---
title: "Action recognition (Kinetics, UCF101, HMDB51)"
description: "From Nov 2023 to Oct 2026, 198 archived papers mentioned Action recognition (Kinetics, UCF101, HMDB51) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Jan 2026 (13)."
url: https://scholar4ai.com/datasets/action-recognition-kinetics-ucf101-hmdb51
markdown_url: https://scholar4ai.com/datasets/action-recognition-kinetics-ucf101-hmdb51.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "From Nov 2023 to Oct 2026, 198 archived papers mentioned Action recognition (Kinetics, UCF101, HMDB51) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in… (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)
---

# Action recognition (Kinetics, UCF101, HMDB51)

[Browse dataset profiles](https://scholar4ai.com/datasets/directory.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: Kinetics-400, Kinetics-600, Kinetics-700, UCF101, UCF-101, HMDB51, HMDB-51, Something-Something, ActivityNet

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



## Key findings

- From Nov 2023 to Oct 2026, 198 archived papers mentioned Action recognition (Kinetics, UCF101, HMDB51) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Jan 2026 (13).
- Action recognition (Kinetics, UCF101, HMDB51) was mentioned in 3 papers in the last 30 days (2026-10-07 to 2026-11-05), ranking #103 of the 246 datasets mentioned.
- By journal category: AI (3).
- Most of them appeared in Pattern Recognition (2) and International Journal of Computer Vision (1).
- From 2017 to 2026 (so far), Action recognition (Kinetics, UCF101, HMDB51) was mentioned in 290 papers in the tracked journals, most of them in AI (288), economics (1) and information systems (1).
- 69 of them were published in 2025, against 9 in 2017.
- Since 2023, the institutions with the most of these papers were Chinese Academy of Sciences (17), Shanghai Artificial Intelligence Laboratory (12) and Peking University (11).
- The journals publishing most of them were IEEE Transactions on Pattern Analysis and Machine Intelligence (54), International Journal of Computer Vision (54) and Pattern Recognition (15).
- The most-cited of them is “Vision-Language Models for Vision Tasks: A Survey” (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024), with 998 citations.
- Papers use Action recognition (Kinetics, UCF101, HMDB51) most often with ImageNet (90), YouTube / TikTok (50) and MS COCO (34); it has 31 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 |
|---|---:|---:|---:|---:|
|  | 61 | 71 | 66 | 198 |

## 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) | 9 | 6 | 7 | 17 | 16 | 19 | 30 | 60 | 69 | 55 |
| [Economics](https://scholar4ai.com/categories/economics.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| [Information Systems](https://scholar4ai.com/categories/information-systems.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| All categories | 9 | 6 | 7 | 17 | 16 | 19 | 30 | 60 | 69 | 57 |

## Where the papers come from

*Journals with the most papers, since 2023*

| # | Journal | Papers |
|---:|---|---:|
| 1 | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 54 |
| 2 | [International Journal of Computer Vision](https://scholar4ai.com/journals/international-journal-of-computer-vision.md) | 54 |
| 3 | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | 15 |
| 4 | [Artificial Intelligence Review](https://scholar4ai.com/journals/artificial-intelligence-review.md) | 14 |
| 5 | [IEEE Transactions on Neural Networks and Learning Systems](https://scholar4ai.com/journals/ieee-transactions-on-neural-networks-and-learning-systems.md) | 12 |
| 6 | [Expert Systems with Applications](https://scholar4ai.com/journals/expert-systems-with-applications.md) | 11 |
| 7 | [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | 9 |
| 8 | [Knowledge-Based Systems](https://scholar4ai.com/journals/knowledge-based-systems.md) | 8 |
| 9 | [Neural Networks](https://scholar4ai.com/journals/neural-networks.md) | 7 |
| 10 | [Applied Intelligence](https://scholar4ai.com/journals/applied-intelligence.md) | 5 |

