Vedran Vukotić
Vedran Vukotić
Researcher @ Stark Industries && Field Operative @ S.H.I.E.L.D.
Verified email at inria.fr - Homepage
TitleCited byYear
Is it time to switch to Word Embedding and Recurrent Neural Networks for Spoken Language Understanding?
V Vukotic, C Raymond, G Gravier
International Conference on Spoken Language Processing (Interspeech) 2015, 2015
432015
One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
V Vukotić, SL Pintea, C Raymond, G Gravier, J Van Gemert
International Conference on Image Analysis and Processing ICIAP, 2017
242017
Multimodal and crossmodal representation learning from textual and visual features with bidirectional deep neural networks for video hyperlinking
V Vukotić, C Raymond, G Gravier
Proceedings of the 2016 ACM workshop on Vision and Language Integration …, 2016
232016
Bidirectional Joint Representation Learning with Symmetrical Deep Neural Networks for Multimodal and Crossmodal Applications
V Vukotic, C Raymond, G Gravier
ACM International Conference in Multimedia Retrieval (ICMR) 2016, 2016
232016
A step beyond local observations with a dialog aware bidirectional GRU network for Spoken Language Understanding
V Vukotic, C Raymond, G Gravier
International Conference on Spoken Language Processing (Interspeech) 2016, 2016
152016
Estimating OD matrices at intersections in airborne video-a pilot study
V Braut, M Čuljak, V Vukotić, S Šegvić, M Ševrović, H Gold
2012 Proceedings of the 35th International Convention MIPRO, 977-982, 2012
142012
Exploiting multimodality in video hyperlinking to improve target diversity
R Bois, V Vukotić, AR Simon, R Sicre, C Raymond, P Sébillot, G Gravier
International Conference on Multimedia Modeling, 185-197, 2017
122017
Label-dependency coding in Simple Recurrent Networks for Spoken Language Understanding
M Dinarelli, V Vukotic, C Raymond
International Conference on Spoken Language Processing (Interspeech) 2017, 2017
112017
Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking
V Vukotic, C Raymond, G Gravier
ACM International Conference in Multimedia Retrieval (ICMR) 2017, 2017
92017
A Crossmodal Approach to Multimodal Fusion in Video Hyperlinking
V Vukotić, C Raymond, G Gravier
IEEE MultiMedia, 2018
52018
Irisa at trecvid2016: Crossmodality, multimodality and monomodality for video hyperlinking
R Bois, V Vukotić, R Sicre, C Raymond, G Gravier, P Sébillot
52016
IRISA at DeFT 2015: supervised and unsupervised methods in sentiment analysis
V Vukotić, V Claveau, C Raymond
52015
Raspoznavanje objekata dubokim neuronskim mrežama
V Vukotic
Faculty of Electrical Engineering and Computing, Zagreb, 2014
52014
Convolutional neural networks for Croatian traffic signs recognition
V Vukotic, J Krapac, S Šegvic
Croatian Computer Vision Workshop (CCVW) 2014, 2014
32014
Are Deep Neural Networks good for blind image watermarking?
V Vukotić, V Chappelier, T Furon
2018 IEEE International Workshop on Information Forensics and Security (WIFS …, 2018
12018
Mining Polysemous Triplets with Recurrent Neural Networks for Spoken Language Understanding
V Vukotić, C Raymond
International Conference on Spoken Language Processing (Interspeech) 2019, 2019
2019
Deep neural architectures for automatic representation learning from multimedia multimodal data
V Vukotic
Rennes, INSA, 2017
2017
Izrada demonstracijskog 8-bitnog procesora
V Vukotić, M Mijić
http://www.zemris.fer.hr/~ssegvic/ar2/2012VukoticMijic.pdf, 76, 2012
2012
Astronomsko određivanje pozicije računalnim prepoznavanjem zvijezda
V Vukotić
The system can't perform the operation now. Try again later.
Articles 1–19