The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Objects365: A Large-Scale, High-Quality Dataset for Object Detection
Abstract
In this paper, we introduce a new large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation. The Objects365 pre-trained models significantly outperform ImageNet pre-trained models with 5.6 points gain (42 vs 36.4) based on the standard setting of 90K iterations on COCO benchmark. Even compared with much long training time like 540K iterations, our Objects365 pretrained model with 90K iterations still have 2.7 points gain (42 vs 39.3). Meanwhile, the finetuning time can be greatly reduced (up to 10 times) when reaching the same accuracy. Better generalization ability of Object365 has also been verified on CityPersons, VOC segmentation, and ADE tasks. The dataset as well as the pretrained-models have been released at www.objects365.org.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Existing large DETR models [3, 6, 32, 41, 44, 46] have demonstrated impressive performance on COCO test-dev [20] leaderboard.”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [32]
In the citing paper
“In contrast, DINO achieves the SOTA result with a publicly available SwinL [23] backbone and a public dataset Objects365 [33] (1.7M annotated images) only.”
From DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (2022) · cites this paper as [33]
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
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
Research works printed but not linked: 3
- girshick, 2018, Detectron
- he, 2018, Rethinking im-agenet pre-training, arXiv preprint arXiv 1811 08883
- everingham, 0, The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results
Cited by
Sorted by citations
Items 601–677 of 677
MambaOVD: a Mamba-based open-vocabulary object detection method
Liu, K., Ma, L., & Lu, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-18769-2
A Novel Grasping Robot Control Method Using Motion Execution BCI Combining Knowledge Reasoning
Li, R., Liu, J., Liu, J., Yang, S., Liu, W., Deng, K., & Wang, W. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3622255
“Theobject365datasetcovering365 differentcategoriesofobjectforobjectdetectionrecognition tasks, which contains most of objects which commonly used in the ward [32].”
Plug-and-Play One-Shot Object Detection Framework for Industrial Applications
Yahya, M., Civitelli, E., Longo, N., & Rizzo, A. (2025) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa65518.2025.11205589
“Two label space strategies were explored: (1) a fixed, human-curated label space derived from a combination of labels from the LVIS [8], Objects365 [23], OpenImagesV4 [12], and Visual Genome [11] datasets, resulting in 2520 categories, and (2) machine-generated per-image queries, where N-grams of…”
Learning Based Versatile Voice Eavesdropping Prevention for Mobile Devices
Huang, W., Ren, J., Cao, H., Jiang, H., Yang, P., & Fu, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3624756
“Auxiliary Dataset: In order to further substantiate the superiority of the L-YOLO model, we conducted experiments on two authoritative large-scale datasets, CIFAR-10 [44] and COCO [45]. for object recognition.”
Learning Object Affordance Ranking with Task Context
Huang, H., Luo, H., Zhai, W., Cao, Y. H., & Zha, Z.-J. (2025) · doi:10.1145/3728485.3759173
An Effective Interval Normalization Weighting Method for Accurate Object Detection
Wu, S., Tian, C., Liu, R., Wei, H., & Xu, Y. D. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2025.3624473
“Comprehensive analyses are performed to evaluate the effectiveness of the INWS on the MS-COCO [18], PASCAL VOC [47], and Object365 [48] benchmarks, which are the most prevalent datasets for object detection.”
DBaP-net: Deep network for image defogging based on physical properties prior
Yu, B., Wei, H., Zhang, C., & Wang, W. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105803
Joint learning video segmentation with different prior guidance
Yang, D., Ma, C., Deng, X., Zeng, J., Zhang, J., Huang, W., Jiang, Z., & Huo, Y. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103622
Utilization of similar detection dataset based on dual classification head
Teng, S., Han, X., & Zhang, F. (2025) · Franklin Open · doi:10.1016/j.fraope.2025.100377
LOVD: Open-Vocabulary Object Detection Based on LLM-Enhanced Agents
Li, X., & Xu, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227349
“Traditional object detection works mainly focus on fixed vocabulary (closed set) detection, where object detector is trained on datasets with predefined categories, such as COCO dataset [3] and Objects365 dataset [9], and then object detector is used to detect objects within the fixed category set.”
