This paper describes the ideas and methodologies that we used in the Yahoo learning-torank challenge. Our technique is essentially pointwise with a listwise touch at the last combination step. The main ingredients of our approach are 1) preprocessing (querywise normalization) 2) multi-class AdaBoost.MH 3) regression calibration, and 4) an exponentially weighted forecaster for model combination....

This paper describes a method to minimize the immense training time of the conventional Adaboost learning algorithm in object detection by reducing the sampling area. A new algorithm with respect to the geometric and accordingly the symmetric relations of the analyzed object is presented. Symmetry enhanced Adaboost (SEAdaboost) can limit the scanning area enormously, depending on the degree of ...

Ordinal data classification (ODC) has a wide range of applications in areas where human evaluation plays an important role, ranging from psychology and medicine to information retrieval. In ODC the output variable has a natural order; however, there is not a precise notion of the distance between classes. The Data Replication Method was proposed as tool for solving the ODC problem using a singl...

This paper describes an improved boosting algorithm, named RegionBoost, and its application in developing a fast and robust invariant Local Binary Pattern histogram based face recognition system. We propose to use a multi-classifier where each classifier, an AdaBoost of feed-forward back-propagation network, is trained using a single Sub-Window of the whole image, the classifiers are finally co...

Recently Viola et al. have introduced a rapid object detection scheme based on a boosted cascade of simple feature classifiers. In this paper we introduce and empirically analysis two extensions to their approach: Firstly, a novel set of rotated haar-like features is introduced. These novel features significantly enrich the simple features of [6] and can also be calculated efficiently. With the...

In this paper, we propose a multi-modal voice activity detection system (VAD) that uses audio and visual information. In multi-modal (speech) signal processing, there are two methods for fusing the audio and the visual information: concatenating the audio and visual features, and employing audioonly and visual-only classifiers, then fusing the unimodal decisions. We investigate the effectivenes...

In this paper we present a fully automatic and accurate segmentation framework for 2D tagged cardiac MR images. This scheme consists of three learning methods: a) an active shape model is implemented to model the heart shape variations, b) an Adaboost learning method is applied to learn confidence-rated boundary criterions from the local appearance features at each landmark point on the shape m...

In this paper, we propose the post-classification scheme that is useful for improving weak-hypothesis combination of AdaBoost. The post-classification scheme allows the weak hypotheses to be combined nonlinearly, and can be shown to have a generally better performance than the original linear-combination approach in either theory or practice. The post-classification scheme provides a general pe...

Recently, Adaboost has been compared to greedy backfitting of extended additive models in logistic regression problems, or “Logitboost". The Adaboost algorithm has been applied to learn fuzzy rules in classification problems, and other backfitting algorithms to learn fuzzy rules in modeling problems but, up to our knowledge, there are not previous works that extend the Logitboost algorithm to l...

This paper proposes a novel technique to exploit discriminative models with subclasses for speech recognition. Speech recognition using discriminative models has attracted much attention in the past decade. However, most discriminative models are still based on tree clustering results of HMM states. On the contrary, our proposed method, referred to as subclass AdaBoost, jointly selects optimal ...