P. Over, G. Awad, M. Michel, J. Fiscus, W. Kraaij et al., Trecvid 2011 ? an overview of the goals, tasks, data, evaluation mechanisms and metrics, Proceedings of TRECVID 2011, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00763912

B. Delezoide, F. Precioso, P. Gosselin, M. Redi, B. Mérialdo et al., Irim at trecvid 2011: Semantic indexing and instance search, Proceedings of TRECVID 2011, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00677651

S. Ben-david, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira et al., A theory of learning from different domains, Machine Learning, vol.60, issue.1-2, pp.151-175, 2010.
DOI : 10.1007/s10994-009-5152-4

Y. Mansour, M. Mohri, and A. Rostamizadeh, Domain adaptation: Learning bounds and algorithms, Proceedings of COLT, pp.19-30, 2009.

S. Ben-david, T. Lu, T. Luu, and D. Pal, Impossibility theorems for domain adaptation, JMLR W&CP, vol.9, pp.129-136, 2010.

M. Balcan, A. Blum, and N. Srebro, Improved guarantees for learning via similarity functions, Proceedings of COLT, pp.287-298, 2008.

E. Morvant, A. Habrard, and S. Ayache, Sparse Domain Adaptation in Projection Spaces Based on Good Similarity Functions, 2011 IEEE 11th International Conference on Data Mining, pp.457-466, 2011.
DOI : 10.1109/ICDM.2011.136

URL : https://hal.archives-ouvertes.fr/hal-00629207

P. Smyth and D. Wolpertblitzer, Linearly combining density estimators via stacking Learning bounds for domain adaptation Advances in neural information processing systems, Machine Learning, vol.36, issue.1/2, pp.59-83129, 1999.
DOI : 10.1023/A:1007511322260

. Blitzer, Domain adaptation with coupled subspaces, Journal of Machine Learning Research-Proceedings Track, vol.15, pp.173-181, 2011.

. Blitzer, Domain adaptation with structural correspondence learning, Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP '06, pp.120-128, 2006.
DOI : 10.3115/1610075.1610094

. Boser, A training algorithm for optimal margin classifiers, Proceedings of the fifth annual workshop on Computational learning theory , COLT '92, pp.144-152, 1992.
DOI : 10.1145/130385.130401

. Boucheron, Concentration Inequalities, Advanced Lectures on Machine Learning, pp.208-240, 2004.
DOI : 10.1007/978-1-4757-2440-0

URL : https://hal.archives-ouvertes.fr/hal-00751496

]. O. Bousquet-et-elisseeff, A. Bousquet, and . Elisseeff, Stability and generalization, Journal of Machine Learning Research, vol.2, pp.499-526, 2002.

]. L. Bregman, The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming . USSR computational mathematics and mathematical physics, pp.200-217, 1967.

]. L. Breiman, Random Forests, Machine Learning, pp.5-32, 2001.

. Breiman, Classification and regression trees, 1984.

]. L. Bruzzone-et-marconcini, M. Bruzzone, and . Marconcini, Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.32, issue.5, pp.770-787, 2010.
DOI : 10.1109/TPAMI.2009.57

. J. Zhang, C. Ye, L. Zhang, and . Zhang, Generalization bounds for domain adaptation, Proceedings of Annual Conference on Neural Information Processing Systems, pp.45-175, 2012.

. Cao, Distance metric learning under covariate shift, Proceedings of International Joint Conference on Artificial Intelligence, pp.1204-1210, 2011.

]. O. Catoni and . Catoni, A PAC-Bayesian approach to adaptive classification. preprint, 2003.

]. T. Dietterich, Ensemble Methods in Machine Learning, Multiple Classifier Systems, pp.1-15, 2000.
DOI : 10.1007/3-540-45014-9_1

D. Et-varadhan, ]. D. Donsker, and S. S. Varadhan, Asymptotic evaluation of certain markov process expectations for large time, Communications on Pure and Applied Mathematics, vol.28, pp.1975-111, 1975.

. Duan, Domain transfer svm for video concept detection, Proceedings of Conference on Computer Vision and Pattern Recognition, pp.1375-1381, 2009.

. Duda, Pattern classification. Pattern Classification and Scene Analysis : Pattern Classification, pp.25-85, 2001.

. Everingham, The PASCAL visual object classes challenge 2007 (VOC2007) results, pp.96-146, 2007.

. Evgeniou, Learning multiple tasks with kernel methods, Journal of Machine Learning Research, vol.6, issue.1, p.615, 2006.

F. Et-warmuth, ]. S. Floyd, and M. K. Warmuth, Sample compression, learnability, and the Vapnik-Chervonenkis dimension, Machine Learning Journal, vol.21, issue.3, pp.269-304, 1995.
DOI : 10.1007/3-540-62685-9_1

F. Et-schapire, ]. Y. Freund, and R. E. Schapire, Experiments with a new boosting algorithm, Proceedings of International Conference on Machine Learning, pp.148-156, 1996.

