The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
The potential of vision-language models for content moderation of children’s videos
Open accessAbstract
Natural language supervision has been shown to be effective for zero-shot learning in many computer vision tasks, such as object detection and activity recognition. However, generating informative prompts can be challenging for more subtle tasks, such as video content moderation. This can be difficult, as there are many reasons why a video might be inappropriate, beyond violence and obscenity. For example, scammers may attempt to create junk content that is similar to popular educational videos but with no meaningful information. This paper evaluates the performance of several CLIP variations for content moderation of children's cartoons in both the supervised and zero-shot setting. We show that our proposed model (Vanilla CLIP with Projection Layer) outperforms previous work conducted on the Malicious or Benign (MOB) benchmark for video content moderation. This paper presents an in depth analysis of how context-specific language prompts affect content moderation performance. Our results indicate that it is important to include more context in content moderation prompts, particularly for cartoon videos as they are not well represented in the CLIP training data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The cited source says what the claim attributes to it.
In the citing paper
“These capabilities are increasingly vital for agents operating in domains such as robotics [88], autonomous vehicles [89,90], and visual content moderation [91,92].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [91]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Reynolds, L., & McDonell, K. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451760 · Cited by 952 · cited 2×
“Reynolds and McDonell [11] present an overview of prompt programming strategies for large language models that illustrates how different prompting strategies can yield very different outcomes on downstream tasks.”
BackgroundNeimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00355 · Cited by 551
Research works printed but not linked: 30
- Donchev, 2023, 40 Mind Blowing YouTube Facts, Figures and Statistics - 2023
- Auxier, 2020, Parenting children in the age of screens
- Placido, 2017, YouTubes “Elsagate” illuminates the unintended horrors of the digital age, Forbes, 11
- 10.4236/jss.2015.39033 · DOI
- 2023, Important info for parents about YouTube Kids
- 10.1145/3511808.3557442 · DOI
- 10.32473/flairs.36.133315 · DOI
- Radford, 2021, Learning transferable visual models from natural language supervision
- Wang, 2021, ActionCLIP: A new paradigm for video action recognition, arXiv preprint
- 10.1145/3503161.3549201 · DOI
- 10.1145/3501247.3531556 · DOI
- 10.1109/ACCESS.2022.3147519 · DOI
- 10.1145/3297280.3297487 · DOI
- 10.1145/3442442.3452314 · DOI
- 10.1007/s11042-022-12709-2 · DOI
- Jia, 2021, Scaling up visual and vision-language representation learning with noisy text supervision
- 10.1109/ICCV.2015.510 · DOI · Paper page
- 10.1109/cvpr52729.2023.00633 · DOI
- Yang, 2023, AIM: Adapting image models for efficient video action recognition
- Kaliamoorthi, 2019, Prado: Projection attention networks for document classification on-device, 10.18653/v1/D19-1506 · DOI
- Sankar, 2020, Proformer: Towards on-device lsh projection based transformers, arXiv preprint
- Frome, 2013, Devise: A deep visual-semantic embedding model, Advances in neural information processing systems, 26
- Kay, 2017, The Kinetics Human Action Video Dataset
- Agrawal, 1994, Fast algorithms for mining association rules, 1215, 487
- Soomro, 2012, UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Krizhevsky, 2009, Learning multiple layers of features from tiny images
- 10.1007/978-3-642-42051-1_16 · DOI · Paper page
- 10.1109/CVPR.2017.502 · DOI · Paper page
- 10.1109/CVPR.2015.7298878 · DOI · Paper page
- Lattman, 2007, The origins of Justice Stewarts I know it when I see it
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
Metadata
- Authors
- Ahmed, S. H., Hu, S., & Sukthankar, G.
- Affiliations
- University of Central Florida (US)
- Venue
- 2023 International Conference on Machine Learning and Applications (ICMLA)
- Publisher
- IEEE
- Published
- 2023-12-15
- Pages
- 1237-1241
- OpenAlex
- W4392943349
- Cited by
- 4
- References
- 4
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 1
- FWCI
- 0.71
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Conference on Machine Learning and Applications (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- video content moderation, children's animation, vision-language models, CLIP, zero-shot learning, natural language supervision, prompt engineering, projection layer, educational videos
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The potential of vision-language models for content moderation of children’s videos. https://app.cochat.ai/papers/10.1109/icmla58977.2023.00186
- The paper
- Ahmed, S. H., Hu, S., & Sukthankar, G. (2023). The potential of vision-language models for content moderation of children’s videos. 2023 International Conference on Machine Learning and Applications (ICMLA). https://doi.org/10.1109/icmla58977.2023.00186
