Advance on large scale near-duplicate video retrieval

Emerging Internet services and applications attract increasing users to involve in diverse video-related activities,such as video searching,video downloading,video sharing and so on.As normal operations,they lead to an explosive growth of online video volume,and inevitably give rise to the massive near-duplicate contents.Near-duplicate video retrieval(NDVR)has always been a hot topic.The primary purpose of this paper is to present a comprehensive survey and an updated review of the advance on large-scale NDVR to supply guidance for researchers.Specifically,we summarize and compare the definitions of near-duplicate videos(NDVs)in the literature,analyze the relationship between NDVR and its related research topics theoretically,describe its generic framework in detail,investigate the existing state-of-the-art NDVR systems.Finally,we present the development trends and research directions of this topic.

Visual polysemy and synonymy:toward near-duplicate image retrieval

that are duplicate or near duplicate to a query image.One of the most popular and practical methods in near-duplicate image retrieval is based on bag-of-words(BoW)model.However,the fundamental deficiency of current BoW method is the gap between visual word and image’s semantic meaning.Similar problem also plagues existing text retrieval.A prevalent method against such issue in text retrieval is to eliminate text synonymy and polysemy and therefore improve the whole performance.Our proposed approach borrows ideas from text retrieval and tries to overcome these deficiencies of BoW model by treating the semantic gap problem as visual synonymy and polysemy issues.We use visual synonymy in a very general sense to describe the fact that there are many different visual words referring to the same visual meaning.By visual polysemy,we refer to the general fact that most visual words have more than one distinct meaning.To eliminate visual synonymy,we present an extended similarity function to implicitly extend query visual words.To eliminate visual polysemy,we use visual pattern and prove that the most efficient way of using visual pattern is merging visual word vector together with visual pattern vector and obtain the similarity score by cosine function.In addition,we observe that there is a high possibility that duplicates visual words occur in an adjacent area.Therefore,we modify traditional Apriori algorithm to mine quantitative pattern that can be defined as patterns containing duplicate items.Experiments prove quantitative patterns improving mean average precision(MAP)significantly.

Speed-up Multi-modal Near Duplicate Image Detection

Near-duplicate image detection is a necessary operation to refine image search results for efficient user exploration. The existences of large amounts of near duplicates require fast and accurate automatic near-duplicate detection methods. We have designed a coarse-to-fine near duplicate detection framework to speed-up the process and a multi-modal integra-tion scheme for accurate detection. The duplicate pairs are detected with both global feature (partition based color his-togram) and local feature (CPAM and SIFT Bag-of-Word model). The experiment results on large scale data set proved the effectiveness of the proposed design.

A Novel Web Video Event Mining Framework with the Integration of Correlation and Co-Occurrence Information

The massive web videos prompt an imperative demand on efficiently grasping the major events. However, the distinct characteristics of web videos, such as the limited number of features, the noisy text information, and the unavoidable error in near-duplicate keyframes （NDKs） detection, make web video event mining a challenging task. In this paper, we propose a novel four-stage framework to improve the performance of web video event mining. Data preprocessing is the first stage. Multiple Correspondence Analysis （MCA） is then applied to explore the correlation between terms and classes, targeting for bridging the gap between NDKs and high-level semantic concepts. Next, co-occurrence information is used to detect the similarity between NDKs and classes using the NDK-within-video information. Finally, both of them are integrated for web video event mining through negative NDK pruning and positive NDK enhancement. Moreover, both NDKs and terms with relatively low frequencies are treated as useful information in our experiments. Experimental results on large-scale web videos from YouTube demonstrate that the proposed framework outperforms several existing mining methods and obtains good results for web video event mining.