MM

The emergence of cloud computing is presenting us with unprecedented opportunities to redefine how people search for and interact with multimedia on client devices (such as PC, TV, and phone). In this talk, I will introduce some key trends in computing ...

To realize generic image recognition, the system needs to learn an enormous amount of targets in the world and their appearances. Therefore, visual knowledge acquisition using massive amounts of web images has been studied recently, and search-based ...

We describe an efficient and scalable system for automatic image categorization. Our approach seeks to marry scalable "model-free" neighborhood-based annotation with accurate boosting-based per-tag modeling. For accelerated neighborhood-based ...

The Bag-of-Words (BoW) model is a promising image representation for annotation. One critical limitation of existing BoW models is the semantic loss during the codebook generation process, in which BoW simply clusters visual words in Euclidian space. ...

In this paper, we have developed a new multi-label multi-task learning framework to leverage large-scale weakly-tagged images for inter-related classifier training. A novel image and tag cleansing algorithm is developed for tackling the issues of spam, ...

With the rapid growth of multimedia data, it becomes increasingly important to develop semantic concept modeling approaches that are consistently effective, highly efficient, and easily scalable. To this end, we first propose the robust subspace bagging ...

Content-based video copy detection is relevant for structuring large video databases. The use of local features leads to good robustness to most types of photometric or geometric transformations. However, to achieve both good precision and good recall ...

With the proliferation of text and multimedia information, users are now able to find answers to almost any questions on the Web. Meanwhile, they are also bewildered by the huge amount of information routinely presented to them. Question-answering (QA) ...

In this paper, we study two methods to improve the robustness property of projection based hashing methods. For this class of hashing methods, a feature matrix is projected onto a set of projection matrices. Then, the projected values are compared to a ...

In this paper, we propose a novel scale and rotation invariant Gabor texture descriptor for content-based image copy detection. Firstly, the Gabor filters with different orientations and scales using a fixed-size window are constructed. Secondly, the ...

In this paper, we describe a system for detecting duplicate images and videos in a large collection of multimedia data. Our system consists of three major elements: Local-Difference-Pattern (LDP) as the unified feature to describe both images and videos,...

In the paper, we propose and test an unsupervised approach for image ranking. Prior solutions are based on image content and the similarity graph connecting images. We generalize this idea by directly estimating the likelihood of each photo in a feature ...

We focus on the problem of large-scale near duplicate image retrieval. Recent studies have shown that local image features, often referred to as key points, are effective for near duplicate image retrieval. The most popular approach for key point based ...

The evolution of IP video systems has resulted in unprecedented access to a wide range of video material for consumers via IPTV and Web delivery. Retrieval technologies help users find relevant content, but suffer from a paucity of reliable content ...

This paper presents two models for content-based automatic image annotation and retrieval in web image repositories, based on the co-occurrence of tags and visual features in the images. In particular, we show how additional measures can be taken to ...

Multi-concept identification in high volume multimedia streams is critical for a number of applications, including large-scale multimedia analysis, processing, and retrieval. Content of interest is filtered using a collection of binary classifiers that ...

Previous web image re-ranking approaches usually construct similarity measure on image level. Considering the diversity of large scale web image database, these approaches ignore the difference of importance between target area and background area in ...

To make full use of the overwhelming volume of news videos available today, it is necessary to track the development of news stories from different channels, mine their dependencies, and organize them in a semantic way. We propose a novel news topic ...