---
title: "Facial expression (FER2013, AffectNet, RAF-DB)"
description: "Facial expression (FER2013, AffectNet, RAF-DB): compare tasks, official access, usage conditions and evaluation. Includes research-paper mention counts and trends."
url: https://scholar4ai.com/datasets/facial-expression-fer2013-affectnet-raf-db
markdown_url: https://scholar4ai.com/datasets/facial-expression-fer2013-affectnet-raf-db.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "Facial expression (FER2013, AffectNet, RAF-DB): compare tasks, official access, usage conditions and evaluation. Includes research-paper mention counts and trends. (as of 2026-11-05)"
data_url: https://scholar4ai.com/data/rankings.json
updated: 2026-11-05T06:02:37+09:00
window: 2026-10-07 to 2026-11-05
source: OpenAlex (CC0)
---

# Facial expression (FER2013, AffectNet, RAF-DB)

[Browse dataset profiles](https://scholar4ai.com/datasets/directory/page/3.md)

Faces, people, poses, facial expressions and human actions in images and video.

- data category: Face, person and video benchmarks
- 0 papers in the last 7 days
- Names searched for: FER2013, FER-2013, AffectNet, RAF-DB

Most-used data: https://scholar4ai.com/rankings/datasets.md · All Face, person and video benchmarks datasets: https://scholar4ai.com/datasets/face-person-and-video-benchmarks.md

## Tasks, access and usage conditions

Mention counts below measure name matches in tracked papers, not benchmark quality or downloads. A family count can cover multiple datasets; it is not a separate count for each comparison row. Choose a task and version first, preserve evaluation splits, and follow the linked release terms. The site's content license does not replace the datasets' own terms.

*Dataset comparison: tasks, access and usage conditions*

| Dataset / version | Task and evaluation | Access and preparation | Usage conditions |
|---|---|---|---|
| FER2013 | Seven-class facial-expression classification from small grayscale images. Evaluation: Report class balance and macro-F1 as well as accuracy; expression labels do not directly establish a person’s internal emotional state. | [Official source / documentation](https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge) Use the original competition data/rules and distinguish its public and private test partitions. | Accept the original competition and source-image terms. An uploaded copy on another dataset hub does not establish new rights. |
| AffectNet / AffectNet+ | Facial-expression categories and continuous valence/arousal annotations. Evaluation: Identify the original or extended release, label subset and categorical versus continuous task; compare like-for-like splits. | [Official source / documentation](https://www.mohammadmahoor.com/pages/databases/affectnet/) The creator now directs requests through AffectNet+, which includes AffectNet; follow the agreement/request process. | Research purposes only under the creator’s agreement; cite the dataset when using its images. |
| RAF-DB | Basic and compound facial-expression recognition. Evaluation: Separate basic and compound labels, retain the official partition and report class-level performance. | [Official source / documentation](https://openaccess.thecvf.com/content_cvpr_2017/html/Li_Reliable_Crowdsourcing_and_CVPR_2017_paper.html) The original paper identifies the creator’s RAF-DB release. Obtain the dataset through the creator’s current request process; the paper is documentation, not a download. | Confirm the release agreement and permitted purpose with the creator; no universal open-data license is asserted here. |

Guide updated 2026-11-05.

## Key findings

- From Nov 2023 to Oct 2026, 57 archived papers mentioned Facial expression (FER2013, AffectNet, RAF-DB) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Jan 2025 (4).
- No paper of the tracked journals mentioned Facial expression (FER2013, AffectNet, RAF-DB) in the last 30 days (2026-10-07 to 2026-11-05).
- From 2017 to 2026 (so far), Facial expression (FER2013, AffectNet, RAF-DB) was mentioned in 76 papers in the tracked journals, most of them in AI (66), higher education and research (4) and information systems (2).
- 20 of them were published in 2025, against 1 in 2017.
- Since 2023, the institutions with the most of these papers were Chinese Academy of Sciences (5), Institute of Automation (4) and University of Chinese Academy of Sciences (4).
- The journals publishing most of them were Neural Computing and Applications (9), Information Fusion (5) and Pattern Recognition (4).
- The most-cited of them is “A comprehensive review of model compression techniques in machine learning” (Applied Intelligence, 2024), with 271 citations.
- Papers use Facial expression (FER2013, AffectNet, RAF-DB) most often with ImageNet (23), Face recognition (LFW, CelebA, VGGFace2) (10) and Speech emotion (IEMOCAP, RAVDESS) (9); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