. Gelman, Bayesian data analysis, 2004.

. Geng, DAML: Domain Adaptation Metric Learning, IEEE Transactions on Image Processing, vol.20, issue.10, pp.2980-2989, 2011.
DOI : 10.1109/TIP.2011.2134107

. Geras, ]. K. Sutton, C. Geras, and . Sutton, Multiple-source cross-validation, 2013.

. Germain, PACbayesian domain adaptation bound with specialization to linear classifiers, Proceedings of International Conference on Machine Learning, pp.2013-156

. Germain, Une analyse PAC-Bayésienne de l'adaptation de domaine et sa spécialisation aux classifieurs linéaires, Conférence Francophone sur l'Apprentissage Automatique, pp.2013-156

. Germain, PAC-Bayesian learning of linear classifiers, Proceedings of the 26th Annual International Conference on Machine Learning, ICML '09, pp.59-62, 2009.
DOI : 10.1145/1553374.1553419

. Germain, From PAC-Bayes bounds to kl regularization, Proceedings of annual conference on Neural Information Processing Systems, pp.603-610, 2009.

. Germain, A PAC-Bayes sample compression approach to kernel methods, Proceedings of International Conference on Machine Learning, pp.62-81, 2011.

. Gigù-ere, Risk bounds and learning algorithms for the regression approach to structured output prediction, Proceedings of International Conference on Machine Learning, pp.63-177, 2013.

. Glorot, Domain adaptation for largescale sentiment classification : A deep learning approach, Proceedings of International Conference on Machine Learning, pp.2011-177, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00752091

. Gong, Connecting the dots with landmarks : Discriminatively learning domain-invariant features for unsupervised domain adaptation, Proceedings of International Conference on Machine Learning, pp.2013-153, 2013.

. Graepel, PAC-Bayesian Compression Bounds on the Prediction Error of Learning Algorithms for Classification, Machine Learning, vol.4, issue.6, pp.55-76, 2005.
DOI : 10.1007/s10994-005-0462-7

. Guermeur, Théorie et Applications. Habilitationà Habilitation`Habilitationà diriger des recherches, Guermeur. SVM Multiclasses, issue.1, 2007.

. Habrard, Domain Adaptation with Good Edit Similarities: A Sparse Way to Deal with Scaling and Rotation Problems in Image Classification, 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence, pp.181-188, 2011.
DOI : 10.1109/ICTAI.2011.35

URL : https://hal.archives-ouvertes.fr/hal-00618757

. Habrard, Boosting for Unsupervised Domain Adaptation, Proceedings of European Conference on Machine Learning and Principles of Data Mining and Knowledge Discovery, pp.2013-2053, 2013.
DOI : 10.1007/978-3-642-40991-2_28

URL : https://hal.archives-ouvertes.fr/hal-00869394

. Harel, . M. Mannor, S. Harel, and . Mannor, The Perturbed Variation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.37, issue.10, pp.1943-1951
DOI : 10.1109/TPAMI.2015.2404836

]. T. Hastie-et-tibshirani, R. Hastie, . Tibshirani-]-m, S. Kubat, and . Matwin, Discriminant adaptive nearest neighbor classification Addressing the curse of imbalanced training sets : one-sided selection, Machine Learning-International Workshop then Conference, pp.179-186, 1996.

. Kulis, What you saw is not what you get: Domain adaptation using asymmetric kernel transforms, CVPR 2011, pp.1785-1792, 2011.
DOI : 10.1109/CVPR.2011.5995702

K. Et-leibler, ]. S. Kullback, and R. A. Leibler, On information and sufficiency . The Annals of, Mathematical Statistics, vol.22, issue.1, pp.79-86, 1951.

]. L. Kuncheva, Combining Pattern Classifiers: Methods and Algorithms, IEEE Transactions on Neural Networks, vol.18, issue.3, pp.92-93, 2004.
DOI : 10.1109/TNN.2007.897478

. A. Lacasse and . Lacasse, Bornes PAC-Bayes et algorithmes d'apprentissage, Thèse, 2010.

. Lacasse, PAC-bayes bounds for the risk of the majority vote and the variance of the Gibbs classifier, Proceedings of annual conference on Neural Information Processing Systems, pp.60-67, 2007.

]. J. Langford, Tutorial on practical prediction theory for classification, Journal of Machine Learning Research, vol.6, issue.62, pp.273-306, 2005.

. Langford, ]. J. Shawe-taylor, J. Langford, and . Shawe-taylor, PAC-bayes & margins, Proceedings of Annual Conference on Advances in Neural Information Processing Systems, pp.439-446, 2002.

