{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:28:49Z","timestamp":1780421329455,"version":"3.54.1"},"reference-count":74,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2003,6,1]],"date-time":"2003-06-01T00:00:00Z","timestamp":1054425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2003,6]]},"DOI":"10.1016\/s1047-3203(03)00019-1","type":"journal-article","created":{"date-parts":[[2003,5,13]],"date-time":"2003-05-13T01:09:24Z","timestamp":1052788164000},"page":"150-183","source":"Crossref","is-referenced-by-count":94,"title":["Survey of compressed-domain features used in audio-visual indexing and analysis"],"prefix":"10.1016","volume":"14","author":[{"given":"Hualu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Divakaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony","family":"Vetro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huifang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/S1047-3203(03)00019-1_BIB1","doi-asserted-by":"crossref","unstructured":"Akutsu, A., Tonomura, Y., Hashimoto, H., Ohba, Y., 1992. Video indexing using motion vectors. In: Proc. SPIE Conf. on Visual Communications and Image Processing, SPIE vol. 1818, pp. 1522\u20131530","DOI":"10.1117\/12.131425"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB2","doi-asserted-by":"crossref","unstructured":"Ardizzone, E., La Cascia, M., Avanzato, A., Bruna, A., 1999. Video indexing using MPEG motion compensation vectors. In: Proc. IEEE Internat. Conf. on Multimedia Computing and Systems, 1999","DOI":"10.1109\/MMCS.1999.778574"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB3","doi-asserted-by":"crossref","unstructured":"Ardizzone, E., La Cascia, M., Molinelli, E., 1996. Motion and color based video indexing and retrieval. In: Proc. Internat. Conf. on Pattern Recognition","DOI":"10.1109\/ICPR.1996.546809"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB4","doi-asserted-by":"crossref","unstructured":"Arman, F., Hsu, A., Chiu, M.-Y., 1993. Image processing on compressed data for large video databases. In: Proc. ACM Multimedia 93, Anaheim, CA, pp. 267\u2013272","DOI":"10.1145\/166266.166297"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB5","doi-asserted-by":"crossref","unstructured":"Bao, O.K.-C., Lay, J.A., Guan, L., 2000. Compressed domain video parsing using energy histograms of the lower frequency DCT coefficients. Proc. SPIE Conference on Storage and Retrieval for Multimedia Database 2000, San Jose, CA, January, pp. 293\u2013300","DOI":"10.1117\/12.373561"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB6","doi-asserted-by":"crossref","unstructured":"Bergen, J.R., Anandan, P., Hanna, K.J., Hingorani, R., 1992. Hierarchical model-based motion estimation. In: Proc. 2nd European Conf. on Computer Vision","DOI":"10.1007\/3-540-55426-2_27"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB7","doi-asserted-by":"crossref","unstructured":"Boccignone, G., De Santo, M., Percannella, G., 2000. An algorithm for video cut detection in MPEG sequences. In: Proc. SPIE Conf. on Storage and Retrieval of Media Databases 2000, San Jose, CA, January, pp. 523\u2013530","DOI":"10.1117\/12.373585"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB8","doi-asserted-by":"crossref","unstructured":"Boreczky, J.S., Rowe, L.A., 1996. Comparison of video shot boundary detection techniques. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases IV, January, pp. 170\u2013179","DOI":"10.1117\/12.238675"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB9","unstructured":"Chang, S.-F., Messerschmit, D.G., 1995. Manipulation and compositing of MC-DCT compressed video, IEEE J. Selected Areas Commun. Special Issue on Intelligent Signal Processing, January, pp. 1\u201311"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB10","unstructured":"Chen, J.-Y., Taskiran, C., Delp, E.J., Bouman, C.A., 1998. ViBE: a new paradigm for video database browsing and search. In: Proc. IEEE Workshop on Content-Based Access of Image and Video Databases"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB11","unstructured":"Davis, J.W., 1998. Recognizing movement using motion histograms. Technical Report No. 487, MIT Media Laboratory Perceptual Computing Section, April"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB12","doi-asserted-by":"crossref","unstructured":"Dimitrova, N., Golshani, F., 1995. Motion recovery for video content analysis. ACM Trans. Information Systems vol. 13, No. 4, October, pp. 408-439","DOI":"10.1145\/211430.211433"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB13","doi-asserted-by":"crossref","unstructured":"Divakaran, A., Ito, H., Sun, H., Poon, T., 1999. Scene change detection and feature extraction for MPEG-4 sequences. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 545\u2013551","DOI":"10.1117\/12.333874"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB14","doi-asserted-by":"crossref","unstructured":"Divakaran, A., Sun, H., 2000. A descriptor for spatial distribution of motion activity for compressed video. In: Proc. SPIE Conf. on Storage and Retrieval for Media Databases 2000, San Jose, CA, January, pp. 392\u2013398","DOI":"10.1117\/12.373571"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB15","unstructured":"Dolby Laboratories, Dolby AC-3: Multi-channel perceptual coding. Available from http:\/\/www.dolby.com\/tech\/multipc.html, 1997"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB16","unstructured":"Eng, H.-L., Ma, K.-K., 1999. Motion trajectory extraction based on macroblock motion vectors for video indexing. In: Proc. IEEE Internat. Conf. on Image Processing, Kobe, Japan, October"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB17","doi-asserted-by":"crossref","unstructured":"Faloutsos, C., Lin, K., 1995. FastMap: a fast algorithm for indexing, data mining, and visualization of traditional and multimedia databases. In: Proc. ACM SIGMOD Conf., pp. 163\u2013174","DOI":"10.1145\/223784.223812"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB18","doi-asserted-by":"crossref","unstructured":"Feng, J., Lo, K.T., Mehrpour, H., 1996. Scene change detection algorithm for MPEG video sequence. In: Proc. IEEE Internat. Conf. on Image Processing, Lausanne, Switzerland","DOI":"10.1109\/ICIP.1996.561031"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB19","doi-asserted-by":"crossref","unstructured":"Fernando, W.A.C., Canagarajah, C.N., Bull, D.R., 1999. Video segmentation and classification for content based storage and retrieval using motion vectors. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 687\u2013698","DOI":"10.1117\/12.333889"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB20","doi-asserted-by":"crossref","unstructured":"Ford, R.M., 1999. A quantitative comparison of shot boundary detection metrics. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 666\u2013676","DOI":"10.1117\/12.333887"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB21","series-title":"Digital Video: An Introduction to MPEG-2","author":"Haskell","year":"1997"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB22","doi-asserted-by":"crossref","unstructured":"He, L., Sanocki, E., Gupta, A., Grudin, J., 1999. Auto-summarization of audio-video presentations. In: Proc. ACM Multimedia 99, Orlando, FL, October, pp. 489\u2013498","DOI":"10.1145\/319463.319691"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB23","doi-asserted-by":"crossref","unstructured":"Ho, Y.S., Gersho, A., 1989. Classified transform coding of images using vector quantization. In: Proc. ICASSP 89, pp. 1890\u20131893","DOI":"10.1109\/ICASSP.1989.266823"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB24","unstructured":"Huang, J., Liu, Z., Wang, Y., 1998. Integration of audio and visual information for content-based video segmentation. In: Proc. IEEE Internat. Conf. on Image Processing"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB25","unstructured":"ISO\/IEC IS 11172\u20142, MPEG-1 Video, 1993"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB26","unstructured":"ISO\/IEC IS 11172\u20143, MPEG-1 Audio, 1993"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB27","unstructured":"ISO\/IEC IS 13818\u20142, MPEG-2 Video, 1996"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB28","unstructured":"ISO\/IEC IS 13818\u20143, MPEG-2 Audio BC, 1996"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB29","unstructured":"ISO\/IEC IS 13818\u20147, MPEG-2 Audio AAC, 1997"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB30","doi-asserted-by":"crossref","unstructured":"Kobla, V., DeMenthon, D., Doermann, D., 1999. Detection of slow-motion replay sequences for identifying sports videos. In: Proc. IEEE Workshop on Multimedia Signal Processing","DOI":"10.1109\/MMSP.1999.793810"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB31","doi-asserted-by":"crossref","unstructured":"Kobla, V., DeMenthon, D., Doermann, D., 1999. Special effect edit detection using VideoTrails: a comparison with existing techniques. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII","DOI":"10.1117\/12.333850"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB32","doi-asserted-by":"crossref","unstructured":"Kobla, V., Doermann, D., Faloutsos, C., 1997. VideoTrails: representing and visualizing structure in video sequences. In: Proc. ACM Multimedia 97, pp. 335\u2013346","DOI":"10.1145\/266180.266384"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB33","doi-asserted-by":"crossref","unstructured":"Kobla, V., Doermann, D., Lin, K.-I., 1996. Archiving, indexing, and retrieval of video in the compressed domain. In: Proc. SPIE Conf. on Multimedia Storage and Archiving Systems, SPIE vol. 2916, pp. 78\u201389","DOI":"10.1117\/12.257312"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB34","doi-asserted-by":"crossref","unstructured":"Kobla, V., Doermann, D., Lin, K.-I., Faloutsous, C., 1997. Compressed domain video indexing techniques using DCT and motion vector information in MPEG video. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases V, SPIE vol. 3022, pp. 200\u2013211","DOI":"10.1117\/12.263408"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB35","doi-asserted-by":"crossref","unstructured":"Lienhart, R., 1999. Comparison of automatic shout boundary detection algorithms. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 290\u2013301","DOI":"10.1117\/12.333848"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB36","doi-asserted-by":"crossref","unstructured":"Meng, J., Chang, S.-F., 1996. CVEPS\u2014a compressed video editing and parsing system. In: Proc. ACM Multimedia 96","DOI":"10.1145\/244130.244145"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB37","doi-asserted-by":"crossref","unstructured":"Meng, J., Juan, Y., Chang, S.-F., 1995. Scene change detection in an MPEG compressed video sequence. In: IS & T\/SPIE Symposium Proceedings, vol. 2419, San Jose, CA, February","DOI":"10.1117\/12.206359"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB38","doi-asserted-by":"crossref","unstructured":"Nang, J., Hong, S., Ihm, Y., 1999. An efficient video segmentations scheme for MPEG video stream using macroblock information. In: Proc. ACM Multimedia 99, Orlando, FL, October, pp. 23\u201326","DOI":"10.1145\/319463.320047"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB39","doi-asserted-by":"crossref","unstructured":"Naphade, M.R., Kristjansson, T., Frey, B.J., Huang, T.S., 1998. Probabilistic multimedia objects (Multijects): a novel approach to video indexing and retrieval in multimedia systems. In: Proc. IEEE Internat. Conf. on Image Processing, vol. 5, Chicago, IL, October","DOI":"10.1109\/ICIP.1998.999041"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB40","doi-asserted-by":"crossref","unstructured":"Naphade, M.R., Huang, T.S., 2000. A probabilistic framework for semantic indexing and retrieval in video. In: Proc. IEEE Internat. Conf. on Multimedia and Expo, vol. 1, New York, NY, July\u2013August","DOI":"10.1109\/ICME.2000.869642"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB41","unstructured":"Ngo, C.W., Pong, T.C., Zhang, H.J., Chin, R.T., 2000. Motion characterization by temporal slice analysis. In: Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, vol. 2, Hilton Head Island, SC, June 13\u201315"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB42","doi-asserted-by":"crossref","unstructured":"Ngo, C.W., Pong, T.C., Zhang, H.J., 2001. On clustering video shots. In: Proc. ACM Multimedia 2001, Ottawa, Ont., Canada, September 30\u2013October 5, pp. 51\u201360","DOI":"10.1145\/500141.500151"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB43","doi-asserted-by":"crossref","unstructured":"Patel, N.V., Sethi, I.K., 1995. Audio characterization for video indexing. In: Proc. SPIE Conference on Storage & Retrieval for Image and Video Databases IV, San Jose, CA, February","DOI":"10.1117\/12.234776"},{"issue":"4","key":"10.1016\/S1047-3203(03)00019-1_BIB44","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1016\/S0031-3203(96)00114-8","article-title":"Video shot detection and characterization for video databases","volume":"30","author":"Patel","year":"1997","journal-title":"Patter Recognition"},{"issue":"2","key":"10.1016\/S1047-3203(03)00019-1_BIB45","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/76.564111","article-title":"Robust methods for high quality stills from interlaced video in the presence of dominant motion","volume":"7","author":"Patti","year":"1997","journal-title":"IEEE Trans. Circuits Systems Video Technol."