CoChat
Sign Up
Cited by 343Image and Video Quality AssessmentDigital Media Forensic DetectionImage Retrieval and Classification Techniques

The Konstanz natural video database (KoNViD-1k)

Open access
Hosu, Vlad, Hahn, Franz, Jenadeleh, Mohsen, Lin, Hanhe, Men, Hui, Sziranyi, Tamas, Li, Shujun, Saupe, Dietmar·2017·2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)
DOI 10.1109/qomex.2017.7965673
Open this paper in CoChat — free accountOpen PDF

Abstract

Subjective video quality assessment (VQA) strongly depends on semantics, context, and the types of visual distortions. Currently, all existing VQA databases include only a small number of video sequences with artificial distortions. The development and evaluation of objective quality assessment methods would benefit from having larger datasets of real-world video sequences with corresponding subjective mean opinion scores (MOS), in particular for deep learning purposes. In addition, the training and validation of any VQA method intended to be ‘general purpose’ requires a large dataset of video sequences that are representative of the whole spectrum of available video content and all types of distortions. We report our work on KoNViD-1k, a subjectively annotated VQA database consisting of 1,200 public-domain video sequences, fairly sampled from a large public video dataset, YFCC100m. We present the challenges and choices we have made in creating such a database aimed at ‘in the wild’ authentic distortions, depicting a wide variety of content.

Integrity signals

Registry

Crossref · 10.1109/qomex.2017.7965673

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • KoNViD-1k consists of 1,200 public-domain videos sampled from the YFCC100M dataset, annotated by 642 crowd-workers.

    “It consists of 1,200 public-domain videos sampled from the YFCC100M dataset [15], and was annotated by 642 crowd-workers.”

    From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [10]

  • SOTA deep CNN-based BVQA models produce accurate quality predictions on legacy (single synthetic distortion) video datasets but struggle on recent in-the-wild UGC databases.

    “These SOTA deep CNN-based BVQA models [71][74] produce accurate quality predictions on legacy (single synthetic distortion) video datasets [1], [6], but struggle on recent in-the-wild UGC databases [10], [12], [13].”

    From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [10]

  • TLVQM currently achieves SOTA performance on three UGC video quality databases, CVD2014, KoNViD-1k, and LIVE-Qualcomm, at a reasonably low complexity.

    “The model currently achieves SOTA performance on three UGC video quality databases, CVD2014 [12], KoNViD-1k [10], and LIVE-Qualcomm [13], at a reasonably low complexity, as reported by the authors.”

    From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [10]

The citation lists haven’t been fetched yet

References 25 · Cited by 343

Authors
Hosu, V., Hahn, F., Jenadeleh, M., Lin, H., Men, H., Sziranyi, T., Li, S., & Saupe, D.
Affiliations
  • University of Konstanz (DE)
  • University of Surrey (GB)
ORCID
Venue
2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)
Publisher
IEEE
Published
2017-05
Pages
1-6
DOI
10.1109/qomex.2017.7965673
OpenAlex
W2611434713
Cited by
343
References
25
Citations by year
2026: 22 · 2025: 59 · 2024: 60 · 2023: 60 · 2022: 45 · 2021: 55 · 2020: 24 · 2019: 9 · 2018: 6 · 2017: 3
FWCI
3.36
Type
conference paper
Language
en
Open access
Licence
public-domain
Locations
  • International Conference on Quality of Multimedia Experience (QoMEX) (publishedVersion, public-domain)
  • Kent Academic Repository (University of Kent) (acceptedVersion)
  • Surrey Research Insight Open Access (The University of Surrey) (submittedVersion)
  • KOPS (University of Konstanz) (submittedVersion, public-domain)
  • Discovery Research Portal (University of Dundee) (submittedVersion, public-domain)
  • SZTAKI Publication Repository (Hungarian Academy of Sciences) (submittedVersion)
Funders
Deutsche Forschungsgemeinschaft (SFB/Transregio 161)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
Keywords
video quality assessment, subjective quality database, mean opinion score, in-the-wild videos, objective quality assessment

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review