ROOT: Region-Word Alignment With Partial Optimal Transport for Open-Vocabulary Object Detection
Deng, J., Lei, Y., Li, W., & Duan, L. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3627395
“…Setting: To evaluate the generalization capability of open-vocabulary detectors, we follow prior studies [13], [17] and transfer a model trained on the OV-LVIS setting ( i.e. , LVIS [10] base categories and Conceptual Cap-tions 3M [57]) to two unseen datasets: COCO and Objects365 [59].”
Open-vocabulary object detection via prompt learning and dual-branch classification
Xiao, Y., Yuan, S., & Zhao, D. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02112-w
“In our experiments, we used the MS COCO [28 ] data-set and the LVIS [29] dataset, as well as the Objects365 [30] dataset.”
Unified Granularity Controller for Interactive Segmentation
Zhao, Y., Li, K., Qiao, P., Liu, C., Ji, R., & Chen, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3642834
“Thesemethodslearnmultiplepossi-bilities[61]ofsparsepromptstodensemasksmappingfrom large-scalemulti-grainedannotations[18],[21],[22],[62],[63], whichrequiresexpensivedataandtrainingcosts.”
Energy-Based Confidence Gap Expansion YoLOOD for Multi-Label OOD Detection
Li, M., Tsang, E. C. C., Xu, W., & He, Q. (2025) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc66258.2025.11280122
“(3) Object365 in [16]: This dataset is a subset of the Object365 dataset[16] containing 20 common categories, divided into 68723 training images, 5000 validation images and 10000 test images.”
An incremental out-of-distribution learning framework for robust open-world object detection
Iqbal, M. A., Gil, J.-M., & Kim, S. K. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110904
Foundation Model-Based Auxiliary Framework for Object Detection in Aerial Remote Sensing Images
Lu, W., Niu, C., Liu, W., Lan, C., & Wang, S. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3649185
EVCS: A Benchmark for Fine-Grained Electric Vehicle Charging Station Detection
Chen, L., Sudbeck, S., Riggers, C., Geib, T., Cordes, K., & Broszio, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-12840-9_6
Wu, C., He, W., Cheng, C.-H., Huang, X., & Bensalem, S. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3650695
Automated Attention Guidance in Virtual Reality Videos
Silva, P. V., Neves, L. L., Goiás, R. A., Silva, D. F. C., Sousa, R. T., & Filho, A. R. G. (2025) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr67689.2025.00017
“…pre-training strategy is based on three primary data types: (i) detection data, containing labeled categories from datasets such as COCO [28], O365 [29], and OpenImage [29]; (ii) grounding data, which includes image-text region pairs from datasets like GoldG, RefCOCO, and Visual Genome,…”
Enhanced Visual Prompt for Open-Set Interactive Detection
Lu, Y., Song, H., Chen, D., Lu, Z., & Wang, Y. (2025) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai68704.2025.11345862
“The training dataset includes COCO2017 [20], Objects365v2 [21], V3Det [22], LVIS [23], OIDv6 [24], and a 10% sampled UMG [25], containing approximately 3.8M images and over 20,000 classes, as shown in Table II.”
HazSense: A Multimodal RGB-D Dataset for Real-World Hazard Detection
Brahma, S., & Sayed, K. (2025) · IEEE International Conference on Intelligent Reality (ICIR) · doi:10.1109/icir68135.2025.11361555
MLLM-Based Evaluation and Enhancement of Open-Set Object Detection Dataset Annotations
Gao, X., Nong, Q., Dong, X., & Gao, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5722-6_35
SWiM3 : Solid Waste Mapping Dataset
Ahmed, M. B., Razzaq, J., & Razeen, S. (2025) · International Conference on Digital Futures and Transformative Technologies (ICoDT2) · doi:10.1109/icodt269104.2025.11360732
Park, J., & Sim, J.-Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3659334
“The output features of CoME blocks are fused with the hierarchical features from a Swin-L [42] pre-trained on the Object365 dataset [54], and then progress through the decoder blocks with complementary cross-attention (CoCA), where both high and low cross-correlations are complementarily utilized…”
MR-GDINO: Memory and Retrieval for Efficient Open-World Continual Object DetectionPreprint
Dong, B., Huang, Z., Yang, G., Lei Zhang, A., & Zuo, W. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6248124
Neau, M., Falomir, Z., Buche, C., & Sugimoto, A. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00789
“In contrast to other tasks, such as Object Detection [7, 23], the task of SGG has not yet seen the emergence of large-scale, high-quality datasets with a large vocabulary.”
