System and method for annotating multi-modal characteristics in multimedia documents
View Patent ↗A manual annotation system of multi-modal characteristics in multimedia files. There is provided an arrangement for selection an observation modality of video with audio, video without audio, audio with video, or audio without video, to be used to annotate multimedia content. While annotating video or audio features is isolation results in less confidence in the identification of features, observing both audio and video simultaneously and annotating that observation results in a higher confidence level.
1. An apparatus for managing multimedia content, said apparatus comprising:
a processor;
an arrangement for supplying multimedia content;
an input interface for permitting a selection, for observation, of at least one of the following modes associated with the multimedia content: an audio portion that includes video; and a video portion that includes audio; and
an arrangement for labeling observations of a selected mode;
wherein said arrangement for labeling observations of a selected mode comprises:
an arrangement for assigning semantic, multimedia content-based labels to segments of said observations of a selected mode;
wherein said arrangement for assigning semantic, multimedia content-based labels is configured to:
provide a label from a predefined set of multimedia content descriptors; and
assign a new label not present in said predefined set of multimedia content descriptors; and
an arrangement permitting a user to label audio while viewing video having:
a check box for labeling foreground sounds;
a check box for labeling background sounds; and
a keyword text box arrangement; and
an arrangement for storing said semantic, multimedia content-based labels with the multimedia content.
2. The apparatus according to claim 1 , wherein said input interface permits the selection, for observation, of both of the following associated with the multimedia content: an audio portion that includes video; and a video portion that includes audio.
3. The apparatus according to claim 1 , wherein said input interface additionally permits the selection, for observation, of solely a video portion of multimedia content.
4. The apparatus according to claim 1 , wherein said input interface additionally permits the selection, for observation, of solely an audio portion of multimedia content.
5. The apparatus according to claim 1 , wherein said arrangement for supplying multimedia content comprises a working memory which stores labeled multimedia files in an industry standard format.
6. The apparatus according to claim 1 , wherein said input interface is adapted to: first permit the selection of a multimedia file and then permit the selection of said at least one of: an audio portion simultaneously with video; and a video portion simultaneously with audio.
7. The apparatus according to claim 1 , further comprising a working memory for saving the labeled observations of a selected mode.
8. The apparatus according to claim 1 , wherein said input interface is adapted to permit the selection, for observation, at least the following mode associated with the multimedia content: a video portion that includes audio.
9. The apparatus according to claim 8 , wherein said input interface comprises:
an arrangement for permitting the selection, for observation, of a video mode of multimedia content; and
an arrangement for selectably adding audio to the video mode for observation.
10. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for managing multimedia content, said method comprising the steps of:
supplying multimedia content;
permitting a selection, for observation, of at least one of the following modes associated with the multimedia content: an audio portion that includes video; and a video portion that includes audio;
labeling observations of a selected mode; and
assigning semantic, multimedia content-based labels to segments of said observations of a selected mode;
wherein said assigning semantic, multimedia content-based labels comprises performing:
selecting a label from a predefined set of multimedia content descriptors; and
assigning a new label not present in said pre-defined set of multimedia content descriptors;
labeling audio while viewing video via: one or more check boxes configured for labeling foreground and background sounds, and a keyword text box; and
storing said semantic, multimedia content-based labels with the multimedia content.