Video Scene and Event Detection
A video scene, also called a logical story unit  or simply a story unit, can be defined as a semantically related consecutive series of image frames that depict and convey a high-level concept such as event, topic, object, location, and action, which constitutes a story in a video. Especially, an event can be defined as an incident or situation, which occurs in a particular place during a particular interval of time, for example – homerun in a baseball game, actor’s entrance on stage, car explosion on a highway, etc. Under these definitions, video scene and event detection is used to find all video intervals corresponding to a specific event from a given video.
Video scene and event detection has been an active research area in the community of multimedia signal processing and computer vision and has attracted much interest in many applications such as multimedia information retrieval, video archive indexing...
- 1.Adams B, Amir A, Iyengar G, Lin C-Y, Naphade M, Neti C, Smith JR. Semantic indexing of multimedia content using visual, audio and text cues. EURASIP J Appl Signal Proc. 2003;2:1–16.Google Scholar
- 3.Babaguchi N, Nitta N. Intermodal collaboration: a strategy for semantic content analysis for broadcasted sports video. In Proc Int Conf Image Proc. 2003;1:13–6.Google Scholar
- 5.Goh K-S, Miyahara K, Radhakrishan R, Xiong Z, Divakaran A. Audio-visual event detection based on mining of semantic audio-visual labels. MERL, TR-2004-008. 2004.Google Scholar
- 6.Gong Y, Xu W. Machine learning for multimedia content analysis. Berlin: Springer; 2007.Google Scholar
- 8.Hauptmann AG, Smith MA. Text, speech, and vision for video segmentation: the informedia project. In: Proceedings of the AAAI Symposium on Computational Models for Integrating Language and Vision; 1995. p. 90–5.Google Scholar
- 11.Merlino A, Morey D, Maybury M. Broadcast news navigation using story segmentation. In: Proceedings of the 5th ACM International Conference on Multimedia; 1997. p. 381–91.Google Scholar
- 14.The National Institute of Standards and Technology (NIST). TREC video retrieval evaluation. 2001–2014. http://www-nlpir.nist.gov/projects/trecvid/