Selecting User Generated Content for Use in Media Productions

Bailer, Werner; Weiss, Wolfgang; Wechtitsch, Stefanie

doi:10.1007/978-3-319-27674-8_38

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interactive systems range from carefully crafted user interfaces (UIs) which support users in fast manual browsing of many hours of video via keyframes (Hürst et al, 2015), to more complex methods which can dynamically cluster or re-rank keyframes based on visual similarity or highlighted concepts (Barthel et al, 2015; Lu et al, 2017), or filter keyframes based on colours or objects present (Bailer et al, 2016;Moumtzidou et al, 2017). Ultimately however, each approach aims to support the user in quickly identifying promising scenes before watching them back to make judgements about their relevance.…”

Section: Interactive Content-based Video Retrievalmentioning

confidence: 99%

The development of a video retrieval system using a clinician-led approach

Darby

Sánchez

Bew

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

Patient video taken at home can provide valuable insights into the recovery progress during a programme of physical therapy, but is very time consuming for clinician review. Our work focussed on i) enabling any patient to share information about progress at home, simply by sharing video and ii) building intelligent systems to support Physical Therapists (PTs) in reviewing this video data and extracting the necessary detail. This paper reports the development of the system, appropriate for future clinical use without reliance on a technical team, and the clinician involvement in that development. We contribute an interactive contentbased video retrieval system that significantly reduces the time taken for clinicians to review videos, using human head movement as an example. The system supports query-by-movement (clinicians move their own body to define search queries) and retrieves the essential fine-grained movements needed for clinical interpretation. This is done by comparing sequences of image-based pose estimates (here head rotations) through a distance metric (here Fréchet distance) and presenting a ranked list of similar movements to clinicians for review. In contrast to existing intelligent systems for retrospective review of human movement, the system supports a flexible analysis where clinicians can look for any movement that interests them. Evaluation by a group of PTs with expertise in training movement control showed that 96% of all relevant movements were identified with time savings of as much as 99.1% compared to reviewing target videos in full. The novelty of this contribution includes retrospective progress monitoring that preserves context through video, and content-based video retrieval that supports both fine-grained human actions and queryby-movement. Future research, including large clinician-led studies, will refine the technical aspects and explore the benefits in terms of patient outcomes, PT time, and financial savings over the course of a programme of therapy. It is anticipated that this clinician-led approach will mitigate the reported slow clinical uptake of technology with resulting patient benefit.

show abstract

Section: Interactive Content-based Video Retrievalmentioning

confidence: 99%

The development of a video retrieval system using a clinician-led approach

Darby

Sánchez

Bew

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…The system described in [4] provides a video browsing tool allowing users to efficiently find relevant UGC in large collections. The tool employs iterative clustering on both readily available metadata as well as computed visual features.…”

Section: Automated Processing/classification Of Video and Director Sumentioning

confidence: 99%

“…Even though the resolution and sensor quality of smartphone cameras has significantly increased over the last years, currently the videos and images shown on the large on-stage screens originate exclusively from the limited set of professional cameras installed throughout the event venue. Integrating this UserGenerated Content (UGC) as an additional source of footage into the live event media production would not only offer more camera perspectives to the director, outside the scope of professional camera coverage, but also increase the engagement of the public in the event [4]. This paper presents the design and validation of a framework for collecting and showing user-generated videos at large-scale events.…”

Section: Introductionmentioning

confidence: 99%

The crowd as a cameraman: on-stage display of crowdsourced mobile video at large-scale events

Bohez

Daneels

Herzeele

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

Recording videos with smartphones at large-scale events such as concerts and festivals is very common nowadays. The se videos register the atmosphere of the event as it is experienced by the crowd and offer a perspective that is hard to capture by the professional cameras installed throughout the venue. In this article, we present a framework to collect videos from smartphones in the public and blend these into a mosaic that can be readily mixed with professional camera footage and shown on displays during the event. The video upload is prioritized by matching requests of the event director with video metadata, while taking into account the available wireless network capacity. The proposed framework's main novelty is its scalability, supporting the real-time transmission, processing and display of videos recorded by hundreds of simultaneous users in ultra-dense Wi-Fi environments, as well as its proven integration in commercial production environments. The framework has been extensively validated in a controlled lab setting with up to 1 000 clients as well as in a field trial where 1 183 videos were collected from 135 participants recruited from an audience of 8 050 people. 90 % of those videos were uploaded within 6.8 minutes.

show abstract

Automatic Analysis of Amateur Film and Video Collections

Thallinger

Bailer

2021

2021 International Conference on Content-Based Multimedia Indexing (CBMI)

View full text Add to dashboard Cite

Selecting User Generated Content for Use in Media Productions

Cited by 3 publications

References 10 publications

The development of a video retrieval system using a clinician-led approach

The development of a video retrieval system using a clinician-led approach

The crowd as a cameraman: on-stage display of crowdsourced mobile video at large-scale events

Automatic Analysis of Amateur Film and Video Collections

Contact Info

Product

Resources

About