},{"key":"10.1016\/S1047-3203(03)00019-1_BIB46","series-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB47","doi-asserted-by":"crossref","unstructured":"Saunders, J., 1996. Real-time discrimination of broadcast speech\/music. In: Proc. ICASSP 96, pp. 993\u2013996","DOI":"10.1109\/ICASSP.1996.543290"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB48","doi-asserted-by":"crossref","unstructured":"Saur, D.D., Tan, Y.-P., Kulkarni, S.R., Ramadge, P.J., 1997. Automated analysis and annotation of basketball video. In: Proc. SPIE Conf. Storage and Retrieval for Image and Video Databases V, SPIE vol. 3022, pp. 176\u2013187","DOI":"10.1117\/12.263406"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB49","unstructured":"Scheirer, E., Slaney, M., 1997. Construction and evaluation of a robust multi-feature speech\/music discriminator. In: Proc. ICASSP 97"},{"issue":"4","key":"10.1016\/S1047-3203(03)00019-1_BIB50","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1006\/jvci.1996.0035","article-title":"Convolution-based edge detection for image\/video in block DCT domain","volume":"7","author":"Shen","year":"1996","journal-title":"J. Visual Commun. Image Representation"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB51","doi-asserted-by":"crossref","unstructured":"Shen, B., Sethi, I.K., 1996. Direct feature extraction from compressed images. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Database IV, January","DOI":"10.1117\/12.234779"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB52","doi-asserted-by":"crossref","unstructured":"Shen, K., Delp, E., 1995. A fast algorithm for video parsing using MPEG compressed sequences. In: Proc. IEEE Internat. Conf. on Image Processing, vol. 2, pp. 252\u2013255","DOI":"10.1109\/ICIP.1995.537462"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB53","doi-asserted-by":"crossref","unstructured":"Song, B.C., Ra, J.B., 1999. Fast edge map extraction from MPEG compressed video data for video parsing. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 710\u2013721","DOI":"10.1117\/12.333891"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB54","doi-asserted-by":"crossref","unstructured":"Srinivasan, S., Petkovic, D., Ponceleon, D., 1999. Towards robust features for classifying audio in the CueVideo system. In: Proc. ACM Multimedia 99, Orlando, FL, October, pp. 393\u2013400","DOI":"10.1145\/319463.319658"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB55","doi-asserted-by":"crossref","unstructured":"Sundaram, H., Chang, S.-F., 2000. Audio scene segmentation using multiple models, features and time scales. In: Proc. ICASSP 2000, Istanbul, Turkey, June","DOI":"10.1109\/ICASSP.2000.859335"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB56","doi-asserted-by":"crossref","unstructured":"Sundaram, H., Chang, S.-F., 2000. Determining computable scenes in films and their structures using audio-visual memory models. In: Proc. ACM Multimedia 2000, Los Angeles, CA, October\u2013November","DOI":"10.1145\/354384.354440"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB57","unstructured":"Tan, Y.-P., Kulkarni, S.R., Ramadge, P.J., 1999. A framework for measuring video similarity and its application to video query by example. In: Proc. IEEE Internat. Conf. on Image Processing, Kobe, Japan, October"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB58","doi-asserted-by":"crossref","unstructured":"Tan, Y.-P., Kulkarni, S.R., Ramadge, P.J., 1995. A new method for camera motion parameter estimation. In: Proc. IEEE Internat. Conf. on Image Processing, vol. 1, pp. 406\u2013409","DOI":"10.1109\/ICIP.1995.529732"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB59","unstructured":"Tan, Y.-P., Saur, D.D., Kulkarni, S.R., Ramadge, P.J., 1999. Rapid estimation of camera motion from compressed video with application to video annotation. In: IEEE Trans. on Circuits and Systems for Video Technology"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB60","doi-asserted-by":"crossref","unstructured":"Taniguchi, Y., Akutsu, A., Tonomura, Y., 1997. PanoramaExcerpts: extracting and packing panoramas for video browsing. In: Proc. ACM Multimedia 97, pp. 427\u2013436","DOI":"10.1145\/266180.266396"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB61","doi-asserted-by":"crossref","unstructured":"Tse, Y.T., Baker, R.L., 1991. Camera zoom\/pan estimation and compensation fore video compression. In: Proc. SPIE Conf. on