Large-scale Video Collections Research Articles

Efficient video collection association using geometry-aware Bag-of-Iconics representations

Recent years have witnessed the dramatic evolution in visual data volume and processing capabilities. For example, technical advances have enabled 3D modeling from large-scale crowdsourced photo collections. Compared to static image datasets, exploration and exploitation of Internet video collections are still largely unsolved. To address this challenge, we first propose to represent video contents using a histogram representation of iconic imagery attained from relevant visual datasets. We then develop a data-driven framework for a fully unsupervised extraction of such representations. Our novel Bag-of-Iconics (BoI) representation efficiently analyzes individual videos within a large-scale video collection. We demonstrate our proposed BoI representation with two novel applications: (1) finding video sequences connecting adjacent landmarks and aligning reconstructed 3D models and (2) retrieving geometrically relevant clips from video collections. Results on crowdsourced datasets illustrate the efficiency and effectiveness of our proposed Bag-of-Iconics representation.

Revealing Event Saliency in Unconstrained Video Collection.

Recent progresses in multimedia event detection have enabled us to find videos about a predefined event from a large-scale video collection. Research towards more intrinsic unsupervised video understanding is an interesting but understudied field. Specifically, given a collection of videos sharing a common event of interest, the goal is to discover the salient fragments, i.e., the curt video fragments that can concisely portray the underlying event of interest, from each video. To explore this novel direction, this paper proposes an unsupervised event saliency revealing framework. It first extracts features from multiple modalities to represent each shot in the given video collection. Then, these shots are clustered to build the cluster-level event saliency revealing framework, which explores useful information cues (i.e., the intra-cluster prior, inter-cluster discriminability, and inter-cluster smoothness) by a concise optimization model. Compared with the existing methods, our approach could highlight the intrinsic stimulus of the unseen event within a video in an unsupervised fashion. Thus, it could potentially benefit to a wide range of multimedia tasks like video browsing, understanding, and search. To quantitatively verify the proposed method, we systematically compare the method to a number of baseline methods on the TRECVID benchmarks. Experimental results have demonstrated its effectiveness and efficiency.

Rule-Based Semantic Concept Classification from Large-Scale Video Collections

The explosive growth and increasing complexity of the multimedia data have created a high demand of multimedia services and applications in various areas so that people can access and distribute the data easily. Unfortunately, traditional keyword-based information retrieval is no longer suitable. Instead, multimedia data mining and content-based multimedia information retrieval have become the key technologies in modern societies. Among many data mining techniques, association rule mining (ARM) is considered one of the most popular approaches to extract useful information from multimedia data in terms of relationships between variables. In this paper, a novel rule-based semantic concept classification framework using weighted association rule mining (WARM), capturing the significance degrees of the feature-value pairs to improve the applicability of ARM, is proposed to deal with major issues and challenges in large-scale video semantic concept classification. Unlike traditional ARM that the rules are generated by frequency count and the items existing in one rule are equally important, our proposed WARM algorithm utilizes multiple correspondence analysis (MCA) to explore the relationships among features and concepts and to signify different contributions of the features in rule generation. To the authors best knowledge, this is one of the first WARM-based classifiers in the field of multimedia concept retrieval. The experimental results on the benchmark TRECVID data demonstrate that the proposed framework is able to handle large-scale and imbalanced video data with promising classification and retrieval performance.

Special Section on Object and Event Classification in Large-Scale Video Collections

The nine papers in this special section on object and event classification in large-scale video collections can be categorized into four themes: video indexing, concept detection, video summarization, and event recognition.

Web video retagging

Tags associated with web videos play a crucial role in organizing and accessing large-scale video collections. However, the raw tag list (RawL) is usually incomplete, imprecise and unranked, which reduces the usability of tags. Meanwhile, compared with studies on improving the quality of web image tags, tags associated with web videos are not studied to the same extent. In this paper, we propose a novel web video tag enhancement approach called video retagging, which aims at producing the more complete, precise, and ranked retagged tag list (RetL) for web videos. Given a web video, video retagging first collect its textually and visually related neighbor videos. All tags attached to the neighbors are treated as possible relevant ones and then RetL is generated by inferring the degree of relevance of the tags from both global and video-specific perspectives, using two different graph based models. Two kinds of experiments, i.e., application-oriented video search and categorization and user-based subjective studies are carried out on a large-scale web video dataset, which demonstrate that in most cases, RetL is better than RawL in terms of completeness, precision and ranking.

Special Issue of IEEE Transactions on Multimedia Object and Event Classification in Large-Scale Video Collections

Special Issue of IEEE Transactions on Multimedia Object and Event Classification in Large-Scale Video Collections

Special Issue of IEEE Transactions on Multimedia Object and Event Classification in Large-Scale Video Collections

Special Issue of IEEE Transactions on Multimedia Object and Event Classification in Large-Scale Video Collections

Incorporating Concept Ontology for Hierarchical Video Classification, Annotation, and Visualization

Most existing content-based video retrieval (CBVR) systems are now amenable to support automatic low-level feature extraction, but they still have limited effectiveness from a user's perspective because of the semantic gap. Automatic video concept detection via semantic classification is one promising solution to bridge the semantic gap. To speed up SVM video classifier training in high-dimensional heterogeneous feature space, a novel multimodal boosting algorithm is proposed by incorporating feature hierarchy and boosting to reduce both the training cost and the size of training samples significantly. To avoid the inter-level error transmission problem, a novel hierarchical boosting scheme is proposed by incorporating concept ontology and multitask learning to boost hierarchical video classifier training through exploiting the strong correlations between the video concepts. To bridge the semantic gap between the available video concepts and the users' real needs, a novel hyperbolic visualization framework is seamlessly incorporated to enable intuitive query specification and evaluation by acquainting the users with a good global view of large-scale video collections. Our experiments in one specific domain of surgery education videos have also provided very convincing results.