## Mentions over 36 months

*Papers mentioning it by publication month, Nov 2023 to Oct 2026 (titles, abstracts and keywords; the full texts of earlier months are still being searched)*

| Trend | Nov 23–Oct 24 | Nov 24–Oct 25 | Nov 25–Oct 26 | 36 months |
|---|---:|---:|---:|---:|
|  | 14 | 21 | 22 | 57 |

## Papers per year

*Papers per publication year and category*

| Category | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 (so far) |
|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
| [AI](https://scholar4ai.com/categories/ai.md) | 1 | 0 | 2 | 2 | 4 | 4 | 5 | 17 | 16 | 15 |
| [Higher Education and Research](https://scholar4ai.com/categories/higher-education-and-research.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| [Information Systems](https://scholar4ai.com/categories/information-systems.md) | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 |
| [Economics](https://scholar4ai.com/categories/economics.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| [Statistics](https://scholar4ai.com/categories/statistics.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| [Operations Research](https://scholar4ai.com/categories/operations-research.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 |
| [Marketing](https://scholar4ai.com/categories/marketing.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| All categories | 1 | 0 | 2 | 2 | 4 | 5 | 6 | 18 | 20 | 18 |

## Where the papers come from

*Journals with the most papers, since 2023*

| # | Journal | Papers |
|---:|---|---:|
| 1 | [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | 9 |
| 2 | [Information Fusion](https://scholar4ai.com/journals/information-fusion.md) | 5 |
| 3 | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | 4 |
| 4 | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 4 |
| 5 | [Artificial Intelligence Review](https://scholar4ai.com/journals/artificial-intelligence-review.md) | 4 |
| 6 | [Neural Networks](https://scholar4ai.com/journals/neural-networks.md) | 4 |
| 7 | [Knowledge-Based Systems](https://scholar4ai.com/journals/knowledge-based-systems.md) | 4 |
| 8 | [Applied Intelligence](https://scholar4ai.com/journals/applied-intelligence.md) | 3 |
| 9 | [Expert Systems with Applications](https://scholar4ai.com/journals/expert-systems-with-applications.md) | 3 |
| 10 | [International Journal of Computer Vision](https://scholar4ai.com/journals/international-journal-of-computer-vision.md) | 2 |

*Institutions with the most papers, since 2023*

| # | Institution | Papers |
|---:|---|---:|
| 1 | [Chinese Academy of Sciences](https://scholar4ai.com/institutions/chinese-academy-of-sciences.md) | 5 |
| 2 | [Institute of Automation](https://scholar4ai.com/institutions/institute-of-automation.md) | 4 |
| 3 | [University of Chinese Academy of Sciences](https://scholar4ai.com/institutions/university-of-chinese-academy-of-sciences.md) | 4 |
| 4 | [Tsinghua University](https://scholar4ai.com/institutions/tsinghua-university.md) | 3 |
| 5 | University of Ljubljana | 3 |
| 6 | Beijing National Research Center for Information Science and Technology | 2 |
| 7 | [Centre National de la Recherche Scientifique](https://scholar4ai.com/institutions/centre-national-de-la-recherche-scientifique.md) | 2 |
| 8 | Centre d'Etudes Superieures Industrielles | 2 |
| 9 | [Queensland University of Technology](https://scholar4ai.com/institutions/queensland-university-of-technology.md) | 2 |
| 10 | Symbiosis International University | 2 |

*Countries with the most papers, since 2023*

| # | Country | Papers |
|---:|---|---:|
| 1 | China | 19 |
| 2 | India | 9 |
| 3 | United Kingdom | 7 |
| 4 | France | 6 |
| 5 | Australia | 5 |
| 6 | Germany | 5 |
| 7 | Spain | 3 |
| 8 | Italy | 3 |
| 9 | Saudi Arabia | 3 |
| 10 | Slovenia | 3 |

*Keywords with the most papers, since 2023*

| # | Keyword | Papers |
|---:|---|---:|
| 1 | facial expression recognition | 24 |
| 2 | emotion recognition | 12 |
| 3 | facial emotion recognition | 11 |
| 4 | FER2013 | 8 |
| 5 | AffectNet | 7 |
| 6 | RAF-DB | 7 |
| 7 | [convolutional neural networks](https://scholar4ai.com/keywords/convolutional-neural-networks.md) | 7 |
| 8 | multimodal emotion recognition | 6 |
| 9 | affective computing | 4 |
| 10 | [attention mechanism](https://scholar4ai.com/keywords/attention-mechanism.md) | 4 |

