We show that any weak ranker that can achieve an area under the ROC curve slightly better than 1/2 (which can be achieved by random guessing) can be efficiently boostedto achieve an area under the ROC curve arbitrarily close to 1. We further show that this boosting can be performed even in the presence of independent misclassificationnoise, given access to a noise-tolerant weak ranker.
We show that any weak ranker that can achieve an area under the ROC curve slightly better than 1/2 (which can be achieved by random guessing) can be efficiently boosted to achieve an area under the ROC curve arbitrarily close to 1. We further show that this boosting can be performed even in the presence of independent misclassification noise, given access to a noise-tolerant weak ranker.
Term extraction is to extract domain relevant terms from a domain specific, unstructured corpus, which in an organisational setting can be used for categorisation and information retrieval. Previous statistical approaches to automatic term extraction rely on term frequencies, which may not only hamper the accuracy but also lower the rank of or even discard domain relevant yet infrequent terms. This paper aims at minimising the impact of term frequency and thus improving precision of top-k terms, by using a graph based ranking algorithm with the aids of latent vector representation of terms and term relations embedded in patents instead of general-domain knowledge sources. We show that the proposed method outperforms all the previous works significantly.
If Fox Searchlight Pictures wants to increase attendance at its new film "Jackie," it might consider pitching fans of "True Detective," "The Hunger Games" and Keira Knightley. So says Ranker, a Los Angeles start-up that gets more than 10 million votes on its website each month about what's cool in Hollywood, sports, music, gaming and politics. Ranker's tracking shows that people who rank "Jackie" star Natalie Portman as a great actress tend to also hold in high regard the popular HBO show, the teenage film franchise and English actress Knightley. The company is just starting to make data about such correlations available to the public, leaving uncertainty about whether customers will use the service the way it envisions. But Ranker is trying to land lucrative contracts to sell the data to entertainment companies, talent agencies and advertisers.
Visual tracking is an important research topic in computer vision community. Although there are numerous tracking algorithms in the literature, no one performs better than the others under all circumstances, and the best algorithm for a particular dataset may not be known a priori. This motivates a fundamental problem-the necessity of an ensemble learning of different tracking algorithms to overcome their drawbacks and to increase the generalization ability. This paper proposes a multi-modality ranking aggregation framework for fusion of multiple tracking algorithms. In our work, each tracker is viewed as a ranker' which outputs a rank list of the candidate image patches based on its own appearance model in a particular modality.