HierVision: Standardized and Reproducible Hierarchical Sources for Vision Datasets
Kasarla, T., Rooparaghunath, R. H., D’Arrigo, S., Mago, G., Jha, A., Ayoughi, M., Mishra, S. S., Rodriguez, A. M., Long, T., Atigh, M. G., et al. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00076
“Biological taxonomies tend to be deep and balanced, with low branching factors (1–3), while semantic hierarchies such as ADE20K [133] and Objects-365 [104] are broad and flat, with extremely high branching at the root.”
Deployment Prior Injection for Run-Time Re-Biasable Object Detection
Zhou, M., Yang, Y., Li, H., Patel, V. M., & Hua, G. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3667914
Det-Agent: Open-Vocabulary Object Localization and Detection With Reinforcement Learning Agent
Zhang, R., Wu, X.-J., Wang, C., & Liu, C.-L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668516 · Cited by 1
“To assess the generalization ability of open-vocabulary object detectors, we follow the protocol of ViLD [8] and perform cross-dataset testing, where all models are trained exclusively on the LVIS [20] training set and evaluated on the COCO [19] and Objects365 [27] validation sets.”
The MiniMarket80 Dataset for Evaluation of Unique Item Segmentation in Point Clouds
Sorour, M., Rattray, E., Syahrulfath, A. S., Jaramillo, J., Lin, S., & Webb, B. H. (2026) · AI · doi:10.3390/ai7030096
CamoVid60K: A Large-Scale Video Dataset for Moving Camouflaged Animals Understanding
Vu, T.-A., Zheng, Z., Song, C., Guo, Q., Tsang, I. W.-H., & Yeung, S.-K. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02765-8
A Novel Evaluation Metric for Object Detection in Traffic Scenarios
Huang, L., Cai, X., Feng, S., Li, H., Masood, V., Ying, S., Zhou, B., Jia, W., Liu, H., Zhang, L., et al. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3673625
“As the de facto standard in object detection tasks and benchmarks [1], [2], [3], [4], [5], [6], average precision (AP) measures detection performance by integrating precision and recall, and has been widely adopted in benchmark datasets such as PASCAL VOC [7] and COCO.”
Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
Kang, M., Lee, M., Kim, M., Lee, J., Kim, D., Woo, S., Jeon, I., & Lee, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37132-4_20
Learning 3D Representation From Auto-Labeled 2D Object Boxes
Deng, Q., Hui, L., Yang, J. J., & Xie, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3671587
“The pre-trained YoLo-World is trained with Objects365 [87], GQA [88], Flickr30k [89], and CC3M [90] datasets.”
Zhang, Z., Zhang, J., Chen, Q., Li, G., Chen, D., Jing, S., Wang, H., Li, D., Liu, C., Bai, C., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3680569 · Cited by 1
“We compare YOLO-World [22] and GroundingDino’s [10] pre-trained versions on Object365 [73], CC3M and GoldG.”
AdViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization
Lu, J., Li, J., Gao, Y., Wu, J., Wu, J., Wang, X., & He, X. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02840-0 · Cited by 8
“Inspired by larger backbones (Carion et al., 2020; Zhang et al., 2023a) and extensive datasets (Shao et al., 2019), Grounding DINO (Liu et al., 2024d) (cid:7) Ground DINO advances open-set detection by integrating detection with grounding.”
