@article{ goussies_transfer_2014,
  title = {Transfer {Learning} {Decision} {Forests} for {Gesture} {Recognition}},
  volume = {15},
  url = {http://jmlr.org/papers/v15/goussies14a.html},
  abstract = {Decision forests are an increasingly popular tool in computer
vision problems. Their advantages include high computational
efficiency, state-of-the-art accuracy and multi-class support.
In this paper, we present a novel method for transfer learning
which uses decision forests, and we apply it to recognize
gestures and characters. We introduce two mechanisms into the
decision forest framework in order to transfer knowledge from
the source tasks to a given target task. The first one is mixed
information gain, which is a data-based regularizer. The second
one is label propagation, which infers the manifold structure of
the feature space. We show that both of them are important to
achieve higher accuracy. Our experiments demonstrate
improvements over traditional decision forests in the ChaLearn
Gesture Challenge and MNIST data set. They also compare
favorably against other state-of-the-art classifiers.},
  urldate = {2015-04-26TZ},
  journal = {Journal of Machine Learning Research},
  author = {Goussies, Norberto A. and Ubalde, Sebastián and Mejail, Marta},
  month = {November},
  year = {2014},
  note = {00000},
  keywords = {transfer learning},
  pages = {3667−3690}
}

{"_id":"pbRenoaEo8t5RhtGb","bibbaseid":"goussies-ubalde-mejail-transferlearningdecisionforestsforgesturerecognition-2014","downloads":0,"creationDate":"2015-09-03T07:18:47.422Z","title":"Transfer Learning Decision Forests for Gesture Recognition","author_short":["Goussies, N.<nbsp>A.","Ubalde, S.","Mejail, M."],"year":2014,"bibtype":"article","biburl":"http://bibbase.org/zotero/fred.qi","bibdata":{"abstract":"Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.","author":["Goussies, Norberto A.","Ubalde, Sebastián","Mejail, Marta"],"author_short":["Goussies, N.<nbsp>A.","Ubalde, S.","Mejail, M."],"bibtex":"@article{ goussies_transfer_2014,\n title = {Transfer {Learning} {Decision} {Forests} for {Gesture} {Recognition}},\n volume = {15},\n url = {http://jmlr.org/papers/v15/goussies14a.html},\n abstract = {Decision forests are an increasingly popular tool in computer\nvision problems. Their advantages include high computational\nefficiency, state-of-the-art accuracy and multi-class support.\nIn this paper, we present a novel method for transfer learning\nwhich uses decision forests, and we apply it to recognize\ngestures and characters. We introduce two mechanisms into the\ndecision forest framework in order to transfer knowledge from\nthe source tasks to a given target task. The first one is mixed\ninformation gain, which is a data-based regularizer. The second\none is label propagation, which infers the manifold structure of\nthe feature space. We show that both of them are important to\nachieve higher accuracy. Our experiments demonstrate\nimprovements over traditional decision forests in the ChaLearn\nGesture Challenge and MNIST data set. They also compare\nfavorably against other state-of-the-art classifiers.},\n urldate = {2015-04-26TZ},\n journal = {Journal of Machine Learning Research},\n author = {Goussies, Norberto A. and Ubalde, Sebastián and Mejail, Marta},\n month = {November},\n year = {2014},\n note = {00000},\n keywords = {transfer learning},\n pages = {3667−3690}\n}","bibtype":"article","id":"goussies_transfer_2014","journal":"Journal of Machine Learning Research","key":"goussies_transfer_2014","keywords":"transfer learning","month":"November","note":"00000","pages":"3667−3690","title":"Transfer Learning Decision Forests for Gesture Recognition","type":"article","url":"http://jmlr.org/papers/v15/goussies14a.html","urldate":"2015-04-26TZ","volume":"15","year":"2014","bibbaseid":"goussies-ubalde-mejail-transferlearningdecisionforestsforgesturerecognition-2014","role":"author","urls":{"Paper":"http://jmlr.org/papers/v15/goussies14a.html"},"keyword":["transfer learning"],"downloads":0},"search_terms":["transfer","learning","decision","forests","gesture","recognition","goussies","ubalde","mejail"],"keywords":["transfer learning"],"authorIDs":[],"dataSources":["y8en6y5RHukfeLuPH"]}