This paper considers the problem of web video geolocation: we hope to determine where on the Earth a web video was taken. By analyzing a 6.5-million geotagged web video dataset, we observe that there exist inherent geography intimacies between a video with its relevant videos (related videos and same-author videos). This social relationship supplies a direct and effective cue to locate the video to a particular region on the earth. Based on this observation, we propose an effective web video geolocation algorithm by propagating geotags among the web video social relationship graph. For the video that have no geotagged relevant videos, we aim to collect those geotagged relevant images that are content similar with the video (share some visual or textual information with the video) as the cue to infer the location of the video. The experiments have demonstrated the effectiveness of both methods, with the geolocation accuracy much better than state-of-the-art approaches. Finally, an online web video geolocation system: Video2Locatoin (V2L) is developed to provide public access to our algorithm.

Human skin detection in images is desirable in many practical applications, e.g., adult-content filtering. However, existing methods are mainly pixel-based and ignore that human skin is region-based. In this paper, we introduce a successful region detector, i.e., MSER, into the skin detection by regarding the skin region as the maximally stable extremal region (MSER). We extend the original MSER to both color and texture analysis to reduce the skinlike regions1. Furthermore, to be adaptive to the dynamic illumination and chrominance, face detection is used to customize the skin color model to each image. The proposed method has achieved promising performance over our dataset, which is a challenging set with a great part of hard images. Our True Positive Rate is 81.2% under False Positive Rate 8.2%, which outperforms all of eight state-of-the-art algorithms.

Seabird populations are considered an important and accessible indicator of the health of marine environments: variations have been linked with climate change and pollution [1]. However, manual monitoring of large populations is labour-intensive, and requires significant investment of time and effort. In this paper, we propose a novel detection system for monitoring a specific population of Common Guillemots on Skomer Island, West Wales (UK). We incorporate two types of features, Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP), to capture the edge/local shape information and the texture information of nesting seabirds. Optimal features are selected from a large HOG-LBP feature pool by boosting techniques, to calculate a compact representation suitable for the SVM classifier. A comparative study of two kinds of detectors, i.e., whole-body detector, head-beak detector, and their fusion is presented. When the proposed method is applied to the seabird detection, consistent and promising results are achieved.

Portraits, also known as images of people, constitute an important part of consumer photos. Existing methods manage portraits based on either explicit objectives, e.g., a specified person or event, or aesthetics, i.e., the aesthetic quality of portraits. This paper presents a novel system for personalized portraits ranking. First, four kinds of personalized features, i.e., composition, clothing style, affection and social relationship are proposed to quantify users' intent. Then, example-based and sketch-based user interfaces (UI) are developed, which are capable of capturing users' personal intent hardly described by queries or aesthetics. Finally, portraits ranking is implemented by combing these features together with the developed user interfaces. Experimental results show that the system performs well in providing personalized preferences and the proposed features are effective for portraits ranking. From the user study, our system gets promising results.

In computer vision and multimedia search, it is common to use multiple features from different views to represent an object. For example, to well characterize a natural scene image, it is essential to find a set of visual features to represent its color, texture, and shape information and encode each feature into a vector. Therefore, we have a set of vectors in different spaces to represent the image. Conventional spectral-embedding algorithms cannot deal with such datum directly, so we have to concatenate these vectors together as a new vector. This concatenation is not physically meaningful because each feature has a specific statistical property. Therefore, we develop a new spectral-embedding algorithm, namely, multiview spectral embedding (MSE), which can encode different features in different ways, to achieve a physically meaningful embedding. In particular, MSE finds a low-dimensional embedding wherein the distribution of each view is sufficiently smooth, and MSE explores the complementary property of different views. Because there is no closed-form solution for MSE, we derive an alternating optimization-based iterative algorithm to obtain the low-dimensional embedding. Empirical evaluations based on the applications of image retrieval, video annotation, and document clustering demonstrate the effectiveness of the proposed approach.

A successful interactive image retrieval system is expected to quickly return as many relevant results as possible while costing less users' effort. Considering these system demands, firstly we propose a novel semi-supervised learning algorithm called Locally Non-negative Linear Structure Learning (LNLS), which is based on the assumption that the labels of each data should be sufficiently smooth with respect to the locally non-negative linear structure of dataset. It has two main merits: first, it is robust to the small sample learning problem since it learns structure from both labeled and unlabeled data; second, by emphasizing the non-negativity of locally linear structure, this algorithm preserves the non-negative inherent characteristic of image data and can truly reveal the intrinsic structure of the images corpus, especially the asymmetric relationship between images. Meanwhile, we explore an online updating algorithm for LNLS to tackle the large computation cost. Thus the model can be generalized to the new queries or the newly-labeled samples without retraining. Furthermore, an active learning method for LNLS is proposed to make the most of users' effort to improve the learner. The encouraging experimental results demonstrate the effectiveness and efficiency of our proposed methods.

Today with the rapid increasing popularity of web video sharing, digital copyright protection encounters many troubles. Video copy detection schemes are emerging to cope with the digital video piracy and illegal distribution problems. But the large amount of video data and diversity of copy attacks pose difficulties on copy detection. This paper presents a hierarchical scheme to detect video copies, especially the temporal attacked and re-encoded ones. Our algorithm which is based on the ordinal signature of intra frames and effective R*-tree indexing structure archives real time performance. Comparison experiments are conducted on the benchmarked database of CIVR 2007 copy detection showcase and demonstrate the promising results of the proposed approach.