Jun Yang

Bio: Jun Yang is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: TRECVID & Visual Word. The author has an hindex of 18, co-authored 52 publications receiving 3476 citations. Previous affiliations of Jun Yang include Zhejiang University & City University of Hong Kong.

Evaluating bag-of-visual-words representations in scene classification

Abstract: Based on keypoints extracted as salient image patches, an image can be described as a "bag of visual words" and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text categorization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The impact of these representation choices to scene classification is studied through extensive experiments on the TRECVID and PASCAL collection. This study provides an empirical basis for designing visual-word representations that are likely to produce superior classification performance.

Cross-domain video concept detection using adaptive svms

Abstract: Many multimedia applications can benefit from techniques for adapting existing classifiers to data with different distributions. One example is cross-domain video concept detection which aims to adapt concept classifiers across various video domains. In this paper, we explore two key problems for classifier adaptation: (1) how to transform existing classifier(s) into an effective classifier for a new dataset that only has a limited number of labeled examples, and (2) how to select the best existing classifier(s) for adaptation. For the first problem, we propose Adaptive Support Vector Machines (A-SVMs) as a general method to adapt one or more existing classifiers of any type to the new dataset. It aims to learn the "delta function" between the original and adapted classifier using an objective function similar to SVMs. For the second problem, we estimate the performance of each existing classifier on the sparsely-labeled new dataset by analyzing its score distribution and other meta features, and select the classifiers with the best estimated performance. The proposed method outperforms several baseline and competing methods in terms of classification accuracy and efficiency in cross-domain concept detection in the TRECVID corpus.

Towards optimal bag-of-features for object categorization and semantic video retrieval

Abstract: Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as reliability and scalability of visual classification, nevertheless, remains uncertain due to various implementation choices. In this paper, we evaluate various factors which govern the performance of BoF. The factors include the choices of detector, kernel, vocabulary size and weighting scheme. We offer some practical insights in how to optimize the performance by choosing good keypoint detector and kernel. For the weighting scheme, we propose a novel soft-weighting method to assess the significance of a visual word to an image. We experimentally show that the proposed soft-weighting scheme can consistently offer better performance than other popular weighting methods. On both PASCAL-2005 and TRECVID-2006 datasets, our BoF setting generates competitive performance compared to the state-of-the-art techniques. We also show that the BoF is highly complementary to global features. By incorporating the BoF with color and texture features, an improvement of 50% is reported on TRECVID-2006 dataset.

Learning query-class dependent weights in automatic video retrieval

Abstract: Combining retrieval results from multiple modalities plays a crucial role for video retrieval systems, especially for automatic video retrieval systems without any user feedback and query expansion. However, most of current systems only utilize query independent combination or rely on explicit user weighting. In this work, we propose using query-class dependent weights within a hierarchial mixture-of-expert framework to combine multiple retrieval results. We first classify each user query into one of the four predefined categories and then aggregate the retrieval results with query-class associated weights, which can be learned from the development data efficiently and generalized to the unseen queries easily. Our experimental results demonstrate that the performance with query-class dependent weights can considerably surpass that with the query independent weights.

Adapting SVM Classifiers to Data with Shifted Distributions

Abstract: Many data mining applications can benefit from adapt- ing existing classifiers to new data with shifted distribu- tions. In this paper, we present Adaptive Support Vector Machine (Adapt-SVM) as an efficient model for adapting a SVM classifier trained from one dataset to a new dataset where only limited labeled examples are available. By in- troducing a new regularizer into SVM's objective function, Adapt-SVM aims to minimize both the classification error over the training examples, and the discrepancy between the adapted and original classifier. We also propose a selective sampling strategy based on the loss minimization principle to seed the most informative examples for classifier adap- tation. Experiments on an artificial classification task and on a benchmark video classification task shows that Adapt- SVM outperforms several baseline methods in terms of ac- curacy and/or efficiency.

Active Learning Literature Survey

Abstract: The key idea behind active learning is that a machine learning algorithm can achieve greater accuracy with fewer training labels if it is allowed to choose the data from which it learns. An active learner may pose queries, usually in the form of unlabeled data instances to be labeled by an oracle (e.g., a human annotator). Active learning is well-motivated in many modern machine learning problems, where unlabeled data may be abundant or easily obtained, but labels are difficult, time-consuming, or expensive to obtain. This report provides a general introduction to active learning and a survey of the literature. This includes a discussion of the scenarios in which queries can be formulated, and an overview of the query strategy frameworks proposed in the literature to date. An analysis of the empirical and theoretical evidence for successful active learning, a summary of problem setting variants and practical issues, and a discussion of related topics in machine learning research are also presented.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

A survey of transfer learning

Abstract: Machine learning and data mining techniques have been used in numerous real-world applications. An assumption of traditional machine learning methodologies is the training data and testing data are taken from the same domain, such that the input feature space and data distribution characteristics are the same. However, in some real-world machine learning scenarios, this assumption does not hold. There are cases where training data is expensive or difficult to collect. Therefore, there is a need to create high-performance learners trained with more easily obtained data from different domains. This methodology is referred to as transfer learning. This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied to transfer learning. Lastly, there is information listed on software downloads for various transfer learning solutions and a discussion of possible future research work. The transfer learning solutions surveyed are independent of data size and can be applied to big data environments.

Adapting visual category models to new domains

Abstract: Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recognition. We introduce a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on object recognition tasks, the transform-based adaptation technique we develop is general and could be applied to nonimage data. Another contribution is a new multi-domain object database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target domain labels and moderate to large changes in the imaging conditions.