stream is generated to obtain a transformed image stream. Inverse tone mapping parameters are generated based on the transformed image stream and the second image stream.

Compatible compression of high dynamic range, visual dynamic range, and wide color gamut video

Adaptive motion information cost estimation is achieved in processing video information. A transmission cost is estimated that is associated with encoding a motion vector difference (mvd) in motion vectors that describe a motion characteristic of the video information. The mvd is encoded based on minimizing a rate estimation mismatch associated with the motion vectors. The encoding step includes computing a bit count associated with the mvd using CABAC. A value is indexed that corresponds to the cost from one or more entries in the lookup table. The cost relates to context or content characteristics associated with the video information. The lookup table is adaptively updated based on a change in the contextual information or content characteristics. The value is dynamically adjustable based on the change.

Adaptive motion information cost estimation with dynamic look-up table updating

Assessing a visual quality characteristic includes accessing and processing at least a first image or video signal and a second image or video signal and processing the accessed images or video signals. Based at least in part on processing the accessed images or video signals, a difference is measured between the processed at least first and second images or video signals. The visual quality characteristic relates to a magnitude of the measured difference between the processed at least first and second images or video signals. The at least first and second images or video signals include a high or visual dynamic range and/or a wide color gamut. The visual quality characteristic is assessed based, at least in part, on the measured difference.

Quality assessment of high dynamic range, visual dynamic range and wide color gamut image and video

A first video signal is accessed, and represented in a first color space with a first color gamut, related to a first dynamic range. A second video signal is accessed, and represented in a second color space of a second color gamut, related to a second dynamic range. The first accessed video signal is converted to a video signal represented in the second color space. At least two color-related components of the converted video signal are mapped over the second dynamic range. The mapped video signal and the second accessed video signal are processed. Based on the processing, a difference is measured between the processed first and second video signals. A visual quality characteristic relates to a magnitude of the measured difference between the processed first and second video signals. The visual quality characteristic is assessed based, at least in part, on the measurement of the difference.

Quality assessment for images that have extended dynamic ranges or wide color gamuts

A value of one or more Lagrangian multipliers is adaptively estimate and update based, at least in part, on the video source statistics or dynamic programming. Methods, techniques, and systems involve determining a first Lagrangian multiplier with a video encoder, and updating a second Lagrangian multiplier with the first Lagrangian multiplier. The system can include a Lagrangian multiplier Estimation Module that estimates the Lagrangian multiplier, and a Lagrangian multiplier Update Module that updates the current Lagrangian multiplier using the estimated Lagrangian multiplier. The Online Lagrangian Multiplier Estimation Module may function with Rate Distortion Slope Estimation with Rate Distortion Optimized Mode Decision; Rate Distortion Slope Estimation with Local Approximation; Rate Distortion Slope Estimation with Local Information; or Rate Distortion Slope Estimation with Global Information. The Lagrangian Multiplier Update Module may function with Direct Update; Step Size Update; Sliding Window Update; or Periodical Update.

Adaptive video encoder control

Video compression is performed under multiple distortion constraints. Video coding includes determining a first set of Lagrangian cost values for multiple coding modes using a first distortion metric, determining a second set of Lagrangian cost values for the multiple coding modes using a second distortion metric, and selecting one of the coding modes based on the first set of Lagrangian cost values and the second set of Lagrangian cost values to encode a pixel block using the selected coding mode. The distortion metrics can include information associated with video display characteristics such as screen display size, video processing performance, a distortion characteristic, a temporal characteristic, or a spatial characteristic. The distortion metrics can also include characteristics of multiple video displays, such as parameters for usage, importance, design, and the technology type of the video displays.

Growing community of inventors

Cupertino, CA, United States of America

Zhen Li