Open Images

data category: Object detection and segmentation benchmarks · 0 papers in the last 7 days

← Most-used data · All Object detection and segmentation benchmarks datasets

Images labelled with object boxes or pixel masks, including driving scenes.

Names searched for: Open Images dataset, OpenImages, Open Images V4, Open Images V6

Key findings#

From Nov 2023 to Oct 2026, 45 archived papers mentioned Open Images in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Aug 2024 (5).
No paper of the tracked journals mentioned Open Images in the last 30 days (2026-10-06 to 2026-11-04).
From 2017 to 2026 (so far), Open Images was mentioned in 50 papers in the tracked journals, most of them in AI (50).
12 of them were published in 2025, against 0 in 2017.
Since 2023, the institutions with the most of these papers were Chinese Academy of Sciences (6), Nanyang Technological University (5) and Institute of Automation (4).
The journals publishing most of them were IEEE Transactions on Pattern Analysis and Machine Intelligence (21), International Journal of Computer Vision (12) and Pattern Recognition (3).
The most-cited of them is “The Open Images Dataset V4” (International Journal of Computer Vision, 2020), with 368 citations.
Papers use Open Images most often with MS COCO (30), ImageNet (29) and PASCAL VOC (12); it has 15 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
	22	9	14	45

Papers per year#

20172026 (so far)

Papers per publication year and category
Category	2017	2018	2019	2020	2021	2022	2023	2024	2025	2026 (so far)
AI	0	0	0	1	0	0	8	20	12	9
All categories	0	0	0	1	0	0	8	20	12	9

Where the papers come from#

Journals with the most papers, since 2023
#	Journal	Papers
1	IEEE Transactions on Pattern Analysis and Machine Intelligence	21
2	International Journal of Computer Vision	12
3	Pattern Recognition	3
4	Artificial Intelligence Review	3
5	IEEE Transactions on Neural Networks and Learning Systems	2
6	Journal Of Big Data	2
7	Machine Learning	1
8	Neural Computing and Applications	1
9	AI & Society	1
10	Information Fusion	1

Institutions with the most papers, since 2023
#	Institution	Papers
1	Chinese Academy of Sciences	6
2	Nanyang Technological University	5
3	Institute of Automation	4
4	Amazon (United States)	3
5	Leibniz University Hannover	3
6	National University of Defense Technology	3
7	Australian National University	2
8	ByteDance (China)	2
9	Chinese University of Hong Kong	2
10	Chinese University of Hong Kong, Shenzhen	2

Countries with the most papers, since 2023
#	Country	Papers
1	China	21
2	United States	9
3	United Kingdom	7
4	Hong Kong	6
5	Australia	5
6	Germany	5
7	Singapore	5
8	Canada	3
9	Spain	3
10	Finland	2

Keywords with the most papers, since 2023
#	Keyword	Papers
1	scene graph generation	8
2	image classification	5
3	Visual Genome	4
4	object detection	4
5	out-of-distribution detection	4
6	benchmark dataset	3
7	data augmentation	3
8	evaluation metrics	3
9	instance segmentation	3
10	visual grounding	3

Most-cited papers#

Most-cited papers since 2017
#	Citations	Per month	Title	Journal	Published	Authors
1	368	4.6	The Open Images Dataset V4	International Journal of Computer Vision	2020-03-13	Alina Kuznetsova, Hassan Rom, Neil Alldrin et al.
2	244	5.7	RelTR: Relation Transformer for Scene Graph Generation	IEEE Transactions on Pattern Analysis and Machine Intelligence	2023-04-19	Yuren Cong, Michael Ying Yang, Bodo Rosenhahn B
3	168	7.1	BiFPN-YOLO: One-stage object detection integrating Bi-Directional Feature Pyramid Networks	Pattern Recognition	2024-11-18	John Doherty, Bryan Gardiner, Emmett Kerr et al.
4	114	4.3	Contextual Object Detection with Multimodal Large Language Models	International Journal of Computer Vision	2024-08-20	Yuhang Zang, Wei Li, Jun Han et al.
5	105	4.5	LVLM-EHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models	IEEE Transactions on Pattern Analysis and Machine Intelligence	2024-11-27	Peng Xu, Wenqi Shao, Kaipeng Zhang et al.

Archive counts by publication year: a paper counts when its title, abstract or keywords name the dataset, or when OpenAlex's full-text search finds it there (searched for the last 30 days' papers and, by a pass over the past years, for older ones). Names added to the list later are looked for in older papers as the archive is read again.

Used together with#

Papers use Open Images most often with MS COCO (30), ImageNet (29) and PASCAL VOC (12); it has 15 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST. The whole network →

What papers use Open Images together with (at least 3 papers; lift 1 = chance)
Used with	Type	Papers using both	Lift
MS COCO	Dataset	30	30.9
ImageNet	Dataset	29	11.8
PASCAL VOC	Dataset	12	34.5
CIFAR-10 / CIFAR-100	Dataset	10	6.9
YouTube / TikTok	Dataset	8	4.2
Fine-grained benchmarks (CUB-200, Stanford Cars, Oxford Flowers)	Dataset	7	29.2
ADE20K	Dataset	5	33.9
Cityscapes	Dataset	5	16.1
Wikipedia	Dataset	5	4.7
KITTI	Dataset	4	8.4
nuScenes / Waymo Open / Argoverse	Dataset	4	12.9
SVHN	Dataset	4	18.3

Cite this page

Scholar4AI. (2026). Open Images. Journal and Conference Research Rankings. Retrieved November 4, 2026, from https://scholar4ai.com/datasets/open-images

@misc{scholar4ai-datasets-open-images,
  author = {{Scholar4AI}},
  title = {Open Images},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/open-images}},
  urldate = {2026-11-04},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}

Free to reuse for non-commercial purposes with attribution (CC BY-NC 4.0).