Google Inc.

Future Wei Technologies, Inc.

Photo U.s.a. Corporation

Lei Yang

Steve Benting

Thierry Foucu

Sang-Uok Kum

Debargha Mukherjee

Jun Tian

Hong Heather Yu

Dapeng Oliver Wu

Sam John

Alexander Jay Converse

Hugh Denman

Fatih Porikli

Hai Yu

Prasanna Meda

Qian Chen

James P Peng

A heat transfer process on to a stainless steel cup with a dark surface involves a stainless steel dark surface treatment layer arranged on a base layer of the outer circular surface of the cup body. The stainless steel dark surface treatment layer is sequentially arranged as at least one wire screen printing layer, a resin layer, and a thermal transfer image layer. The is one or several screen printing layers on the dark rough surface to fill up the rough pits on the dark surface to form a smooth surface and then a thermal transfer resin coating is applied, followed by heat transfer printing. A colorful personalized product can thus be produced from the cup.

Sublimation printing on to dark surfaces

A computer-implemented method for estimating head pose angles of a user includes determining a first rotation between a first head pose axis associated with a first image of a plurality of images of the user and a camera axis associated with a camera taking the images. A second rotation is determined between a second head pose axis associated with a second image of the user and the camera axis. The first and second head pose axes are determined based on light reflections within the plurality of images. A head pose angle of the user can be estimated based on the first rotation and the second rotation. An alert can be generated based on the estimated head pose angle.

Head pose and distraction estimation

A request for a video may be received from a client device. A determination whether to transmit the video at a first video resolution or a second video resolution based on a quality of the video at the first video resolution when converted to the second video resolution at the client device may be made. The video may be transmitted to the client device at the determined first video resolution or the second video resolution.

Bitrate selection for video streaming

Videos associated with video resolutions may be received. A first bitrate for each of the video resolutions may be identified based on a first bitrate point associated with the videos where a quality of the videos at a first video resolution that is upscaled to a second video resolution is better than a quality of the videos at the second video resolution at bitrates below the first bitrate point. The upscaling of the first video resolution may correspond to converting the videos from the first video resolution to the second video resolution at a client device. The identified corresponding first bitrate may be assigned to each of the video resolutions.

A plurality of videos associated with a plurality of video resolutions may be received. A minimum bitrate may be identified for each of the video resolutions based on a first bitrate point associated with the videos where a quality of the videos at a first video resolution that is upscaled to a second video resolution is better than a quality of the videos at the second video resolution at bitrates below the first bitrate point. Furthermore, a maximum bitrate may be identified for each of the video resolutions based on a second bitrate point where the rate of change of the quality of the videos is below a threshold value. The identified minimum bitrates and the maximum bitrates may be assigned to the video resolutions.

Adaptive video transcoding based on parallel chunked log analysis is described. The adaptive video transcoding method comprises receiving an intermediate video stream generated from an intermediate transcoding. The method also receives an intermediate transcoding log stream associated with the intermediate video stream. The method partitions the intermediate video stream into a plurality of video chunks, where each video chunk corresponding to a portion of video data of the video stream. The method further generates video chunk statistics for each of the video chunks using the intermediate transcoding log stream and transcoding parameters for each of the video chunks based on the generated video chunk statistics. The method transcodes each of the video chunks to a target format in parallel based on the generated transcoding parameters. The method assembles the transcoded video chunks into a target video stream in the target format.

Adaptive video transcoding based on parallel chunked log analysis

A system and method provide a video description length (VDL) guided constant quality video encoding strategy with bitrate constraint and a video coding system for optimizing encoding bitrate, distortion and complexity of an input video. The method obtains an overall VDL, temporal VDL and spatial VDL of the input video and compares the overall VDL, temporal VDL and spatial VDL of the input video with a reference VDL, temporal VDL and spatial VDL. Based on the comparison, the method adjusts the encoding bitrate, the overall encoding complexity, temporal encoding complexity and spatial encoding complexity of the input video and encodes the input video with the adjusted encoding bitrate, overall encoding complexity, temporal encoding complexity and spatial encoding complexity of the input video.

Rate-distortion-complexity optimization of video encoding guided by video description length

A system and method provide a video coding system for optimizing encoding bitrate, distortion and complexity for a video hosting service. The system comprises an encoding module configured to encode multiple videos with a bitrate control strategy, a pair of complexity allocation control parameters and one or more target output video formats specifications, which include target resolution, target bitrate and target quality information. The encoding module obtains encoding bitrate, distortion and complexity performance samples from the encoding. From the encoding bitrate, distortion and complexity performance samples, the encoding module is configured to select optimal encoding bitrate, distortion and complexity performance samples. The encoding computation profile mapping module is configured to obtain multiple computation levels from the optimal encoding bitrate, distortion and complexity performance samples. For each computational level, a pair of optimized complexity allocation control parameters and number of encoding passes are selected.

Rate-distortion-complexity optimization of video encoding

A system and method for securing media content are provided. A method for distributing security media content includes embedding a marking payload into media content, thereby producing embedded media content, applying a transform to the embedded media content, thereby producing secured media content, and distributing the secured media content. The marking payload is embedded based on perceptual information regarding the media content.

System and method for securing media content

In accordance with an embodiment, a method of comparing a first group of frames to a second group of frames includes electronically receiving the first group of frames, selecting a group of frames from the first group of frames as a first key frame set, calculating a hash distance between an image hash for each frame in the first key frame set to an image hash of each frame of a second key frame set taken from second group of frames, and choosing frames in the first group of frames with a minimum hash distances to respective reference frames to form a series of minimum hash distances.

Video signature based on image hashing and shot detection

In accordance with an embodiment, a method of authenticating images includes electronically receiving an anchor image and a query image, performing a feature point extraction of an anchor image, and performing a feature point extraction of a query image. The method also includes clustering feature points of the anchor image and feature points of the query image, where clustering includes determining matching feature points, determining outlier feature points, and excluding outlier feature points. Whether the anchor image is similar to the query image is determined based on a distance between the feature points of the anchor image and the feature points of the query image. If the anchor image is similar to the query image, possible tampered areas of the query image based on the outlier feature points are identified.

Growing community of inventors

Palo Alto, CA, United States of America

Lei Yang