{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T14:51:51Z","timestamp":1661784711490},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,6,2]],"date-time":"2013-06-02T00:00:00Z","timestamp":1370131200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s11554-013-0357-y","type":"journal-article","created":{"date-parts":[[2013,6,1]],"date-time":"2013-06-01T04:29:05Z","timestamp":1370060945000},"page":"571-587","source":"Crossref","is-referenced-by-count":9,"title":["Exploiting task and data parallelism for advanced video coding on hybrid CPU\u00a0+\u00a0GPU platforms"],"prefix":"10.1007","volume":"11","author":[{"given":"Svetislav","family":"Momcilovic","sequence":"first","affiliation":[]},{"given":"Nuno","family":"Roma","sequence":"additional","affiliation":[]},{"given":"Leonel","family":"Sousa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,6,2]]},"reference":[{"issue":"1","key":"357_CR1","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/MCAS.2004.1286980","volume":"4","author":"J. Ostermann","year":"2004","unstructured":"Ostermann, J., Bormans, J., List, P., Marpe, D., Narroschke, M., Pereira, F., Stockhammer, T., Wedi, T.: Video coding with H.264\/AVC tools, performance, and complexity. IEEE Circuits Syst. Mag. 4(1), 7\u201328 (2004)","journal-title":"IEEE Circuits Syst. Mag."},{"issue":"7","key":"357_CR2","first-page":"668","volume":"13","author":"T. Wiegand","year":"2003","unstructured":"Wiegand, T., Schwartz, H., Kossentini, F., Ulivan G., S.: Rate-constrained coder control and comparison of video coding standards. IEEE Trans. Circuits Syst. Video Technol. 13(7), 668\u2013703 (2003)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"357_CR3","doi-asserted-by":"crossref","unstructured":"Lu, C.-T., Hang, H.-M.:Multiview encoder parallelized fast search realization on NVIDIA CUDA. In: Proc. Visual Communications and Image Processing (VCIP), IEEE, pp. 1\u20134 (2011)","DOI":"10.1109\/VCIP.2011.6116010"},{"issue":"1","key":"357_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMM.2008.2008873","volume":"11","author":"M. Schwalb","year":"2009","unstructured":"Schwalb, M., Ewerth, R., Freisleben, B.: Fast motion estimation on graphics hardware for H.264 video encoding. IEEE Trans. Multimed. 11(1), 1\u201310 (2009)","journal-title":"IEEE Trans. Multimed."},{"key":"357_CR5","doi-asserted-by":"crossref","unstructured":"Momcilovic, S., Sousa, L.: Development and evaluation of scalable video motion estimators on GPU. In: Proc. Workshop on Signal Processing Systems (SIPS) (2009)","DOI":"10.1109\/SIPS.2009.5336269"},{"key":"357_CR6","doi-asserted-by":"crossref","unstructured":"Kung, M.C., Au, O., Wong, P., Liu, C.-H.: Intra frame encoding using programmable graphics hardware. In: Proc. Pacific Rim Conference on Advances in Multimedia Information Processing (PCM), pp. 609\u2013618. Springer, Berlin (2007)","DOI":"10.1007\/978-3-540-77255-2_76"},{"key":"357_CR7","unstructured":"Obukhov, A., Kharlamovl, A.: Discrete cosine transform for 8x8 blocks with CUDA. Research report, NVIDIA, Santa Clara, CA (2008)"},{"issue":"5","key":"357_CR8","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1109\/TCSVT.2005.846440","volume":"15","author":"G. Shen","year":"2005","unstructured":"Shen, G., Gao, G.-P., Li, S., Shum, H.-Y., Zhang, Y.-Q.: Accelerate video decoding with generic GPU. IEEE Trans. Circuits Syst. Video Technol. 15(5), 685\u2013693 (2005)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"357_CR9","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/TCSVT.2011.2105553","volume":"21","author":"B. Pieters","year":"2011","unstructured":"Pieters, B., Hollemeersch, C.-F., De Cock, J., Lambert, P., De Neve, W., Vande Walle, R.: Parallel deblocking filtering in MPEG-4 AVC\/H.264 on massively parallel architectures. IEEE Trans. Circuits Syst. Video Technol. 21(1), 96\u2013100 (2011)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"357_CR10","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1109\/MSP.2009.935416","volume":"27","author":"N.-M. Cheung","year":"2010","unstructured":"Cheung, N.-M., Fan, X., Au O., C., Kung, M.-C.: Video coding on multicore graphics processors. IEEE Signal Process. Mag. 27(2), 79\u201389 (2010)","journal-title":"IEEE Signal Process. Mag."},{"key":"357_CR11","doi-asserted-by":"crossref","unstructured":"Azevedo, A., Juurlink, B., Meenderinck, C., Terechko, A., Hoogerbrugge, J., Alvarez, M., Ramirez, A., Valero, M.: A highly scalable parallel implementation of H.264. In: Transactions on High-Performance Embedded Architectures and Compilers (HiPEAC), pp. 111\u2013134 (2011)","DOI":"10.1007\/978-3-642-24568-8_6"},{"key":"357_CR12","unstructured":"Chen, W.-N., Hang, H.-M.: H.264\/AVC motion estimation implementation on Compute Unified Device Architecture (CUDA). In: Proc. International Conference on Multimedia and Expo (ICME), pp. 697\u2013700 (2008)"},{"key":"357_CR13","doi-asserted-by":"crossref","unstructured":"Momcilovic, S., Roma, N., Sousa, L.: Multi-level parallelization of advanced video coding on hybrid CPU\/GPU platform. In: Proceedings of the 10th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar\/Euro-Par 2012) (2012)","DOI":"10.1007\/978-3-642-36949-0_19"},{"key":"357_CR14","first-page":"905","volume":"2","author":"H.F. Ates","year":"2005","unstructured":"Ates, H.F., Altunbasak, Y.: SAD reuse in hierarchical motion estimation for the H.264 encoder. Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP) 2, 905\u2013908 (2005)","journal-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)"},{"key":"357_CR15","unstructured":"First the Tick, Now the Tock: Next Generation Intel Microarchitecture (Nehalem). Intel Corporation (2008)"},{"issue":"4","key":"357_CR16","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/MM.2008.57","volume":"28","author":"M. Garland","year":"2008","unstructured":"Garland, M., Le Grand, S., Nickolls, J., Anderson, J., Hardwick, J., Morton, S., Phillips, E., Zhang, Y., Volkov, V.: Parallel computing experiences with CUDA. IEEE Micro 28(4), 13\u201327 (2008)","journal-title":"IEEE Micro"},{"issue":"2","key":"357_CR17","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J. Nickolls","year":"2008","unstructured":"Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable parallel programming with CUDA. Queue 6(2), 40\u201353 (2008)","journal-title":"Queue"},{"issue":"1","key":"357_CR18","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"E.W. Dijkstra","year":"1959","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs. Numer. Math. 1(1), 269\u2013271 (1959)","journal-title":"Numer. Math."},{"key":"357_CR19","unstructured":"Chapman, B., Jost, G., van der Pas, R.: Using OpenMP: Portable Shared Memory Parallel Programming (Scientific and Engineering Computation). The MIT Press, Cambridge (2007)"},{"key":"357_CR20","unstructured":"Intel Corporation. SSE4 Programming Reference (2007). http:\/\/edc.intel.com\/Link.aspx?id=1630"},{"key":"357_CR21","unstructured":"Momcilovic, S., Ilic, A., Roma, N., Sousa, L.: Advanced Video Coding on CPUs and GPUs: Parallelization and RD Analysis. Technical report (available online), INESC-ID (2013)"},{"key":"357_CR22","doi-asserted-by":"crossref","unstructured":"Aji, A.M., Feng, W., Blagojevic, F., Nikolopoulos, D.S.: Cell-SWat: modeling and scheduling wavefront computations on the cell broadband engine. In: CF \u201908: Proceedings of the 5th Conference on Computing Frontiers, pp. 13\u201322. ACM, New York (2008) (ISBN 978-1-60558-077-7)","DOI":"10.1145\/1366230.1366235"},{"key":"357_CR23","unstructured":"ITU-T. JVT Reference Software, version 17.2 (2010). http:\/\/iphome.hhi.de\/suehring\/tml\/download"},{"key":"357_CR24","unstructured":"Tan, T.; Sullivan,G.; Wedi. Recommended simulation common conditions for coding efficiency experiments-revision 3. Doc. VCEG-AI10, ITU-Telecommunications Standardization Sector, STUDY GROUP 16 Question 6, Video Coding Experts Group (VCEG), Lisbon, Portugal (2008)"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-013-0357-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11554-013-0357-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-013-0357-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,14]],"date-time":"2019-07-14T06:08:27Z","timestamp":1563084507000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11554-013-0357-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,2]]},"references-count":24,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["357"],"URL":"https:\/\/doi.org\/10.1007\/s11554-013-0357-y","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,2]]}}}