Technical Disclosure Commons Defensive Publications Series

December 04, 2017

Interface for Exploring Videos Christopher Pentoney Rodrigo de Oliveira Anshuman Kumar Mary Cassin Joshua Lewandowski

Follow this and additional works at: http://www.tdcommons.org/dpubs_series Recommended Citation Pentoney, Christopher; de Oliveira, Rodrigo; Kumar, Anshuman; Cassin, Mary; and Lewandowski, Joshua, "Interface for Exploring Videos", Technical Disclosure Commons, (December 04, 2017) http://www.tdcommons.org/dpubs_series/851

This work is licensed under a Creative Commons Attribution 4.0 License. This Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons.

Pentoney et al.: Interface for Exploring Videos

Interface for Exploring Videos ABSTRACT Searching and browsing for videos is a common task. Search engines attempt to provide a quality user experience by showing the most relevant results at the top of a results page. However, efficiency and relevancy can sometimes be less of a concern, e.g., when browsing for interesting content, such as videos, e.g., without entering a search query. When users browse or search for videos, showing a hierarchical list of search results does not enable easy discovery of other content that they may enjoy. This disclosure describes techniques to improve user enjoyment when browsing videos, e.g., directly, or after performing a video search. Clusters of videos from various sources are displayed, e.g., in a virtual reality user interface. The distance between the clusters represents the overlap of viewer audience from respective video sources. KEYWORDS video search; content discovery; video discovery; virtual reality; user interface BACKGROUND Searching and browsing for videos is a common task. Search engines attempt to provide a quality user experience by showing the most relevant results at the top of a search results page. However, efficiency and relevancy can sometimes be less of a concern, e.g., when browsing for interesting content, such as videos, e.g., without entering a search query. When users browse or search for videos, showing a hierarchical list of search results does not enable easy discovery of other content that they may enjoy. Video search is a context in which other ways of displaying search results can be useful. For example, when a user searches for video content, they are searching for entertainment, for

Published by Technical Disclosure Commons, 2017

2

Defensive Publications Series, Art. 851 [2017]

videos that pique their interests. Therefore, a typical display of results, e.g., in a list format based on efficiency and relevancy, may not surface additional potential content that a user is likely to be interested in watching. DESCRIPTION This disclosure describes techniques to increase user enjoyment and to enable users to easily discover additional interesting video content when exploring online videos, e.g., by browsing or searching for videos. Video results are displayed in a user interface that includes clusters that each represent different sources of videos. The distance between the different clusters corresponds to the estimated audience overlap between the respective sources. The interface used to display the video results is suitable as a virtual reality user interface.

Fig. 1: Virtual reality user interface for display of clustered video results

http://www.tdcommons.org/dpubs_series/851

3

Pentoney et al.: Interface for Exploring Videos

Figure 1 is a portion of an example virtual reality interface to display video source results spaced a specified distance apart from one another corresponding to the amount of estimated audience overlap. Virtual reality interface (102) displays visual clusters of videos (104a, 104b, and 104c), each of which is separated by a respective distance (108a, 108b, and 108c) from other clusters of videos. Each visual cluster includes, for example, video thumbnails (106) for videos from the video source. Figure 1 is an example interface, and in different implementations, video thumbnails are not included. For example, instead of or in addition to video thumbnails, other information can be included. The distances between clusters correspond to the audience overlap between the video sources. For example, cluster 104a is separated by a distance 108a from cluster 104c. The distance represents the extent to which the audience of the video source represented by cluster 104a overlaps with the audience of the video sources represented by cluster 104c. Clusters representing a first video source are shown closer to clusters representing other video sources that share a greater portion of the audience with the first video source. Clusters with less proportion of overlapping audience are shown at a greater distance from the first video source. For example, if a user searches for videos from a specific comedian from a particular region or city, the interface displays thumbnail videos from the comedian as nearby to a cluster representing a source of comedy videos from another comedian that is from the same region or city as the first comedian. These clusters are near each other because of the overlapping audience of viewers. Although the user in this example searched for comedy videos from a particular comedian, the user may in fact find that the comedy videos from nearby clusters are also of interest.