Self-citationZhang, S., Zang, Q., Hu, Y. '., Du, J., Wang, X., Kong, Y., Fu, X., Nanayakkara, S. C., Yi, X., & Li, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790288 · Cited by 3
“This precluded the need for larger datasets like Object365 [105] or specialized ones such as PA-HMDB51 [123].”
Latent Diffusion‐GAN: Adversarial Learning in the Autoencoded Latent Space
Jun, U.-C., Ko, J., & Kang, J. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70409
Jiang, X., Chen, J., Li, Y., Pan, Y., Chen, K., Li, Z., Yao, T., & Mei, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463851
Self-citationPang, Y. L., & Oh, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460591
VLAD-Grasp: Vision-Language Adaptive Depth Grasping for Part-Specific Manipulation
Liu, M., Zou, Y., Wang, H. E., Qiu, S., & Lei, F. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3686670
“According to previous studies [4], [36], Precision@0.5, Precision@0.75, and Precision@0.9 are used as the evaluation metrics, where a prediction is considered correct when the Intersection over Union (IoU) between the predicted and ground-truth bounding boxes exceeds the corresponding threshold.”
InfluentialTraining-Free Few-Shot Segmentation via Vision-Language Guided Prompting
Yoon, E., Park, T., & Lee, J. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00630
“For open-vocabulary detection component in our proposed approach, we use OWL-ViT [21] (ViT-L/14) pretrained on the Objects365 [30] and WebLI [7].”
Fast Digitization in XR of Reality-Linked Gaussian-Splatted Proxies
Yang, B., Liu, S., Natarajan, K., & Feiner, S. (2026) · IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · doi:10.1109/vrw70859.2026.00389
“Object detection runs on-device using YOLO11 trained on the Objects365 dataset [12] via the Unity Sentis inference engine, overlaying bounding boxes on detected objects.”
Promptable image segmentation: a survey of guided input techniques
Nejabat, H., D’Asaro, F., Pecora, A. E., Monopoli, T., & Bottino, A. (2026) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1108/ftcgv-03-2026-001
Relational collaboration of multimodal triplet prompts for open-ended object detection
Zhu, C., & Chen, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116326
Wang, C., He, Q., Pei, J., Xia, L., Liu, J., Li, B., & Di, X. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104828
Paying More Attention to Visual Tokens in Self-evolving Large Multimodal Models
Venkatraman, S., Thawkar, R., Thawakar, O., Anwer, R. M., Cholakkal, H., Khan, S., & Khan, F. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_3
Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction
Hou, X., Liu, M., Du, S., & Fan, Z. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3708265
“We visualize the statistical distribution of MC for datasets across various scenarios, including industrial (ESD [43], CSD [18], MSSD [19]), domestic (AI2thor [44]), urban (Cityscapes [16]) and generic settings (PascalVOC [45], COCO [2], Object365 [46], SA-1B [47]).”
Enhancing scene graph generation via semantic-aligned masked vision-and-language pre-training
Chang, X., Wang, T., Xu, L., & Sun, C. (2026) · The Visual Computer · doi:10.1007/s00371-026-04590-z
“2 O v S G T R [ 8 ] D ET R [ 3 ] O 365v1 [ 44 ] , G o l d G [ 28 ] C a p4 M [ 28 ] N / A N / A The model is pre-trained and then fine-tuned on the VG dataset, except for the first row where the model is trained directly on VG is chosen based on the convergence of the mR metric on the VG validation…”
Cao, Y., Gao, J., Yan, Y., & Wang, H. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3708773
DAPA: Distribution-aware physical attacks against aerial open-vocabulary object detection
Jia, R., Meng, F., Yue, P., He, R., & Sun, W. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114371
Tang, X., & Liu, W. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116599
People Counting Using YOLO-Based Detection and Clustering for a Mobile Robot
Gomulka, K., Woźniak, P., & Krzeszowski, T. (2026) · Sensors · doi:10.3390/s26154664
“Examples of popular datasets include COCO [22] and Object365 [23], which provide diverse real-world images with varying lighting and object scales to ensure the robustness of model training.”