]. F. Laviolette-et-marchand, M. Laviolette, and . Marchand, PAC-Bayes risk bounds for stochastic averages and majority votes of sample-compressed classifiers, Journal of Machine Learning Research, vol.8, issue.72, pp.1461-1487, 2007.

. Laviolette, From PAC-Bayes Bounds to Quadratic Programs for Majority Votes, Proceedings of International Conference on Machine Learning, pp.71-72, 2011.

. Laviolette, From PAC-Bayes Bounds to Quadratic Programs for Majority Votes : Extended version, pp.70-187, 2011.

. Lettvin, What the Frog's Eye Tells the Frog's Brain, Cité page 2.) [Lever et al. Distributiondependent PAC-Bayes priors. Dans Proceedings of Algorithmic Learning Theory, pp.1940-1951, 1959.
DOI : 10.1109/JRPROC.1959.287207

. Lever, Tighter PAC-Bayes bounds through distribution-dependent priors, Theoretical Computer Science, vol.473, pp.4-28, 2013.
DOI : 10.1016/j.tcs.2012.10.013

L. Et-bilmes, ]. X. Li, and J. Bilmes, A bayesian divergence prior for classifier adaptation, Proceedings of International Conference on Artificial Intelligence and Statistics, 2007.

. Lin, Support vector machines for classification in nonstandard situations, Machine Learning, pp.191-202, 2002.

. Liu, Evigan: a hidden variable model for integrating gene evidence for eukaryotic gene prediction, Bioinformatics, vol.24, issue.5, pp.597-605, 2008.
DOI : 10.1093/bioinformatics/btn004

]. D. Lowe and . Lowe, Object recognition from local scale-invariant features, Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999.
DOI : 10.1109/ICCV.1999.790410

. P. Machart and . Machart, Coping with the Computational and Statistical Bipolar Nature of Machine Learning, Thèse, pp.2012-102
URL : https://hal.archives-ouvertes.fr/tel-00771718

. J. Mairal and . Mairal, Sparse coding for machine learning, image processing and computer vision. thèse, ´ Ecole normale supérieure de Cachant, 2010.
URL : https://hal.archives-ouvertes.fr/tel-00595312

. Mansour, Domain adaptation : Learning bounds and algorithms, Proceedings of Annual Conference on Learning Theory, pp.19-30, 2009.

. Mansour, Multiple source adaptation and the rényi divergence, Proceedings of annual Conference on Uncertainty in Artificial Intelligence, pp.367-374, 2009.

S. Mansour, Robust domain adaptation, Mansour et M. Schain Proceedings of International Symposium on Artificial Intelligence and Mathematics, pp.43-44, 2012.
DOI : 10.1007/s10472-013-9391-5

. Marchand, ]. M. Sokolova, M. Marchand, and . Sokolova, Learning with decision lists of data-dependent features, Journal of Machine Learning Research, vol.6, pp.427-451, 2005.

]. A. Margolis, A literature review of domain adaptation with unlabeled data, pp.2011-2046, 2011.

. Maurer, Andreas Maurer. A note on the PAC-Bayesian theorem, 2004.

´. Bougrain and . Editeur, Conférence Francophone sur l'Apprentissage Automatique, pp.111-126

. Morvant, Parsimonious unsupervised and semi-supervised domain adaptation with good similarity functions, Knowledge and Information Systems, vol.50, issue.3, pp.309-349, 2012.
DOI : 10.1007/s10115-012-0516-7

URL : https://hal.archives-ouvertes.fr/hal-00686205

. Morvant, PAC-Bayesian Generalization Bound on Confusion Matrix for Multi-Class Classification, Proceedings of International Conference on Machine Learning Omnipress, 2012. (Full Paper, Acceptance rate : 27%). (Cité page 102, pp.815-822, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00674847

. Nock, A SIMPLE LOCALLY ADAPTIVE NEAREST NEIGHBOR RULE WITH APPLICATION TO POLLUTION FORECASTING, International Journal of Pattern Recognition and Artificial Intelligence, vol.17, issue.08, pp.1369-1382, 2003.
DOI : 10.1142/S0218001403002952

. Opelt, Weak Hypotheses and Boosting for Generic Object Detection and Recognition, Proceedings of European Conference on Computer Vision (ECCV), pp.71-84, 2004.
DOI : 10.1007/978-3-540-24671-8_6

Y. J. Pan, Q. Pan, and . Yang, A survey on transfer learning. Knowledge and Data Engineering, IEEE Transactions on, vol.22, issue.10, pp.1345-1359, 2010.

. Parrado-hernández, PAC-Bayes bounds with data dependent priors, Journal of Machine Learning Research, vol.13, issue.62, pp.3507-3531, 2012.