## Most-cited papers

*Most-cited papers since 2017*

| # | Citations | Per month | Title | Journal | Published | Authors |
|---:|---:|---:|---|---|---|---|
| 1 | 271 | 10.4 | [A comprehensive review of model compression techniques in machine learning](https://doi.org/10.1007/s10489-024-05747-w) | [Applied Intelligence](https://scholar4ai.com/journals/applied-intelligence.md) | 2024-09-02 | Pierre V. Dantas, Waldir Sabino da Silva, Lucas Carvalho Cordeiro et al. |
| 2 | 155 | 2.2 | [FER-net: facial expression recognition using deep neural net](https://doi.org/10.1007/s00521-020-05676-y) | [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | 2021-01-09 | Mohan Karnati, Ayan Seal, Ondřej Krejcar et al. |
| 3 | 99 | 2.9 | [Learning From Human Educational Wisdom: A Student-Centered Knowledge Distillation Method](https://doi.org/10.1109/tpami.2024.3354928) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2024-01-16 | Shunzhi Yang, Jinfeng Yang, MengChu Zhou et al. |
| 4 | 82 | 4.0 | [Emotion recognition for enhanced learning: using AI to detect students’ emotions and adjust teaching methods](https://doi.org/10.1186/s40561-025-00374-5) | [Smart Learning Environments](https://scholar4ai.com/journals/smart-learning-environments.md) | 2025-02-21 | Said Abdelrahim Salloum, Khaled Mohammad Alomari, Aseel M. Alfaisal et al. |
| 5 | 78 | 2.5 | [GPT-4V with emotion: A zero-shot benchmark for Generalized Emotion Recognition](https://doi.org/10.1016/j.inffus.2024.102367) | [Information Fusion](https://scholar4ai.com/journals/information-fusion.md) | 2024-03-21 | Zheng Lian, Licai Sun, Haiyang Sun et al. |

## Used together with

Papers use Facial expression (FER2013, AffectNet, RAF-DB) most often with ImageNet (23), Face recognition (LFW, CelebA, VGGFace2) (10) and Speech emotion (IEMOCAP, RAVDESS) (9); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

*What papers use Facial expression (FER2013, AffectNet, RAF-DB) together with (at least 3 papers; lift 1 = chance)*

| Used with | Type | Papers using both | Lift |
|---|---|---:|---:|
| [ImageNet](https://scholar4ai.com/datasets/imagenet.md) | Dataset | 23 | 6.1 |
| [Face recognition (LFW, CelebA, VGGFace2)](https://scholar4ai.com/datasets/face-recognition-lfw-celeba-vggface2.md) | Dataset | 10 | 21.3 |
| [Speech emotion (IEMOCAP, RAVDESS)](https://scholar4ai.com/datasets/speech-emotion-iemocap-ravdess.md) | Dataset | 9 | 35.4 |
| [CIFAR-10 / CIFAR-100](https://scholar4ai.com/datasets/cifar-10-cifar-100.md) | Dataset | 7 | 3.2 |
| [Twitter / X](https://scholar4ai.com/datasets/twitter-x.md) | Dataset | 6 | 0.8 |
| [YouTube / TikTok](https://scholar4ai.com/datasets/youtube-tiktok.md) | Dataset | 6 | 2.0 |
| [Facebook](https://scholar4ai.com/datasets/facebook.md) | Dataset | 4 | 0.8 |
| [Kaggle](https://scholar4ai.com/datasets/kaggle.md) | Dataset | 4 | 4.4 |
| [Amazon Mechanical Turk](https://scholar4ai.com/datasets/amazon-mechanical-turk.md) | Dataset | 3 | 3.2 |
| [Fine-grained benchmarks (CUB-200, Stanford Cars, Oxford Flowers)](https://scholar4ai.com/datasets/fine-grained-benchmarks-cub-200-stanford-cars-oxford-flowers.md) | Dataset | 3 | 8.2 |
| [IMDb](https://scholar4ai.com/datasets/imdb.md) | Dataset | 3 | 8.0 |
| [Stanford Sentiment Treebank](https://scholar4ai.com/datasets/stanford-sentiment-treebank.md) | Dataset | 3 | 32.6 |

The whole network: https://scholar4ai.com/code/network.md

## Cite this page

Scholar4AI. (2026). Facial expression (FER2013, AffectNet, RAF-DB). Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/facial-expression-fer2013-affectnet-raf-db

```bibtex
@misc{scholar4ai-datasets-facial-expression-fer2013-affectnet-raf-db,
  author = {{Scholar4AI}},
  title = {Facial expression (FER2013, AffectNet, RAF-DB)},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/facial-expression-fer2013-affectnet-raf-db}},
  urldate = {2026-11-05},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).