Zobrazeno 1 - 10
of 18
pro vyhledávání: '"O Connor, N. E."'
Autor:
Linardos, P., Mohedano, E., Nieto, J. J., O Connor, N. E., Giro-I-Nieto, X., Kevin McGuinness
Publikováno v:
Linardos, Panagiotis, Mohedano, Eva, Nieto, Juan Jose, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 , Giró-i-Nieto, Xavier ORCID: 0000-0002-9935-5332 and McGuinness, Kevin ORCID: 0000-0003-1336-6477 (2019) Simple vs complex temporal recurrences for video saliency prediction. In: 30th British Machine Vision Conference (BMVC), 9-12 Sept 2019, Cardiff, Wales, UK.
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Scopus-Elsevier
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Scopus-Elsevier
This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f163141cfc72a4d676766f82275b38ed
https://hdl.handle.net/2117/179382
https://hdl.handle.net/2117/179382
Autor:
Destelle, F., Ahmadi, A., O Connor, N. E., Moran, K., Anargyros Chatzitofis, Zarpalas, D., Daras, P.
Publikováno v:
Scopus-Elsevier
Destelle, Francois, Ahmadi, Amin, O'Connor, Noel E. ORCID: 0000-0002-4033-9135, Moran, Kieran ORCID: 0000-0003-2015-8967 , Chatzitofis, Anargyros, Zarpalas, Dimitrios ORCID: 0000-0002-9649-9306 and Daras, Petros (2014) Low-cost accurate skeleton tracking based on fusion of kinect and wearable inertial sensors. In: 22nd European Signal Processing Conference (EUSIPCO 2014), 1-5 Sept 2014, Lisbon, Portugal.
Destelle, Francois, Ahmadi, Amin, O'Connor, Noel E. ORCID: 0000-0002-4033-9135
In this paper, we present a novel multi-sensor fusion method to build a human skeleton. We propose to fuse the joint po- sition information obtained from the popular Kinect sensor with more precise estimation of body segment orientations provided by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8fec98bcd47440c5cfb006eacc4fa33
Insight Centre for Data Analytics (DCU) at TRECVid 2014: instance search and semantic indexing tasks
Autor:
Mcguinness, K., Mohedano, E., Zhang, Z., Feiyan Hu, Albatal, R., Gurrin, C., O Connor, N. E., Smeaton, A. F., Salvador, A., Giró-I-Nieto, X., Ventura, C.
Publikováno v:
Scopus-Elsevier
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
Universitat Jaume I
McGuinness, Kevin ORCID: 0000-0003-1336-6477, Mohedano, Eva, Zhang, Zhenxing, Hu, Feiyan ORCID: 0000-0001-7451-6438 , Albatal, Rami ORCID: 0000-0002-9269-8578 , Gurrin, Cathal ORCID: 0000-0003-2903-3968 , O'Connor, Noel E. ORCID: 0000-0002-4033-9135 , Smeaton, Alan F. ORCID: 0000-0003-1028-8389 , Salvador, Amaia, Giró-i-Nieto, Xavier ORCID: 0000-0002-9935-5332 and Ventura, Carles (2014) Insight Centre for Data Analytics (DCU) at TRECVid 2014: instance search and semantic indexing tasks. In: TRECVid 2014, 8-12 Nov 2014, Orlando FL..
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
Universitat Jaume I
McGuinness, Kevin ORCID: 0000-0003-1336-6477
Insight-DCU participated in the instance search (INS) and semantic indexing (SIN) tasks in 2014. Two very different approaches were submitted for instance search, one based on features extracted using pre-trained deep convolutional neural networks (C
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f062a29f1bfd2a045c9fa04ef57e26fd
https://hdl.handle.net/2117/24915
https://hdl.handle.net/2117/24915
Publikováno v:
Scopus-Elsevier
In this paper we describe our system and experiments performed for both the automatic search task and the event detection task in TRECVid 2008. For the automatic search task for 2008 we submitted 3 runs utilizing only visual retrieval experts, contin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8e8d7573f668ed94f8e704eede7233e6
http://doras.dcu.ie/2172/1/dcunotebook2008.pdf
http://doras.dcu.ie/2172/1/dcunotebook2008.pdf
Publikováno v:
Scopus-Elsevier
In this paper we describe our retrieval system and experiments performed for the automatic search task in TRECVid 2007. We submitted the following six automatic runs: • F A 1 DCU-TextOnly6: Baseline run using only ASR/MT text features. • F A 1 DC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::33e203d57260692d49025779062bd514
http://doras.dcu.ie/431/1/trecvid_2007_3.pdf
http://doras.dcu.ie/431/1/trecvid_2007_3.pdf
Publikováno v:
European Signal Processing Conference (Eusipco)
European Signal Processing Conference (Eusipco), 2007, Poznan, Poland
Scopus-Elsevier
European Signal Processing Conference (Eusipco), 2007, Poznan, Poland
Scopus-Elsevier
International audience; A system is presented for analysing drum performance video sequences. A novel ellipse detection algorithm is introduced that automatically locates drum tops. This algorithm fits ellipses to edge clusters, and ranks them accord
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::887d2fc563dc721fa88fb6d5fb4a0b52
https://hal.telecom-paris.fr/hal-03153911
https://hal.telecom-paris.fr/hal-03153911
Publikováno v:
Scopus-Elsevier
In this paper we describe our retrieval system and experiments performed for the automatic search task in TRECVid 2006. We submitted the following six automatic runs: • F A 1 DCU-Base 6: Baseline run using only ASR/MT text features. • F A 2 DCU-T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::870698a28cf61fcec183160872218958
http://doras.dcu.ie/428/1/trecvid_2006.pdf
http://doras.dcu.ie/428/1/trecvid_2006.pdf
Publikováno v:
Scopus-Elsevier
Arazo Sánchez, Eric, Ortego, Diego ORCID: 0000-0002-1011-3610, Albert, Paul, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and McGuinness, Kevin ORCID: 0000-0003-1336-6477 (2019) Unsupervised label noise modeling and loss correction. In: International Conference on Machine Learning (ICML), 10-15 June 2019, Long Beach, CA, USA.
Arazo Sánchez, Eric, Ortego, Diego ORCID: 0000-0002-1011-3610
Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks tend to fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::448169cf098a74e3a4f800829ad2eb79
http://www.scopus.com/inward/record.url?eid=2-s2.0-85078000343&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85078000343&partnerID=MN8TOARS
Autor:
Wilkins, P., Byrne, D., Jones, G. J. F., Lee, H., Keenan, G., Kevin McGuinness, O Connor, N. E., O Hare, N., Smeaton, A. F., Adamek, T., Troncy, R., Amin, A., Benmokhtar, R., Dumont, E., Huet, B., Merialdo, B., Tolias, G., Spyrou, E., Avrithis, Y., Papadopoulous, G. T., Mezaris, V., Kompatsiaris, I., Mörzinger, R., Schallauer, P., Bailer, W., Chandramouli, K., Izquierdo, E., Goldmann, L., Haller, M., Samour, A., Corbet, A., Sikora, T., Praks, P., Hannah, D., Halvey, M., Hopfgartner, F., Villa, R., Punitha, P., Goyal, A., Jose, J. M.
Publikováno v:
Scopus-Elsevier
TRECVID 2008
TRECVID 2008
In this paper we describe K-Space’s participation in\ud TRECVid 2008 in the interactive search task. For 2008\ud the K-Space group performed one of the largest interactive\ud video information retrieval experiments conducted\ud in a laboratory sett
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::20c6fca297b2e0aa144d8377b9642699
http://www.scopus.com/inward/record.url?eid=2-s2.0-84905193177&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-84905193177&partnerID=MN8TOARS
Autor:
Wilkins, P., Adamek, T., Ferguson, P., Hughes, M., Jones, G. J. F., Keenan, G., Mcguinness, K., Malobabić, J., O Connor, N. E., Sadlier, D., Smeaton, A. F., Benmokhtar, R., Dumont, E., Huet, B., Merialdo, B., Spyrou, E., Koumoulos, G., Avrithis, Y., Moerzinger, R., Schallauer, P., Bailer, W., Zhang, Q., Piatrik, T., Krishna Chandramouli, Izquierdo, E., Goldmann, L., Haller, M., Sikora, T., Praks, P., Urban, J., Hilaire, X., Jose, J. M.
Publikováno v:
Scopus-Elsevier
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1c8118c6fa27086dc151383407a709be
http://www.scopus.com/inward/record.url?eid=2-s2.0-84905160454&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-84905160454&partnerID=MN8TOARS