V. I. Paulsen and . Paulsen, Completely bounded maps and operator algebras. Cambridge studies in advanced mathematics, 2002.

. Peterson, . W. Jr, E. J. Wesley-peterson, and . Weldon-jr, Error-Correcting Codes, 1972.

]. J. Quinlan and . Quinlan, C4. 5 : programs for machine learning, 1993.

]. L. Ralaivola, Confusion-based online learning and a passiveaggressive scheme, Proceedings of Annual Conference on Neural Information Processing Systems, pp.3293-3301, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00819045

. Ralaivola, Chromatic PAC- Bayes bounds for non-iid data : Applications to ranking and stationary ?-mixing processes, Journal of Machine Learning Research, vol.11, pp.1927-1956, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00415162

]. B. Ripley and . Ripley, Pattern recognition and neural networks, 2007.
DOI : 10.1017/CBO9780511812651

. Smeaton, Evaluation campaigns and TRECVid, Proceedings of the 8th ACM international workshop on Multimedia information retrieval , MIR '06, pp.321-330, 2006.
DOI : 10.1145/1178677.1178722

. Snoek, Early versus late fusion in semantic video analysis, Proceedings of the 13th annual ACM international conference on Multimedia , MULTIMEDIA '05, pp.399-402, 2005.
DOI : 10.1145/1101149.1101236

S. Et-barto, ]. R. Sutton, and A. G. Barto, Reinforcement Learning, 1998.
DOI : 10.1016/B978-012526430-3/50003-9

T. Et-efros, ]. A. Torralba, and A. A. Efros, Unbiased look at dataset bias, Proceedings of Conference on Computer Vision and Pattern Recognition, pp.1521-1528, 2011.

. J. Tropp and . Tropp, User-Friendly Tail Bounds for Sums of Random Matrices, Foundations of Computational Mathematics, vol.16, issue.2, pp.1-46, 2011.
DOI : 10.1007/s10208-011-9099-z

. Urner, Access to unlabeled data can speed up prediction time, Proceedings of International Conference on Machine Learning, pp.641-648, 2011.

]. L. Valiant, A theory of the learnable, Communications of the ACM, vol.27, issue.11, pp.1134-1142, 1984.
DOI : 10.1145/1968.1972

]. V. Vapnik and . Vapnik, Estimation of Dependences Based on Empirical Data, 1982.

]. V. Vapnik and . Vapnik, Statistical Learning Theory, 1998.

]. V. Vapnik and . Vapnik, The nature of statistical learning theory, 1995.

C. N. Vapnik, A. Vapnik, and . Ya, Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, pp.264-280, 1971.

W. Et-kankanhalli, ]. X. Wang, and M. S. Kankanhalli, Portfolio theory of multimedia fusion, Proceedings of ACM Multimedia Conference, pp.723-726, 2010.

S. Q. Weinberger, L. K. Weinberger, and . Saulwickramaratna, Distance metric learning for large margin nearest neighbor classification Performance degradation in boosting, Multiple Classifier Systems, pp.11-21, 2001.

. D. Wolpert and . Wolpert, Stacked generalization, Neural Networks, vol.5, issue.2, pp.241-259, 1992.
DOI : 10.1016/S0893-6080(05)80023-1

. Xu, Sparse algorithms are not stable : A no-free-lunch theorem, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.34, issue.1, pp.187-193, 2012.

]. H. Xu-et-mannor, S. Xu, and . Mannor, Robustness and generalization, Proceedings of Annual Conference on Computational Theory, pp.503-515, 2010.

]. H. Xu-et-mannor, S. Xu, and . Mannor, Robustness and generalization, Machine Learning, pp.391-423, 2012.

Y. , J. Yang, and R. Jin, Distance Metric Learning : A Comprehensive Survey, 2006.

Y. Et-doretto, ]. Y. Yao, and G. Doretto, Boosting for transfer learning with multiple sources, Proceedings of Conference on Computer Vision and Pattern Recognition, pp.1855-1862, 2010.

. Yue, A support vector method for optimizing average precision, Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR '07, pp.271-278, 2007.
DOI : 10.1145/1277741.1277790

]. T. Zhang and . Zhang, Statistical analysis of some multi-category large margin classification methods, Journal of Machine Learning Research, vol.5, pp.1225-1251, 2004.

Y. Zhang, D. Zhang, and . Yeung, Transfer metric learning by learning task relationships, Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD '10, pp.1199-1208, 2010.
DOI : 10.1145/1835804.1835954

. Zhong, Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning, Proceedings of European Conference on Machine Learning and Principles of Data Mining and Knowledge Discovery, pp.547-562, 2010.
DOI : 10.1007/978-3-642-15939-8_35