ViComp: composition of user-generated videos

Bano, Sophia; Cavallaro, Andrea

doi:10.1007/s11042-015-2641-2

Cited by 11 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Maar ze waren wel geschikt om vergelijkingen te trekken tussen verschillende verhalen op internationaal niveau. 14 Vooral Europese sprookjes krijgen een AT (Aarne -Thompson) index. De AT-index helpt dus aanverwante verhalen uit verschillende landen te identificeren.…”

Section: De Internationale En De Hongaarse Indeling Van Sprookjesunclassified

De koning op het dievenpad

Csontos,

Pusztai

2024

actaneer

View full text Add to dashboard Cite

This study examines two stories from the Middle Ages: The Dutch knight novel, Karel ende Elegast and the Hungarian folk tale, Mátyás király lopni megy [King Matthias goes stealing]. In both stories, the king in disguise goes to steal with an accomplice (an experienced thief). As a result, an attack on the king on the next day is prevented. The motif of the king in disguise having to go stealing to uncover a conspiracy against him is a universal fairy tale motif. In different countries and cultures, one can find this wandering motif from Norway to Mongolia. In this study, we want to make a Hungarian contribution to this research.

show abstract

Section: De Internationale En De Hongaarse Indeling Van Sprookjesunclassified

De koning op het dievenpad

Csontos,

Pusztai

2024

actaneer

View full text Add to dashboard Cite

show abstract

“…The system proposed in [6] edits the footage from multiple social cameras, and the quality assessment highly depends on the 3D reconstruction of scenes. Moreover, the audio information is also used by [4,3] to perform camera selection. In the video montage system [13] which composes the mashups by retrieving the specific footage, the semantics of the video content is extracted to match the query information, such as the script texts [14], voices [15], etc.…”

Section: Related Workmentioning

confidence: 99%

“…Various view selection algorithms have also been introduced to achieve different goals. The greedy selection [4,3] is a popular strategy, but the solutions usually are not globally optimal. The DP-based methods [2,10] can obtain the optimal solutions numerically, but the selections at the current time are made without considering the future information, and the final result is retrieved in a backward manner.…”

Section: Related Workmentioning

confidence: 99%

“…recording the human target, e.g., a suspect at a crime scene, a child in a playground, etc., the algorithm automatically selects one of the camera views that presents the target in the best way according to certain criteria, while also following general editing principles for the entire time period. Previous studies have proposed mashup systems to edit the performance videos [1,2,3], concert recordings [4], football match live streams [5], and social videos [6], etc. However, the quality assessment methods they used aim at improving the diversified viewing experience, rather than depicting the individual's states and activities, which should be emphasized in the mashup of personal videos in the aforementioned scenarios.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Based Automatic Personal Mashup Generation

Liu

Cao

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Synchronized video editing system, or mashup generation from multiple synchronized videos, has gained much attention due to its high efficiency and low cost in processing videos to convey information. However, few of the existing methods focus on generating the personal mashup over a complete timeline from synchronized surveillance videos, which is increasingly demanded for effectively presenting personal activities without violating the privacy of others. To fill this gap, we develop a Reinforcement Learning (RL)-based personal mashup generation system, which assesses the frame quality at a semantic level and formulates the view selection as an RL problem to improve the efficiency in retrieving the mashups with arbitrary beginnings. Furthermore, we propose a framing objective to perform spatial editing, which enables the views to automatically zoom in and out, so as to present the target people more comprehensively. Both qualitative and quantitative analyses are presented to demonstrate the effectiveness of the proposed frame quality measurements, the RLbased algorithm, and the framing objective.

show abstract

“…Some software simplified the editing step. For example, (Shrestha et al 2010;Bano and Cavallaro 2015) automatically combined the most desirable segments from different recordings resulting in a single video stream. (Casares et al 2002) used metadata to make digital video editing more accessible to novices.…”

Section: Simplifying Video Editing Stepmentioning

confidence: 99%

Protocols and software for simplified educational video capture and editing

et al. 2019

View full text Add to dashboard Cite

Recently, educational videos have become important parts of e-learning systems which have in turn become widely used due to their flexibility. These videos should be of high quality since higher production values lead to superior learning outcomes. However, creating high quality video is a difficult task for teachers since it needs technical knowledge that includes video recording and timeline usage. Hence, creating educational video production software, that is at the same time easy-to-use and able to produce high quality educational videos, is very advantageous. In this paper, we developed protocols for an easy-to-use piece of software that enables teachers that have little technological background to produce their own educational videos autonomously. In fact, our contribution is to reduce the complexity of the whole video production process by introducing a preparation step based on micro-teaching and upstream specification. An evaluation of the software with six teachers is performed. This evaluation, based on think-aloud protocol and quantitative measurements, showed that the introduction of the preparation step allowed the participant teachers to produce high quality educational videos in less than three hours.

show abstract

ViComp: composition of user-generated videos

Cited by 11 publications

References 36 publications

De koning op het dievenpad

De koning op het dievenpad

Reinforcement Learning Based Automatic Personal Mashup Generation

Protocols and software for simplified educational video capture and editing

Contact Info

Product

Resources

About