Abstract: The present disclosure is directed towards methods and systems for providing relevant video scenes in response to a video search query. The systems and methods identify a plurality of key frames of a media object and detect one or more content features represented in the plurality of key frames. Based on the one or more detect content features, the systems and methods associate tags indicating the detected content features with the plurality of key frames of the media object. The systems and methods, in response to receiving a search query including search terms, compare the search terms with the tags of the selected key frames, identify a selected key frame that depicts at least one content feature related to the search terms, and provide a preview image of the media item depicting the at least one content feature.

Abstract: Techniques and systems are described to enable an analytics system to generate a forecast value for audience impressions of subsequent digital video content. In one example, an analytics system generated a linear regression model using data. The data describes audience segment values for past audience impressions of digital video content and a time series of when the digital video content is made available for consumption. The analytics system generates forecast values for audience impressions of digital video content using the linear regression model. In one example, the analytics system generates a forecast value for audience impressions of a subsequent item of digital video content based on scheduled availability for the subsequent item.

Abstract: A digital medium environment is described to recommend a transition from use of a limited-functionality application to a full-functionality application. As described herein, the limited-functionality application includes a subset of the functionalities of the full-functionality application. Interactions by a user with a limited-functionality application to generate or edit a creation (e.g., a photo, video, or document) are monitored. Based on the interactions, it is determined that the user needs a functionality for the creation that is not available in the limited-functionality application but is supported by the full-functionality application. A recommendation to transition the creation to the full-functionality application that supports the functionality is displayed. The recommendation may include a selectable control that, when selected, causes the creation to be transitioned to the full-functionality application to enable the functionality to be applied to the creation.

Abstract: Offline consumer behavior and interactions are observed using beacons positioned at venues where consumers spend time and interact with each other. The beacons communicate with mobile computing devices that are carried by the observed consumers. The observed consumer behavior provides actionable insights into how consumers influence each other. For example, the people that a particular consumer spends time with form a “circle of influence” associated with that consumer. If the consumer makes a purchase, members of the circle of influence are observed to understand the degree to which they were influenced by the purchase, if at all. Metrics that quantify a consumer's influence over other consumers allow marketers to more effectively target both the influencing and influenced consumers. Also, if relatively little information is known about a particular consumer, that consumer's digital marketing profile can be supplemented using information known about the consumers with whom he/she often spends time.

Abstract: Systems and methods for providing real-time marketing campaigns are disclosed. One disclosed method includes steps of identifying, by a marketing system, a target product for a marketing campaign; executing a real time capture system to requesting and receiving, by a real-time capture system, user comment information from one or more social media sites; determining, by a sentiment engine, sentiments associated with the user comment information about the target product; and identifying, by the marketing system, one or more features of the target product associated with the sentiments and a target population for the marketing campaign based on the user comment information.

Abstract: Techniques are disclosed for presenting recommended marketing content that can be dynamically varied (e.g., in real time or near-real time) based on the particular content of a web page that a user is currently reading, the content that the user has previously read, or a combination of these factors. For example, the current interactions of a user with content of a web page, such as scroll position or eye fixation, can be used to identify which portion or portions of the web page content the user is currently reading and which portions of the web page content the user is skimming or skipping over. Keywords can then be generated based on the content in those portions of the web page that the user is currently reading. Next, recommended marketing content corresponding to the keywords can be retrieved and presented to the user.

Abstract: In implementations of a service system to determine journeys based on companion relationship, a server computing device maintains event information about events associated with previous visitors within a designated geographic region, and a devices graph that correlates user identities with devices. A journey determination application can receive an indication that a mobile device has entered the designated geographic region, and correlate the mobile device to an identity of a user. A companion device that is associated with the mobile device can be determined based on companionship information identifying the association of the devices, and the companion device correlates to a companion. The journey determination application determines a journey based on a relationship of the companion to the user of the mobile device and based on the events associated with the previous visitors within the designated geographic region, the journey being designed to elicit a location-based visitor response from the user.

Abstract: Systems and methods disclosed herein score leads by determining and applying a scoring rule based on lead participation in an activity. This involves a processor of a computing device receiving information on participation in the activity by prior leads that resulted in conversions or rejections. A scoring rule is determined for the activity by assigning a score to the activity based on the information on participation in the activity by the prior leads that resulted in the conversions or the rejections. A new lead is scored using the scoring rule by assigning the new lead the score based on participation by the new lead in the activity. The scoring of the new lead can be used in various ways. In one example, the score of the new lead is used to determine to send a communication to the new lead.

Abstract: Systems and techniques for masking non-public content in screen images are provided. An example system includes a screen capture tool, a region-based object detection system, a classifier, and an image masking engine. The screen capture tool may be configured to generate a screen image representing a screen being displayed by the system. The region-based object detection system may be configured to identify multiple regions within the screen image as potential non-public content regions. The classifier may be configured to selectively classify the identified regions as non-public content regions. The image masking engine may be configured to generate a masked image by masking the regions classified as non-public content regions in the screen image.

Abstract: Interaction-based content configuration is described. In one or more implementations, interactions of an online store customer with an online store are tracked. When a shopping session is ended and an item viewed during the shopping session is not purchased, personalized marketing content is generated for the customer. To do so, the tracked interactions are analyzed to ascertain which content corresponding to the unpurchased item the customer focused on during the shopping session. The tracked interactions track a gaze of the customer relative to displayed content of the online store, for instance. Further, the content the customer focused on is determined as that which held the customer's gaze for a period of time or which the customer gazed at a greater number of times than other content. The personalized marketing content is configured to include a portion of the focused-on content.

