{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:14Z","timestamp":1763468234012},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/icme.2014.6890234","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T11:47:19Z","timestamp":1410349639000},"page":"1-6","source":"Crossref","is-referenced-by-count":14,"title":["Improved audio features for large-scale multimedia event detection"],"prefix":"10.1109","author":[{"given":"Florian","family":"Metze","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shourabh","family":"Rawat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"0","journal-title":"Proc INTERSPEECH [27]"},{"key":"ref11","article-title":"Compact audio representation for event detection in consumer media","author":"zhuang","year":"0","journal-title":"Proc INTERSPEECH [27]"},{"key":"ref12","article-title":"Robust event detection from spoken content in consumer domain videos","author":"tsakalidis","year":"0","journal-title":"Proc INTERSPEECH [27]"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072059"},{"journal-title":"2013 TRECVID Multimedia Event Detection Track","year":"2013","key":"ref14"},{"journal-title":"A Complete Cross-platform Solution to Record Convert and Stream Audio and Video","year":"2013","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034625"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637765"},{"journal-title":"Speech and Signal Processing ICASSP 2013","article-title":"IEEE International Conference on Acoustics","year":"2013","key":"ref28"},{"key":"ref4","article-title":"Noisemes: Manual annotation of environmental noise in audio streams","author":"susanne","year":"2012","journal-title":"Tech Rep CM U-LT I-12–07"},{"journal-title":"13th Annual Conference of the International Speech Communication Association","article-title":"INTERSPEECH 2012","year":"2012","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","article-title":"Audio concept ranking for video event detection on user-generated content","author":"elizalde","year":"2013","journal-title":"Proceedings of the First Workshop on Speech Language and Audio in Multimedia (SLAM)"},{"key":"ref5","article-title":"Event-based video retrieval using audio","author":"qin","year":"0","journal-title":"Proc INTERSPEECH [27]"},{"key":"ref8","article-title":"IBM Research and Columbia University TRECVID-2011 Multimedia Event Detection (MED) System","author":"cao","year":"2011","journal-title":"Proc TRECVID"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2390214.2390219"},{"key":"ref2","article-title":"Creating HAVIC: Heterogeneous audio visual internet collection","author":"strassel","year":"2012","journal-title":"Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)"},{"key":"ref9","article-title":"Robust audio codebooks for large scale event detection in consumer videos","author":"rawat","year":"2013","journal-title":"Proc Interspeech Lyon France"},{"key":"ref1","article-title":"TRECVID 2013 - An introduction to the goals, tasks, data, evaluation mechanisms, and metrics","author":"over","year":"2013","journal-title":"Proc TRECVID"},{"key":"ref20","article-title":"Optimizing bottleneck features for LVCSR","author":"grezl","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref24","article-title":"A large set of audio features for sound description (similarity and classification) in the CUIDADO project","author":"peeters","year":"2004","journal-title":"Tech Rep IRCAM"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: a CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference (SciPy)"},{"key":"ref26","first-page":"8663","article-title":"Subband auto-correlation features for video soundtrack classification","author":"cotton","year":"0","journal-title":"Proc ICASSP [28]"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"}],"event":{"name":"2014 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2014,7,14]]},"location":"Chengdu, China","end":{"date-parts":[[2014,7,18]]}},"container-title":["2014 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6882588\/6890121\/06890234.pdf?arnumber=6890234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T11:18:22Z","timestamp":1602674302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6890234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme.2014.6890234","relation":{},"subject":[],"published":{"date-parts":[[2014,7]]}}}