Published by Technical Disclosure Commons, 2017

4

Defensive Publications Series, Art. 851 [2017]

The virtual reality interface displays these video sources as clusters of videos comprised of individual video thumbnails. The interface enables a user to fly between the clusters of video sources in virtual reality. This way, a user can see different segments of video results in interactive virtual reality separated based on audience overlap rather than simply viewing a textual list of results. A video source is any source of videos, such as videos authored by a specific user, videos posted to an internet video channel, videos by a specific internet video content curator, etc. Each cluster of videos also includes bibliographic information about the source of the videos. For example, a cluster of videos may correspond to an internet video channel. The bibliographic information about the creator, upload dates, language, video duration, etc. can be listed or associated with the cluster. The relationships between the clusters can encourage the user to explore other content about a topic in which they are interested, and can also encourage users to discover new topics altogether. The individual video thumbnails can be static or live thumbnails. The virtual reality interface can show clusters of related videos, wherein each cluster is made up of video thumbnails that play simultaneously. In another example, the video thumbnails are played once a user of the virtual reality interface zooms in or flies sufficiently close to a particular cluster. If a user likes the video content presented in a cluster, the user can easily fly over to a nearby cluster to see other video sources that were viewed by a similar audience. The virtual reality interface enables 360-degree clusters of video results to be displayed to the user. Each cluster is differentiated by its distance to other clusters rather than in a textual list ordered hierarchically based on relevancy. The virtual reality interface can be utilized in

http://www.tdcommons.org/dpubs_series/851

5

Pentoney et al.: Interface for Exploring Videos

video browsing and search, and can also be beneficial for content discovery in social platforms or e-commerce portals. The user interface focuses on making the process of discovering and viewing new sources of content enjoyable. Users are free to engage and view different clusters and videos contained therein and to choose any video to start watching immediately. The user interface makes reviewing results more fun because the user can interact with the video results and the individual videos contained therein in virtual reality. The farther a user travels in virtual reality, the user can find more variety and videos that are still of interest. For variety, the user may fly a longer trip to explore a further connected cluster. To make the virtual reality interface entertaining and engaging it can also be presented as a universe of planets. For example, each video source can be represented by a planet and the user may fly to adjacent planets to view videos from another source with audience overlap. Further, the user can fly to and explore videos from a distant planet, e.g., a video source with less audience overlap. Other virtual reality themes could also be adopted, e.g., an ocean with various islands representing video sources, a theme park with rides representing video sources, a library with shelves representing various sources and books as clusters of videos, etc. The present technique may also be used to display and explore results from other types of content that can be connected through a shared attribute. For example, the interface can enable the discovery of music, viewing of documents or web pages, and others. In these cases, the clusters can display sources of music, documents, web pages, etc. such as composers, artists, bands, specific journalists or news sources, document authors, etc. connected with a distance determined based on their audience overlap. For example, the virtual reality interface may display clusters of songs, wherein a cluster includes songs by a particular artist and wherein the

Published by Technical Disclosure Commons, 2017

6

Defensive Publications Series, Art. 851 [2017]

clusters are separated by a distance corresponding to the overlap of the audience that listens to music from the different clusters. In another example, the virtual reality interface can display clusters of news articles, wherein the clusters include articles by particular journalists or news sources, and are distanced in virtual reality based on the overlap of audience readership. The entire virtual reality interface can be adapted for and displayed on one display, such as on a computer display. Additionally, a portion of the virtual reality interface can be displayed as a software-rendered globe coupled with controls that enable the user to drag portions of the virtual reality interface corresponding to exploring content in its virtual reality interface equivalent. Instead of a user moving their head to look around at the clusters of media in virtual reality, the user can click and drag using their mouse or finger on a screen. In situations in which certain implementations discussed herein may collect or use personal information about users (e.g., user data, information about a user’s social network, user's location and time at the location, user's biometric information, user's activities and demographic information), users are provided with one or more opportunities to control whether information is collected, whether the personal information is stored, whether the personal information is used, and how the information is collected about the user, stored and used. That is, the systems and methods discussed herein collect, store and/or use user personal information specifically upon receiving explicit authorization from the relevant users to do so. For example, a user is provided with control over whether programs or features collect user information about that particular user or other users relevant to the program or feature. Each user for which personal information is to be collected is presented with one or more options to allow control over the information collection relevant to that user, to provide permission or authorization as to whether the information is collected and as to which portions of the information are to be

http://www.tdcommons.org/dpubs_series/851

7

Pentoney et al.: Interface for Exploring Videos

collected. For example, users can be provided with one or more such control options over a communication network. In addition, certain data may be treated in one or more ways before it is stored or used so that personally identifiable information is removed. As one example, a user’s identity may be treated so that no personally identifiable information can be determined. As another example, a user’s geographic location may be generalized to a larger region so that the user's particular location cannot be determined. CONCLUSION This disclosure describes a virtual reality user interface that makes browsing videos enjoyable. The videos are obtained directly from a video source (e.g., a video hosting website, a social media feed, etc.), from a video search, etc. Video results are shown as clusters representing video sources. Each cluster is separated from other clusters based on the extent to which the audience of video sources overlap. Using a user interface per the present techniques, users can discover video content easily, focusing on new sources in topic areas they are already interested in or exploring new topics entirely.

Published by Technical Disclosure Commons, 2017

8

Interface for Exploring Videos - Research at Google

Dec 4, 2017 - information can be included. The distances between clusters correspond to the audience overlap between the video sources. For example, cluster 104a is separated by a distance 108a from cluster 104c. The distance represents the extent to which the audience of the video source represented by cluster.

