A hierarchical organization scheme for video data

Zhang, Yu Jin; Lu, Huangjun

doi:10.1016/s0031-3203(01)00189-3

Cited by 27 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in our task the sequences of frames are matched, so it is possible to slightly defer the normalization. Thus, in this paper we consider either conventional approach with aggregation of the normalized features (hereinafter "L 2 -norm -> Medoid" (2) and "L 2 -norm -> AvePool" (3)), or its slightly modified version with normalization of aggregated vectors (2), (3) (hereinafter "Medoid -> L 2 -norm" and "AvePool -> L 2 -norm", respectively).…”

Section: Automatic Organization Of Video Datamentioning

confidence: 99%

Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks

Sokolova

Kharchevnikova

Savchenko

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we propose the two-stage approach of organizing information in video surveillance systems. At first, the faces are detected in each frame and a video stream is split into sequences of frames with face region of one person. Secondly, these sequences (tracks) that contain identical faces are grouped using face verification algorithms and hierarchical agglomerative clustering. Gender and age are estimated for each cluster (person) in order to facilitate the usage of the organized video collection. The particular attention is focused on the aggregation of features extracted from each frame with the deep convolutional neural networks. The experimental results of the proposed approach using YTF and IJB-A datasets demonstrated that the most accurate and fast solution is achieved for matching of normalized average of feature vectors of all frames in a track.

show abstract

Section: Automatic Organization Of Video Datamentioning

confidence: 99%

Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks

Sokolova

Kharchevnikova

Savchenko

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The purpose of video organization in Das and Liou [1998] is to achieve a content-based indexing of video archives. In Zhang and Lu [2002], a video clip is organized into four layers {frame, shot, episode, video program} to facilitate indexing, browsing, and querying. Similarly, in Zhu et al [2005] a video clip is organized into a hierarchy of video contents {keyframe, shot, group, scene, video} with which hierarchical video browsing and retrieval are integrated for efficient video access.…”

Section: Related Workmentioning

confidence: 99%

A Sketch-Based Approach for Interactive Organization of Video Clips

Liu

et al. 2014

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

With the rapid growth of video resources, techniques for efficient organization of video clips are becoming appealing in the multimedia domain. In this article, a sketch-based approach is proposed to intuitively organize video clips by: (1) enhancing their narrations using sketch annotations and (2) structurizing the organization process by gesture-based free-form sketching on touch devices. There are two main contributions of this work. The first is a sketch graph, a novel representation for the narrative structure of video clips to facilitate content organization. The second is a method to perform context-aware sketch recommendation scalable to large video collections, enabling common users to easily organize sketch annotations. A prototype system integrating the proposed approach was evaluated on the basis of five different aspects concerning its performance and usability. Two sketch searching experiments showed that the proposed context-aware sketch recommendation outperforms, in terms of accuracy and scalability, two state-of-the-art sketch searching methods. Moreover, a user study showed that the sketch graph is consistently preferred over traditional representations such as keywords and keyframes. The second user study showed that the proposed approach is applicable in those scenarios where the video annotator and organizer were the same person. The third user study showed that, for video content organization, using sketch graph users took on average 1/3 less time than using a mass-market tool Movie Maker and took on average 1/4 less time than using a state-of-theart sketch alternative. These results demonstrated that the proposed sketch graph approach is a promising video organization tool.

show abstract

“…A shot in a video sequence refers to a contiguous recording of one or more video frames depicting a continuous action in time and space. In a video database, the isolation of shots is of interest because the shot level organization of video sequences is considered to be the basic unit in video indexing and is appropriate for video browsing and content-based video retrieval [12]. In general, there are two types of shot changes: (1) abrupt change or hard cut, and (2) gradual change due to the various video editing effects, such as fade-in, fade-out, dissolve and wipe.…”

Section: Shot Boundary Detection Algorithmmentioning

confidence: 99%

“…Such a multilayer abstraction makes it not only more convenient to reference video information but also simplifies video indexing and storage organization. Several multilevel structures have been proposed in the literature [6,7,12,31,32]. However, their tree structure is not adaptive.…”

Section: Scene Treementioning

confidence: 99%