Near-Duplicate Subsequence Matching Between the Continuous Stream and Large Video Dataset

Abstract

In this paper, we study the subsequence matching problem of near-duplicate video detection. In particular, we address the application of monitoring a continuous stream with a large video dataset. To achieve real-time response and high accuracy, we propose a novel framework containing two characteristics. First, the subsequence matching is transformed to a 2-D Hough space projection of pairwise frame similarities between two subsequences. We present an approximate Hough transform that replaces the 2-D Hough space with a 1-D Hough space. The near-duplicate subsequence detection can be deemed to be the voting and searching in the 1-D Hough space with a lower time complexity. Second, a coarse-to-fine matching strategy is incorporated in the proposed framework. The coarse level matching selects the candidate videos based on the time-decay hit frequency between the query stream and dataset videos. The fine level matching applies the approximate Hough transform to detect the near-duplicate subsequences coexisting within the query stream and candidate videos. Several state-of-the-art methods are implemented for comparison. Experimental results show our framework outperforms in terms of accuracy and efficiency.Index Terms-Content-based retrieval, near-duplicate detection, video copy detection.

Scheduling algorithms for time-constrained big-file transfers in the Internet of Vehicles

“…In order to achieve higher network utilization, big-file transfer based on multi-path routing has attracted significant attention, particularly for resource-limited networks [8,9] . Multi-path file transfer problems encompass both the single-file multi-path transfer problem [10][11][12] and the multi-file multi-path transfer problem [13][14][15][16] . However, most of previous works do not consider the size of files and how to search for a path set in a given network.…”

Incremental probabilistic Latent Semantic Analysis for video retrieval

“…For these incremental databases, topic extraction algorithms such as pLSA and LDA, have a computational burden too heavy to recompute topics each time the databases increase their size with new samples. In other kinds of applications, some authors [24] have shown the advantages of considering an incremental scenario to manage large video collections in an efficient way, therefore this scheme may help us to improve the topic extraction task. In this work, we are interested in exploring whether video retrieval performance is affected by the use of different topic models and how video retrieval systems based on topic models are able to efficiently manage these incremental databases.…”

Frame-level Matching for Near Duplicate Videos Using Binary Frame Descriptor

“…, and Chang-Su Kim [3,4] 은 오직 유사중복 구간의 유무만을 결정한다. 반면에 다 이나믹 프로그래밍(dynamic programming)을 기반으로 최 적화 문제를 해결함으로써 더욱 정밀한 프레임 단위의 정 합을 가능하게 하는 기법들도 연구되고 있다 [5][6][7] .…”