Abstract: Creating audience segments for campaigns is described. In one or more embodiments, an audience manager is configured to create, for one or more videos, a video audience segment associated with the video by storing, in a data management platform, user identifiers of users that viewed the video. The user identifiers can be received from a client player each time that a video is played at the client player. The audience manager is further configured to extract demographic information from a demographic report associated with the video that is received from a demographics provider, and to associate the demographic information with the video audience segment. The audience manager is further configured to generate a target audience segment for a campaign by merging and combining user identifiers that are included in two or more video audience segments.

Abstract: In various implementations, a visual representation of a product is presented to an online consumer. The visual representation can have one or more regions that are each associated with one or more feature tags associated with a particular category of the product. While the consumer interacts with the visual representation, interaction times between the consumer and the product's visual representation are monitored and measured to determine which features of the product appear to be of particular interest to the consumer. Based on the monitored interaction times, product upsell recommendations associated with the same category of the product are generated and presented to the user.

Abstract: Methods score users to determine if they will receive marketing communications sent to users on a subscription list. One method calculates an un-subscription score for a user based on: a degree of sentiment determined by identifying user interaction with a web page and assessing content of the interaction for indications of sentiment; or a degree of sentiment determined by identifying a user communication and assessing its content for indications of sentiment. Responsive to determining that the un-subscription score exceeds a threshold, the method excludes the user when sending the marketing communication to users on the subscription list. Another method calculates a degree of sentiment based on user interactions with a page and user communications, and calculates the user's un-subscription score based on the degree of sentiment. Responsive to comparing the un-subscription score with a threshold, the method excludes the user when sending the marketing communication to users on the list.

Abstract: An image search is executed. The search results are presented as a collection of thumbnail images organized according to an initial ranking. As the user browses the thumbnail images, he/she encounters a thumbnail image of interest. Selecting this thumbnail causes an enlarged preview image to be displayed. The user can manipulate the enlarged preview image with panning and zooming operations, thereby enabling the user to more closely inspect portions of the preview image which attract the user's interest. These interactions with the search results, which include the initial selection of the thumbnail image and the subsequent manipulation of the enlarged preview image, provide insight into the user's interest. Once the user has interacted with a threshold quantity of search results, the collection of thumbnail images is filtered and reorganized to more prominently position those search results that correspond to the user's interest, as gleaned from analyzing the aforementioned user interactions.

Abstract: Associating social comments with individual assets used in a campaign is described. In one or more embodiments, a campaign that includes one or more assets (e.g., images or videos of products) is published to one or more social networks. Comments (e.g., user comments, user shares, or other textual feedback) to the campaign on the one or more social networks are collected and analyzed to attribute each comment to an individual asset of the campaign. Social metadata, such as a social mention count and a social sentiment score, is generated based on the comments to enhance metadata of the individual asset.

Abstract: In embodiments of synchronizing linked assets from unsynchronized file folders, files are organized in folders of a file system, where the folders include a synchronized folder and an unsynchronized folder, the synchronized folder having been selected for synchronization of the files contained in the synchronized folder, and the unsynchronized folder containing linked assets. The files contained in the synchronized folder are synchronized with a network-based memory system that stores an instantiation of the files. A synchronization service can determine that a file contained in the synchronized folder references to one or more of the linked assets contained in the unsynchronized folder. The synchronization service can then synchronize a linked asset from the unsynchronized folder automatically based on criteria associated with the file contained in the synchronized folder.

Abstract: A method for recommending hashtags includes determining keywords from a post planned for publishing by a publisher. An input criteria comprising at least one of age group, geographical location, date range, or a keyword is received. Previous posts associated with the keywords and satisfying the input criteria are obtained. The previous posts are categorized into one or more categories based on sentiment of each post and for each category hashtags used in the obtained previous posts in that category are determined. The hashtags are ranked based on predefined criteria comprising at least one of frequency of appearance of respective hashtag in posts, number of likes or shares or retweets of post comprising respective hashtag, number of followers of person who used respective hashtag, or sentiment of post comprising respective hashtag. The hashtags are then recommended, based on ranking, to the publisher for use with the post planned for publishing.

Abstract: Techniques and systems are described to enable an analytics system to generate a forecast value for audience impressions of subsequent digital video content. In one example, an analytics system generated a linear regression model using data. The data describes audience segment values for past audience impressions of digital video content and a time series of when the digital video content is made available for consumption. The analytics system generates forecast values for audience impressions of digital video content using the linear regression model. In one example, the analytics system generates a forecast value for audience impressions of a subsequent item of digital video content based on scheduled availability for the subsequent item.

Abstract: Replacing content of a surface in video is described. In one or more embodiments, a surface captured in a scene of video content is replaced with replacement content. As part of doing so, an indication of the surface to be replaced is received. The indication may be received as user input to select the surface for replacement from a frame of video content or as a pattern that can be used to search for the surface in frames of the video content. Once the surface is identified, it is tracked throughout the video content using motion tracking techniques. The motion tracking identifies frames of the video content that include the identified surface as well as locations of surface in the identified frames. Based on the identified frames and locations, the replacement content is incorporated into the video content to replace the surface.

Abstract: A computer-implemented method for providing performance indicators of destination documents includes identifying a referral document to a destination document, where the referral document comprising a source of at least one visitor to the destination document. The method also includes extracting referral keywords from content of the referral document, the referral keywords corresponding to a referral context of the referral document. The method further includes determining a degree of correlation between the referral document and the destination document based on a comparison between the referral keywords and destination keywords, the destination keywords corresponding to destination context of the destination document.