*Institutions with the most papers, since 2023*

| # | Institution | Papers |
|---:|---|---:|
| 1 | [Chinese Academy of Sciences](https://scholar4ai.com/institutions/chinese-academy-of-sciences.md) | 17 |
| 2 | Shanghai Artificial Intelligence Laboratory | 12 |
| 3 | [Peking University](https://scholar4ai.com/institutions/peking-university.md) | 11 |
| 4 | [University of Chinese Academy of Sciences](https://scholar4ai.com/institutions/university-of-chinese-academy-of-sciences.md) | 11 |
| 5 | [University of Science and Technology of China](https://scholar4ai.com/institutions/university-of-science-and-technology-of-china.md) | 11 |
| 6 | [Nanjing University](https://scholar4ai.com/institutions/nanjing-university.md) | 10 |
| 7 | [Zhejiang University](https://scholar4ai.com/institutions/zhejiang-university.md) | 10 |
| 8 | [Nanyang Technological University](https://scholar4ai.com/institutions/nanyang-technological-university.md) | 9 |
| 9 | [Tsinghua University](https://scholar4ai.com/institutions/tsinghua-university.md) | 9 |
| 10 | [Institute of Automation](https://scholar4ai.com/institutions/institute-of-automation.md) | 8 |

*Countries with the most papers, since 2023*

| # | Country | Papers |
|---:|---|---:|
| 1 | China | 129 |
| 2 | United States | 32 |
| 3 | United Kingdom | 28 |
| 4 | Australia | 26 |
| 5 | Singapore | 20 |
| 6 | Hong Kong | 16 |
| 7 | India | 10 |
| 8 | France | 8 |
| 9 | Italy | 7 |
| 10 | South Korea | 6 |

*Keywords with the most papers, since 2023*

| # | Keyword | Papers |
|---:|---|---:|
| 1 | human action recognition | 21 |
| 2 | [vision-language models](https://scholar4ai.com/keywords/vision-language-models.md) | 21 |
| 3 | CLIP | 18 |
| 4 | video action recognition | 17 |
| 5 | UCF101 | 13 |
| 6 | [multimodal fusion](https://scholar4ai.com/keywords/multimodal-fusion.md) | 13 |
| 7 | HMDB51 | 11 |
| 8 | video classification | 10 |
| 9 | [attention mechanism](https://scholar4ai.com/keywords/attention-mechanism.md) | 9 |
| 10 | [domain generalization](https://scholar4ai.com/keywords/domain-generalization.md) | 9 |

## Most-cited papers

*Most-cited papers since 2017*

| # | Citations | Per month | Title | Journal | Published | Authors |
|---:|---:|---:|---|---|---|---|
| 1 | 998 | 30.9 | [Vision-Language Models for Vision Tasks: A Survey](https://doi.org/10.1109/tpami.2024.3369699) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2024-02-26 | Jingyi Zhang, Jiaxing Huang, Sheng Jin et al. |
| 2 | 929 | 8.2 | [Long-Term Temporal Convolutions for Action Recognition](https://doi.org/10.1109/tpami.2017.2712608) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2017-06-06 | Gül Varol, Ivan Laptev A, Cordelia Schmid |
| 3 | 924 | 9.4 | [Temporal Segment Networks for Action Recognition in Videos](https://doi.org/10.1109/tpami.2018.2868668) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2018-09-03 | Limin Wang, Yuanjun Xiong, Zhe Wang et al. |
| 4 | 628 | 15.3 | [UniFormer: Unifying Convolution and Self-Attention for Visual Recognition](https://doi.org/10.1109/tpami.2023.3282631) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2023-06-05 | Kunchang Li, Yali Wang, Junhao Zhang et al. |
| 5 | 579 | 20.2 | [A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends](https://doi.org/10.1109/tpami.2024.3415112) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2024-06-17 | Jie Gui, Tuo Chen, Jing Zhang et al. |

