Semantic-event based analysis and segmentation of wedding ceremony videos

Abstract

Wedding is one of the most important ceremonies in our lives. It symbolizes the birth and creation of a new family. In this paper, we present a system for automatically segmenting a wedding ceremony video into a sequence of recognized wedding events, e.g., the couple's wedding kiss. Our goal is to develop an automatic tool for users to efficiently organize, search, and retrieve his/her treasured wedding memories. Furthermore, the event descriptions could benefit and complement the current research in semantic video understanding. Technically, three kinds of event features, i.e., the speech/music discriminator, flashlight detector, and bride indicator, are exploited to build statistical models for each wedding event. Events are then recognized by a hidden Markov model, which takes into account both the fitness of observed features and the temporal rationality of event ordering to improve the segmentation accuracy. We conducted experiments on a rich set of wedding videos, and the results demonstrate the effectiveness of our approach.

Automatic event-based indexing of multimedia content using a joint content-event model

“…The concept detectors that correspond to the five event classes are then evaluated,x n,κ = dκ(śn), κ ∈ [6,7,41,42,82], and the Max Rule [11] is used to assign the test keyframe to the event class with the maximum DoĆ y n = argmax κ∈ [6,7,41,42,82] (xn,κ) .…”

“…[20,6,7]. In [20,7], HMMs are used to recognize ice hockey or wedding ceremony events in video. In [6], a video is represented as a sequence of Bag-of-Words (BoW) histograms and SVMs are used to learn the desired events.…”

Semantic Analysis for Automatic Event Recognition and Segmentation of Wedding Ceremony Videos

“…Therefore, we define thirteen wedding events as listed in Table I. See our prior work [29] for sample key frames and more details.…”

“…At the end, three of them are chosen for their stable performances under various noise types. They are the one-third energy crossing (OEC), the silent interval frequency (SIF), and the music component ratio (MCR), as detailed in our prior work [29].…”

“…This work was partially published in the ACM Workshop on Multimedia Information Retrieval (MIR), 2007 [29]. This work was partially supported by the National Science Council of R.O.C.…”