Newness and distinctiveness is claimed in the features of ornamentation as shown inside the broken line circle in the accompanying representation.

Display screen or portion thereof with graphical user interface

Graphical user interface for a display screen or portion thereof

In this paper, we review 300 references on video retrieval, indicating when text-only solutions are unsatisfactory and showing the promising alternatives which are in majority concept-based. Therefore, central to our discussion is the notion of a semantic concept: an objective linguistic description of an observable entity. Specifically, we present our view on how its automated detection, selection under uncertainty, and interactive usage might solve the major scientific problem for video retrieval: the semantic gap. To bridge the gap, we lay down the anatomy of a concept-based video search engine. We present a component-wise decomposition of such an interdisciplinary multimedia system, covering influences from information retrieval, computer vision, machine learning, and human–computer interaction. For each of the components we review state-of-the-art solutions in the literature, each having different characteristics and merits. Because of these differences, we cannot understand the progress in video retrieval without serious evaluation efforts such as carried out in the NIST TRECVID benchmark. We discuss its data, tasks, results, and the many derived community initiatives in creating annotations and baselines for repeatable experiments. We conclude with our perspective on future challenges and opportunities.

/pdf/concept-based-video-retrieval-1iy430iazc.pdf

Concept-Based Video Retrieval

Models of networked diffusion that are motivated by analogy with the spread of infectious disease have been applied to a wide range of social and economic adoption processes, including those related to new products, ideas, norms and behaviors. However, it is unknown how accurately these models account for the empirical structure of diffusion over networks. Here we describe the diffusion patterns arising from seven online domains, ranging from communications platforms to networked games to microblogging services, each involving distinct types of content and modes of sharing. We find strikingly similar patterns across all domains.In particular, the vast majority of cascades are small, and are described by a handful of simple tree structures that terminate within one degree of an initial adopting "seed." In addition we find that structures other than these account for only a tiny fraction of total adoptions; that is, adoptions resulting from chains of referrals are extremely rare. Finally, even for the largest cascades that we observe, we find that the bulk of adoptions often takes place within one degree of a few dominant individuals. Together, these observations suggest new directions for modeling of online adoption processes.

/pdf/the-structure-of-online-diffusion-networks-3vxzdt54r7.pdf

The structure of online diffusion networks

This disclosure describes systems, methods and user interfaces that allow a user to identify, annotate and share a portion of a media item with another user. Through the user interface, the user may render a media item and identify a segment of the media item. Based on the media item, previously defined and shared segments may be suggested to the user allowing the user to quickly select and identify popular segments for sharing. In addition, previously used annotations of previously defined and shared segments may be suggested to the user allowing users to quickly select annotations. The sharing user may then issue a command that causes a link or other means for accessing the segment to be transmitted to a recipient. Accessing this link or other means, causes the segment defined by the sharing user to be rendered on the recipient's device.

Method and system for personalized segmentation and indexing of media

Systems and methods are disclosed that allow a user to preview media content on a device while the device is downloading the media content and without interrupting the downloading of the media content. In addition, the user may preview any location within a media file regardless of whether the media data for the location has been received by the user's device. The user's device, upon receipt of a command to preview a specific location within a file already being downloaded, determines if the data for that location have already been received. If so, the user's device generates a preview frame from the downloaded data. If not, the user's device transmits a preview request to the media server which generates the preview frame and transmits back to the user's device.

Method and system for previewing media over a network

This paper presents a high-level overview of Yahoo Research Berkeley's approach to multimedia research and the ideas motivating it. This approach is characterized primarily by a shift away from building subsystems that attempt to discover or understand the "meaning" of media content toward systems and algorithms that can usefully utilize information about how media content is being used in specific contexts; a shift from semantics to pragmatics. We believe that, at least for the domain of consumer and web videos, the latter provides a more promising basis for indexing media content in ways that satisfy user needs. To illustrate our approach, we present ongoing work on several applications which generate and utilize contextual usage meta-data to provide novel and useful media experiences.

Watch what I watch: using community activity to understand content

Methods and systems are described for allowing a user to quickly determine parts of a media item in which the user will be interested. In the methods and systems described, a timeline is provided for the media item and semantic icons are used as media landmarks along the timeline. The semantic icons are related to the content or a description of the content at the location in the media item corresponding to the semantic icon's location on the timeline. The semantic icons, in addition to providing some immediate contextual information at a glance, also allow a user access to annotations of the media item. Semantic icons can represent tags, users who have created or modified annotations for the segment of the media item, or other relevant information. The semantic icons may also be used to determine a relative level of interest in different parts of the media item both with respect to the user and with respect to other users.

Method and system for media landmark identification

Against this backdrop systems and methods have been developed for identifying popular segments of media objects A remix system is provided to users allowing the easy remixing of a library of media objects The remixes created by the users are recorded From this information, the relative popularity of the segments and media objects in the library are identified based on how often they appear in the user-generated remixes Actions may then be automatically taken related to the popularity of segments and media objects such as changing payment terms, alerting users of the popular content, and notifying interested parties of the popular or unpopular content

Peter Shafton

Papers

Method and system for personalized segmentation and indexing of media

Method and system for previewing media over a network

Watch what I watch: using community activity to understand content

Method and system for media landmark identification

Identifying popular segments of media objects