摘要:
A method of describing texture of a group of frames (GoF) or a group of pictures (GoP) using homogeneous texture descriptors, and a method and apparatus for retrieving a GoF/GoP using the texture description method are provided. The texture description method includes: generating homogeneous texture descriptors of all frames constituting the GoF or all pictures constituting the GoF; and expressing the GoF or GoP using a predetermined representative homogeneous texture descriptor corresponding to one frame or picture to reduce the amount of data. The GoF/GoP retrieval method includes: establishing a database of homogeneous texture descriptors of a plurality of GoFs' or GoPs', each GoF or GoP being expressed by a predetermined representative homogeneous texture descriptor corresponding to one frame or picture to reduce the amount of data; generating a homogeneous texture descriptor corresponding to one frame or picture of a query GoF or GoP when the query GoF or GoP is input; searching homogeneous texture descriptors that are similar to the homogeneous texture descriptor of the query GoF or GoP in the database; and retrieving GoFs' or GoPs' corresponding to the searched similar homogeneous texture descriptors and arranging GoFs' or GoPs' in the order of degree of similarity. Therefore, the texture of images can be more accurately expressed, and an image can be more efficiently and rapidly retrieved.
摘要:
A method of browsing contents and an apparatus for browsing the same are provided. The method includes providing a plurality of characteristic vector types and a plurality of characteristic value types that correspond to a reference characteristic vector type selected from the plurality of characteristic vector types, and determining an arrangement order of preview information of contents according to a reference characteristic value type that is selected from the plurality of characteristic value types, and providing the preview information in the arrangement order.
摘要:
Systems and methods of presenting media objects are described. In one aspect, a group of media objects is selected from the collection based upon media object relevance to one or more data structures of a selected media file of indexed, temporally-ordered data structures. One or more of the selected media file and the media objects of the selected group are transmitted to a client for contemporaneous presentation at a selected summarization level. In another aspect, media objects in the collection are grouped into multiple clusters based upon one or more media object relevance criteria. The media object clusters are arranged into a hierarchy of two or more levels. A selected cluster is transmitted to a client for contemporaneous presentation at a selected summarization level.
摘要:
A method discovers patterns in unknown multi-dimensional data. A time-series of the multi-dimensional data is generated and a point cross-distance matrix is constructed by self-correlating the time-series. All minimum cost paths in the point cross-distance matrix are located at multiple time resolutions. The minimum cost paths are then related to temporal sub-sequences in the multi-dimensional data to discover high-level patterns in the unknown multi-dimensional data.
摘要:
A method detects events in multimedia. Features are extracted from the multimedia. The features are sampled using a sliding window to obtain samples. A context model is constructed for each sample. An affinity matrix is determined from the models and a commutative distance metric between each pair of context models. A second generation eigenvector is determined for the affinity matrix, and the samples are then clustered into events according to the second generation eigenvector.
摘要:
When a retrieval condition of an attribute list is input from a user interface unit to a retrieval processing unit, the attribute list stored in an attribute list storing unit is retrieved in the retrieval processing unit. Thereafter, attribute information conforming to the retrieval condition is output to and displayed on a displaying unit. Thereafter, when a retrieval condition of the similarity retrieval is input from the user interface unit to the retrieval processing unit, image data stored in the image information storing unit is retrieved in the retrieval processing unit, and specific image data relating to a characteristic descriptor set conforming to the retrieval condition is selected in the retrieval processing unit. Thereafter, the specific image data is output to and displayed on the displaying unit.
摘要:
A method detects events in multimedia. Features are extracted from the multimedia. The features are sampled using a sliding window to obtain samples. A context model is constructed for each sample. An affinity matrix is determined from the models and a commutative distance metric between each pair of context models. A second generation eigenvector is determined for the affinity matrix, and the samples are then clustered into events according to the second generation eigenvector.
摘要:
The method is characterized in that it implements the following steps: random drawing of p candidates from the set of key images, calculation of a cost C for each candidate, selection of the candidate minimizing the cost C, determination of a subset from among the set of key images such that the key images forming the said subset have a distance from the candidate less than a threshold T, determination of a seed from among the key images of the subset such that it minimizes the cost function C for this subset, deletion of the key images of the subset to form a new set of key images for at least one new random draw and determination of a new seed according to the previous 5 steps. The field is that of the selection of shots of interest in a video sequence.