Image Processing Algorithms and Techniques II, Boston, MA, pp. 468\u2013479","DOI":"10.1117\/12.45404"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB62","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, J., Liu, Z., Chen, T., 1997. Multimedia content classification using motion and audio information. In: Proc. ISCAS 97, vol. 2, Hong Kong, June, pp. 1488\u20131491","DOI":"10.1109\/ISCAS.1997.622200"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB63","doi-asserted-by":"crossref","unstructured":"Wolf, W., 1996. Key frame selection by motion analysis. In: Proc. ICASSP 96, vol. II, pp. 1228\u20131231","DOI":"10.1109\/ICASSP.1996.543588"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB64","doi-asserted-by":"crossref","unstructured":"Won, C.S., Park, D.K., Na, I.Y., Yoo, S.-J., 1999. Efficient color feature extraction in compressed video. In: Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases VII, San Jose, CA, January, pp. 677\u2013686","DOI":"10.1117\/12.333888"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB65","doi-asserted-by":"crossref","unstructured":"Yeo, B.-L., Liu, B., 1995a. On the extraction of DC sequence from MPEG video. In: Proc. IEEE Internat. Conf. on Image Processing, vol. 2, pp. 260\u2013263","DOI":"10.1109\/ICIP.1995.537464"},{"issue":"6","key":"10.1016\/S1047-3203(03)00019-1_BIB66","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/76.475896","article-title":"Rapid scene analysis on compressed videos","volume":"5","author":"Yeo","year":"1995","journal-title":"IEEE Trans. Circuits Systems Video Technol.fs"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB67","unstructured":"Yeo, B.-L., Liu, B., 1995c. Unified approach to temporal segmentation of Motion JPEG and MPEG video. In: Proc. Internat. Conf. on Multimedia Computing and Systems, pp. 2\u201313"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB68","doi-asserted-by":"crossref","unstructured":"Yoshida, T., Sakai, Y., 1995. Reliability metric of motion vectors and its application to motion estimation. In: Proc. SPIE Conference on Visual Communications and Image Processing 95, pp. 799\u2013809","DOI":"10.1117\/12.206786"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB69","doi-asserted-by":"crossref","unstructured":"Zabih, R., Miller, J., Mai, K., 1995. A feature-based algorithm for detecting and classifying scene breaks. In: Proc. ACM Multimedia 95, San Francisco, CA, November, pp. 189\u2013200","DOI":"10.1145\/217279.215266"},{"issue":"1","key":"10.1016\/S1047-3203(03)00019-1_BIB70","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/BF01261227","article-title":"Video parsing and browsing using compressed data","volume":"1","author":"Zhang","year":"1995","journal-title":"Multimedia Tools Appl."},{"issue":"1","key":"10.1016\/S1047-3203(03)00019-1_BIB71","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1007\/BF01210504","article-title":"Automatic partitioning of full-motion video","volume":"1","author":"Zhang","year":"1993","journal-title":"Multimedia Syst. J."},{"key":"10.1016\/S1047-3203(03)00019-1_BIB72","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kuo, C.-C.J., 1999a. Heuristic approach for generic audio data segmentation and annotation. In: Proc. ACM Multimedia 99, Orlando, FL, October, pp. 67\u201376","DOI":"10.1145\/319463.319471"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB73","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kuo, C.-C.J., 1999b. Hierarchical classification of audio data for archiving and retrieving. In: Proc. ICASSP 99, vol. 6, pp. 3001\u20133004","DOI":"10.1109\/ICASSP.1999.757472"},{"key":"10.1016\/S1047-3203(03)00019-1_BIB74","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Zhang, H.J., Jain, A.K., 1999. Automatic caption localization in compressed video. In: Proc. IEEE Internat. Conf. on Image Processing, Kobe, Japan, October","DOI":"10.1109\/ICIP.1999.822862"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320303000191?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320303000191?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T16:05:52Z","timestamp":1734019552000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320303000191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,6]]},"references-count":74,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2003,6]]}},"alternative-id":["S1047320303000191"],"URL":"https:\/\/doi.org\/10.1016\/s1047-3203(03)00019-1","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2003,6]]}}}