## Used together with

Papers use Action recognition (Kinetics, UCF101, HMDB51) most often with ImageNet (90), YouTube / TikTok (50) and MS COCO (34); it has 31 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

*What papers use Action recognition (Kinetics, UCF101, HMDB51) together with (at least 3 papers; lift 1 = chance)*

| Used with | Type | Papers using both | Lift |
|---|---|---:|---:|
| [ImageNet](https://scholar4ai.com/datasets/imagenet.md) | Dataset | 90 | 6.3 |
| [YouTube / TikTok](https://scholar4ai.com/datasets/youtube-tiktok.md) | Dataset | 50 | 4.5 |
| [MS COCO](https://scholar4ai.com/datasets/ms-coco.md) | Dataset | 34 | 6.0 |
| [Caltech-101 / 256](https://scholar4ai.com/datasets/caltech-101-256.md) | Dataset | 24 | 26.8 |
| [CIFAR-10 / CIFAR-100](https://scholar4ai.com/datasets/cifar-10-cifar-100.md) | Dataset | 18 | 2.1 |
| [Fine-grained benchmarks (CUB-200, Stanford Cars, Oxford Flowers)](https://scholar4ai.com/datasets/fine-grained-benchmarks-cub-200-stanford-cars-oxford-flowers.md) | Dataset | 17 | 12.2 |
| [Skeleton and pose (NTU RGB+D, Human3.6M)](https://scholar4ai.com/datasets/skeleton-and-pose-ntu-rgb-d-human3-6m.md) | Dataset | 17 | 17.5 |
| [AudioSet / ESC-50](https://scholar4ai.com/datasets/audioset-esc-50.md) | Dataset | 11 | 37.0 |
| [MNIST / Fashion-MNIST](https://scholar4ai.com/datasets/mnist-fashion-mnist.md) | Dataset | 11 | 1.6 |
| [PASCAL VOC](https://scholar4ai.com/datasets/pascal-voc.md) | Dataset | 11 | 5.5 |
| [Cityscapes](https://scholar4ai.com/datasets/cityscapes.md) | Dataset | 9 | 5.0 |
| [Facebook](https://scholar4ai.com/datasets/facebook.md) | Dataset | 8 | 0.4 |

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

## Papers

*Papers mentioning Action recognition (Kinetics, UCF101, HMDB51) in the last 30 days, newest first.*

| Date | Title | Journal | Authors | Affiliations |
|---|---|---|---|---|
| 2026-10-26 | [TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation](https://doi.org/10.1007/s11263-026-03081-x) | [International Journal of Computer Vision](https://scholar4ai.com/journals/international-journal-of-computer-vision.md) | Haokun Lin, Teng Wang, Yixiao Ge et al. | City University of Hong Kong; Chinese Academy of Sciences; Tencent (China); … |
| 2026-10-24 | [Single-stage Temporal Action Detection with Coarse-to-Fine Auxiliary Supervision and asymmetric boundary prior](https://doi.org/10.1016/j.patcog.2026.115180) | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | Xianhua Zeng, SiQi Zhou, XinYu Liu | Chongqing University of Posts and Telecommunications |
| 2026-10-23 | [EMM-CVT: An Efficient Multi-Modal Vision Transformer for compressed video action recognition](https://doi.org/10.1016/j.patcog.2026.115181) | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | Hong Wen, Bing Li, Liang Qian et al. | Beijing Jiaotong University; Nankai University |

## Cite this page

Scholar4AI. (2026). Action recognition (Kinetics, UCF101, HMDB51). Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/action-recognition-kinetics-ucf101-hmdb51

```bibtex
@misc{scholar4ai-datasets-action-recognition-kinetics-ucf101-hmdb51,
  author = {{Scholar4AI}},
  title = {Action recognition (Kinetics, UCF101, HMDB51)},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/action-recognition-kinetics-ucf101-hmdb51}},
  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/).