Google Inc.

Nicola Muscettola

Nitin Khandelwal

Sudheendra Vijayanarasimhan

Sanketh Shetty

Balakrishnan Varadarajan

Weilong Yang

Apostol Ivanov Natsev

WeiHsin Gu

George Dan Toderici

Tomas Izo

Min-Hsuan Tsai

Phuong B Le

Sami Ahmad Abu-El-Haija

Varun Kacholia

Fabio Lopiano

Sreedhar Mukkamalla

Susanna Maria Ricco

Nitin Jindal

Kun Zhang

Gheorghe Postelnicu

Johan Granström

Aparna Chennapragada

Omer Bar-or

Richard Tucker

Johan Georg Granstrom

Patrick Hung

Murali Krishna Viswanathan

Minya Dai

Zhiyi Xie

Jonathan Eng

Susana Ricco

A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.

Selecting and presenting representative frames for video previews

Systems and methods for identifying duplicate media items in a media system are provided. In particular, media content can be uploaded to a serve. The media content can be fingerprinted. A digest is generated based on the fingerprint. The digest is indexed and potential matching media items are identified. Matches are determined from the potential matching media items.

Real-time duplicate detection of videos in a massive video sharing system

A search result is modified to include a predetermined number of channels within a predetermined number of a plurality of entries in the search result. The search result is generated in response to a search query. The search result is modified to comprise a predetermined number of channels within a predetermined number of the plurality of entries. The modified search result is updated based on the plurality of entries and a subset of the updated modified search result is selected to be presented in response to the search query. The subset of the updated modified search result comprises the channel and at least one selection of data content.

Ranking channels in search

A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method selects an entity from a plurality of entities identifying characteristics of a video item, where the video item has associated metadata. The computer-implemented method receives probabilities of existence of the entity in video frames of the video item, and selects a video frame determined to comprise the entity responsive to determining the video frame having a probability of existence of the entity greater than zero. The computer-implemented method determines a scaling factor for the probability of existence of the entity using the metadata of the video item, and determines an adjusted probability of existence of the entity by using the scaling factor to adjust the probability of existence of the entity. The computer-implemented method labels the video frame with the adjusted probability of existence.

Video frame annotation

The present disclosure relates to the identification of video content. In one aspect, a method includes generating a query based on bibliographic data. The method also includes obtaining a collection of resources responsive to the query, wherein one or more of the resources include text and video content. The method further includes calculating occurrence scores for the resources. A particular occurrence score for a particular resource is based at least in part on the bibliographic data matching text included in the particular resource and the text being associated with video content. The method further includes selecting one or more resources as including video content identified by the bibliographic data using the occurrence scores. The method further includes storing data associating the selected resources with the bibliographic data.

Matching video content to video bibliographic data

Systems and methods are provided herein relating to real-time duplicate detection of video content. Fingerprints can be generated for an uploaded video. The fingerprints can be used to match the uploaded video to a set of matching videos. The set of matching videos can be filtered based on the type of match, and the quality of the match. A unique cluster-id can be generated for the uploaded video containing an upload time, and that unique cluster-id can then be modified to associate the uploaded video with a cluster-id of potential duplicates. Cluster-ids can then be used in the context of a search to filter results that have identical cluster-ids. The benefits in using real-time duplicate detection can better maximize user experiences in a video sharing service that contains potential duplicates of the same content.

Real-time duplicate detection for uploaded videos

Growing community of inventors

Sunnyvale, CA, United States of America

Nicola Muscettola