J. Chen, C. M. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment, " in IEEE- SPIE Conference on Multimedia Storage and Archiving Systems IV, Boston (USA), September 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....in network access and user terminal properties. We use a clustering based approach to identify first the appropriate clusters, and then the key frames, for every shot. While other methods that utilize clustering methods to generate visual summaries have previously been proposed [14] 17] [18], one of the contributions of our paper is the use of cluster validity analysis for automatic computation of the optimal number of representative key frames for each shot. This key frame allocation approach offers a quantitative, unsupervised alternative to the heuristic, user driven methods ....

J-Y. Chen et al., "Vibe: A video indexing and browsing environment," in Proc. Multimedia Storage J Archival Systems, 1999, vol. SPIE-3846.

....Colombo et al. 1] suggest a semantic level of representation by organizing low level features into expressive and emotional levels. ViBE is developed to enable semantic browsing of the video content by integrating shot boundary detection, shot tree representation, and pseudo semantic la beling [22]. Ruiet al... 23] use relevance feedback to capture the high level subjectivity by dynamically updating feature weights. PicHunter [24] also employs relevance feedback to predict what the users search for in a Bayesian framework. The framework includes an entropy minimizing display algorithm to ....

J.-Y. Chen, C. Tskiran, A. Albiol, C.A. Bouman, and E.J. Delp, "ViBE: A Video Indexing and Browsing Environment," in Proceedings of the ISTfSPIE Conference on Storage and Retrieval for Media Databases IV, pp. 199-207, Jan. 1999.

.... quantitative evaluation of a clustering algorithm are C 1 : the determination of the number of clusters, and C 2 : the determination of the cluster label for each datum, compared to the ground truth [11] Although many algorithms for video segment clustering have been proposed [48] 46] 16] [6], 34] 21] 22] their performance using the two mentioned criteria is unknown in several cases. Furthermore, we are not aware of any comparative study of video segment clustering techniques. Table 3 compares the performance evaluation procedure of some commonly referenced algorithms, as ....

....of clusters, and C 1 and C 2 indicate whether the two above criteria were used for evaluation. NA indicates that some piece of information was not available. Reference Clips Type of Video Frames Shots E 1 C 1 C 2 [48] 1 Documentary 18000 71 Yes No No [46] 5 Movies TV 132051 1027 Yes No No [6] 23 TV 400000 NA No No No [16] 4 Movies NA NA Yes Yes Yes [34] 7 Movies 176554 1396 Yes Yes No This paper 30 Home 1075348 801 Yes Yes Yes Table 3: Performance Evaluation Procedure of Segment Clustering Algorithms 8.1 Ground truth In our database, a third party cluster ground truth was ....

J-Y Chen, C. Taskiran, A. Albiol, E. J. Delp and C. A. Bouman, ViBE: A Video Indexing and Browsing Environment, in Proc. SPIE Conf. on Multimedia Storage and Archiving Systems IV, SPIE vol. 3846, Boston, Sept 1999, pp. 148-164.

No context found.

J. Chen, C. M. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment, " in IEEE- SPIE Conference on Multimedia Storage and Archiving Systems IV, Boston (USA), September 1999.

No context found.

J. Chen, C. M. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment," in IEEE- SPIE Conference on Multimedia Storage and Archiving Systems IV, Boston (USA), September 1999.

....Segmentation after clustering the luminance histograms. h) Label erosion of size 2 of g. i) Label dilation of size 2 of j. k) Final segmentation 5. RESULTS AND CONCLUSIONS The algorithm proposed in this paper has been tested over a large number of images extracted from the VIBE video database [8]. Figure 9 shows the segmentation results for a small sample set. It can be noticed that the algorithm is able to separate the face areas from the skin colored backgrounds although in some examples the face regions are further split into two or more regions. This is not a big problem for our face ....

J. Chen, C. M. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment, " in IEEE- SPIE Conference on Multimedia Storage and Archiving Systems IV, Boston (USA), September 1999.

No context found.

J.-Y. Chen, C. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment," Proceedings of the SPIE Conference on Multimedia Storage and Archiving Systems IV, vol. 3846, September 1999, Boston, MA, pp. 148--164.

No context found.

J.-Y. Chen, C. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment," Proceedings of the SPIE Conference on Multimedia Storage and Archiving Systems IV, vol. 3846, September 1999, Boston, MA, pp. 148--164.

No context found.

J. Chen, C. M. Taskiran, A. Albiol, C. A. Bouman, and E. J. Delp, "Vibe: A video indexing and browsing environment," in IEEE- SPIE Conference on Multimedia Storage and Archiving Systems IV, Boston (USA), September 1999.

No context found.

J.-Y. Chen, C. Taskiran, A. Albiol, C.A. Bouman, and E.J. Delp, "ViBE: A Video Indexing and Browsing Environment," in Proc. of the IS&T/SPIE Conf. on Storage and Retrieval for Media Databases IV, pp. 199-207, Jan. 1999.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC