Convolutional sketch inversion

Autor: Güçlütürk, Y., Güçlü, U., Lier, R.J. van, Gerven, M.A.J. van, Hua, G., Jégou, H.

Publikováno v: Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops: Proceedings, Part I, 810-814. Cham : Springer
STARTPAGE=810;ENDPAGE=814;TITLE=Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops: Proceedings, Part I
Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops: Proceedings, Part I, pp. 810-814

Contains fulltext : 159908.pdf (Publisher’s version ) (Closed access) In this paper, we use deep neural networks for inverting face sketches to synthesize photorealistic face images. We first construct a semi-simulated dataset containing a very lar

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e6e9265f61d9353c12d4f9fe475755fe
https://hdl.handle.net/2066/159908

Deep disentangled representations for volumetric reconstruction

Autor: Grant, E., Kohli, P., Gerven, M.A.J. van, Hua, G., Jégou, H.

Publikováno v: Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops, Proceedings, 266-279. Cham : Springer
STARTPAGE=266;ENDPAGE=279;TITLE=Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops, Proceedings
Hua, G.; Jégou, H. (ed.), Computer Vision-ECCV 2016 Workshops, Proceedings, pp. 266-279

Item does not contain fulltext We introduce a convolutional neural network for inferring a compact disentangled graphical description of objects from 2D images that can be used for volumetric reconstruction. The network comprises an encoder and a twi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebc386e238b34dd3c59a335e6f3da512

Quaero at TRECVID 2012: Semantic Indexing

Autor: Safadi, B., Derbas, N., Hamadi, A., Thollard, F., Quéno, G., Delhumeau, J., Jégou, H., Gehrig, T., HAZIM KEMAL EKENEL, Stifelhagen, R.

Publikováno v: TRECVID-Proceedings of the workshop on TREC Video Retrieval Evaluation
TRECVID-TREC Video Retrieval Evaluation workshop
TRECVID-TREC Video Retrieval Evaluation workshop, Nov 2012, Gaithersburg, MD, United States. 6p
Scopus-Elsevier

International audience; The Quaero group is a consortium of French and German organizations working on Multimedia Indexing and Retrieval. LIG, INRIA and KIT participated to the semantic indexing task and LIG participated to the organization of this t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::98a12c1f5b2c547b6cbdf81f33b7e479
https://hal.archives-ouvertes.fr/hal-00770240/file/Safadi-al_TRECVID2012.pdf

IRIM at TRECVID2009: High Level Feature Extraction

Autor: Delezoide, B., Le Borgne, H., Moëllic, P. -A, Gorisse, D., Precioso, F., Wang, F., Merialdo, B., Gosselin, P., Granjon, L., Pellerin, D., Rombaut, M., Bredin, H., Koenig, L., Lachambre, H., El Khoury, E., Boris Mansencal, Zhou, Y., Benois-Pineau, J., Jégou, H., Ayache, S., Safadi, B., Quénot, G., Fabrizio, J., Cord, M., Glotin, H., Zhao, Z., Dumont, E., Augereau, B.

Publikováno v: TREC Video Retrieval Evaluation Online Proceedings (TRECVID)
TRECVID 2009-TREC Video Retrieval Evaluation
TRECVID 2009-TREC Video Retrieval Evaluation, Nov 2009, Gaithersburg, MD, United States
HAL
Scopus-Elsevier

International audience; The IRIM group is a consortium of French teams working on Multimedia Indexing and Retrieval. This paper describes our participation to the TRECVID 2009 High Level Features detection task. We evaluated a large number of differe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5aabbac21e04f0f1522f82a27d850897
https://hal.science/hal-00468199/file/IRIMatTRECVID2009.pdf

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.