184KB Sizes 3 Downloads 383 Views

Recommend Documents

What's Cookin'? Interpreting Cooking Videos ... - Research at Google
techniques based on keyword spotting. It also enables ... “slice an onion”, etc. However, our techniques can ...... In Intl. Joint Conf. on AI. S. Guadarrama, N.

EXPLORING LANGUAGE MODELING ... - Research at Google
ended up getting less city-specific data in their models. The city-specific system also includes a semantic stage for inverse text normalization. This stage maps the query variants like “comp usa” and ”comp u s a,” to the most common web- tex

DETECTING HIGHLIGHTS IN SPORTS VIDEOS - Research at Google
fore, automatic detection of these highlights in sports videos has become a fundamental problem of sports video analysis, and is receiving increased attention ...

Paper Interface to Electronic Medical Records: A ... - Research at Google
requirements, such as HIPAA regulations. Somewhat related we ... redundant work and potential regulatory noncompliance. Both clinics were evaluating EMR ...

Zebra: Exploring users' engagement in fieldwork - Research at Google
the interLiving project [2] as a method to explore a design space by: • raising users' interest and ..... Conf. on Designing Interactive Systems, ACM, Amsterdam,.

Blognoon: Exploring a Topic in the Blogosphere - Research at Google
probably, the best known blog search engine, in addition to keyword search, allows .... ory, with a dedicated machine with 8Gb RAM used for host- ing the WKB.

Exploring decision making with Android's ... - Research at Google
Jul 14, 2017 - on Android devices before runtime permission dialogs were ... decisions - indicating that for 10% of grant decisions users may be consenting ...

Exploring the steps of Verb Phrase Ellipsis - Research at Google
instance in dialogue systems or Information Extrac- tion applications. ... Nielsen (2005) presents the first end-to-end system that resolves VPE ..... Whether the antecedent is in quotes and the target is not, or vice versa. H&B. Table 1: Antecedent

Theory for nucleation at an interface and magnetization ...
way as a 1D Schrödinger equation with a step potential, where the potential simplifies in the limits considered in Sec. III. The limit of small applied field is solved in Appendix A, and applied fields close to the critical field are treated in. Appe

Mathematics at - Research at Google
Index. 1. How Google started. 2. PageRank. 3. Gallery of Mathematics. 4. Questions ... http://www.google.es/intl/es/about/corporate/company/history.html. ○.

Simultaneous Approximations for Adversarial ... - Research at Google
When nodes arrive in an adversarial order, the best competitive ratio ... Email:[email protected]. .... model for combining stochastic and online solutions for.

Asynchronous Stochastic Optimization for ... - Research at Google
Deep Neural Networks: Towards Big Data. Erik McDermott, Georg Heigold, Pedro Moreno, Andrew Senior & Michiel Bacchiani. Google Inc. Mountain View ...

SPECTRAL DISTORTION MODEL FOR ... - Research at Google
[27] T. Sainath, O. Vinyals, A. Senior, and H. Sak, “Convolutional,. Long Short-Term Memory, Fully Connected Deep Neural Net- works,” in IEEE Int. Conf. Acoust., Speech, Signal Processing,. Apr. 2015, pp. 4580–4584. [28] E. Breitenberger, “An

Asynchronous Stochastic Optimization for ... - Research at Google
for sequence training, although in a rather limited and controlled way [12]. Overall ... 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) ..... Advances in Speech Recognition: Mobile Environments, Call.

UNSUPERVISED CONTEXT LEARNING FOR ... - Research at Google
grams. If an n-gram doesn't appear very often in the training ... for training effective biasing models using far less data than ..... We also described how to auto-.

Combinational Collaborative Filtering for ... - Research at Google
Aug 27, 2008 - Before modeling CCF, we first model community-user co- occurrences (C-U) ...... [1] Alexa internet. http://www.alexa.com/. [2] D. M. Blei and M. I. ...

Quantum Annealing for Clustering - Research at Google
been proposed as a novel alternative to SA (Kadowaki ... lowest energy in m states as the final solution. .... for σ = argminσ loss(X, σ), the energy function is de-.

Voice Search for Development - Research at Google
26-30 September 2010, Makuhari, Chiba, Japan. INTERSPEECH ... phone calls are famously inexpensive, but this is not true in most developing countries.).

MEASURING NOISE CORRELATION FOR ... - Research at Google
the Fourier frequency domain. Results show improved performance for noise reduction in an easily pipelined system. Index Terms— Noise Measurement, Video ...

Approximation Schemes for Capacitated ... - Research at Google
set of types of links having different capacities and costs that can be used to .... all Steiner vertices in M have degree at least 3 and are contained in the small-.