Adrien Gaidon
Adrien Gaidon
Machine Learning Lead, Toyota Research Institute (TRI)
Geverifieerd e-mailadres voor tri.global - Homepage
TitelGeciteerd doorJaar
Virtual worlds as proxy for multi-object tracking analysis
A Gaidon, Q Wang, Y Cabon, E Vig
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016
4022016
Actom sequence models for efficient action detection
A Gaidon, Z Harchaoui, C Schmid
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2011
1712011
Temporal Localization of Actions with Actoms
A Gaidon, Z Harchaoui, C Schmid
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
1542013
INRIA-LEARs video copy detection system
M Douze, A Gaidon, H Jegou, M Marszałek, C Schmid
982008
Activity representation with motion hierarchies
A Gaidon, Z Harchaoui, C Schmid
International journal of computer vision 107 (3), 219-238, 2014
942014
Recognizing activities with cluster-trees of tracklets
A Gaidon, Z Harchaoui, C Schmid
British Machine Vision Conference (BMVC), 2012
812012
Procedural generation of videos to train deep action recognition networks
C Roberto de Souza, A Gaidon, Y Cabon, A Manuel Lopez
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017
64*2017
Sympathy for the details: Dense trajectories and hybrid classification architectures for action recognition
CR De Souza, A Gaidon, E Vig, AM López
European conference on computer vision, 697-716, 2016
402016
A time series kernel for action recognition
A Gaidon, Z Harchaoui, C Schmid
British Machine Vision Conference (BMVC), 2011
382011
Mining visual actions from movies
A Gaidon, M Marszalek, S Cordelia
British Machine Vision Conference (BMVC), 2009
302009
Online learning to sample
G Bouchard, T Trouillon, J Perez, A Gaidon
arXiv preprint arXiv:1506.09016, 2015
262015
Superdepth: Self-supervised, super-resolved monocular depth estimation
S Pillai, R Ambrus, A Gaidon
ICRA, 2019
242019
Self-learning object detectors for unlabeled videos using multi-task learning
A Gaidon, ZEN Gloria, JAR Serrano
US Patent 9,158,971, 2015
232015
Roi-10d: Monocular lifting of 2d detection to 6d pose and metric shape
F Manhardt, W Kehl, A Gaidon
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
212019
Learning to fuse things and stuff
J Li, A Raventos, A Bhargava, T Tagawa, A Gaidon
arXiv preprint arXiv:1812.01192, 2018
212018
Classification aided two stage localization
H Harzallah, C Schmid, F Jurie, A Gaidon
132008
Online domain adaptation for multi-object tracking
A Gaidon, E Vig
British Machine Vision Conference (BMVC), 2015
122015
Exploring the Limitations of Behavior Cloning for Autonomous Driving
F Codevilla, E Santana, AM López, A Gaidon
Proceedings of the IEEE International Conference on Computer Vision, 2019
112019
Self-learning camera: Autonomous adaptation of object detectors to unlabeled video streams
A Gaidon, G Zen, JA Rodriguez-Serrano
arXiv preprint arXiv:1406.4296, 2014
112014
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
K Cao, C Wei, A Gaidon, N Arechiga, T Ma
Advances in Neural Information Processing Systems, 2019
102019
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20