Efficient Post-hoc Calibration in Object Detection Without Held-Out Data
Ebert, N., Stricker, D., & Wasenmüller, O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31335-5_20
OpenAqua: A Large-Scale Fine-Grained Dataset and Benchmark for Open Underwater Visual Perception
Luo, L., Mu, P., & Bai, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817535
“Specifically, we evaluate the zero-shot inference performance of models pre-trained on large-scale general datasets [10, 23, 45, 50] across all taxonomic levels of the Mini-test set.”
TruthLens: Object Hallucination Detection via Self-evaluating Truthfulness Scores in LVLMs
Wu, Y., Lai, R., Lu, X., Chen, Q., Zhou, Z., Zhuang, J., Yu, W., & Wang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_30
Person–Object Relationship Consistency Learning For Zero–Shot Spatio–Temporal Action Detection
Babazaki, Y., Shibata, T., & Takahashi, T. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630221
Wang, D., & Minet, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7305808
Incremental Vision–Language Object Detection via Sparse Frequency Transform
Song, X. R., Yang, Z., He, Y., Dong, S., Wang, Q., & Gong, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3723720
“The model is pretrained on the O365 [54], GoldG [55], CC3M [56], and SBU [57] datasets.”
Bilakeri, S., Manisha, & Akshatha, K. R. (2026) · The Visual Computer · doi:10.1007/s00371-026-04700-x
Unlocking the potential of open-vocabulary detectors for visual-prompted object detection
Li, Y., Deng, Y., Suo, W., Wang, J., & Wang, P. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114824
MonoSOWA++: Universal Autolabeling Pipeline for Monocular 3D Object Detection
Skvrna, J., & Neumann, L. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03007-7
Computationally efficient hash based single image dehazing leveraging depth anything
Bhatia, J. K., Agrawal, S. C., & Jalal, A. S. (2026) · The Imaging Science Journal · doi:10.1080/13682199.2026.2726540
Zhang, Y., Peng, D., Guo, Z., Zhang, Z., Yang, X., Sun, T., Sun, S., Zhang, Y., Li, Y., Zhao, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_22 · Cited by 4
Jiang, Y., Xie, Z., Liu, W., Huang, L., Yang, F., & Liu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37196-6_10
Towards Robust Underwater Object Detection: UWOD Dataset and Transfer Learning Insights
Alrowais, N. A., AlAwajy, A. M., Almugren, N., Aljami, H. M., Alobaid, A. O., Alghamdi, M., Alsumari, W., Alqaeri, H. R., Almutairi, A., Alsaeed, R., et al. (2026) · Data · doi:10.3390/data11090236
Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything
Li, J., Gao, B.-B., Fu, W., Luo, J., Deng, H., Guo, Y., Liu, J., Liu, Y., Wang, C., & Tao, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_32
Self-citationExplicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection
Su, P., Ren, W., Han, S., Dong, Q., Xu, H., Ai, X., Wang, Z., Wang, Z., & Liu, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37281-9_35
: Open Reinforcement Learning Recipes for Visual Reasoning
Sarch, G. H., Cai, L., Wang, Q., Wu, H., Chen, D., & Liu, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36969-7_32
Using Multimodal Large Language Models for False Alarm Reduction in Image-Based Fire Detection
Gao, Q., Wang, H., Qin, Z., Fan, L., Li, K., Wang, C., & Zhang, Q. (2026) · Fire Technology · doi:10.1007/s10694-026-02000-3
“3b) were selected from the Object365 dataset [32], primarily depicting indoor scenes such as bedrooms, dining rooms, and shopping malls.”
Jia, R., Meng, F., Yue, P., He, R., & Sun, W. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3736941
“Traditional object detection is commonly formulated as a closed-set recognition problem, where training and evaluation share a predefined category vocabulary, such as those in COCO [22] and Objects365 [23].”
Ren, M., Pan, Y., Zhou, B., Feng, Z., & Zhang, X. (2026) · Remote Sensing · doi:10.3390/rs18193420
Self-citationSubstrate-Driven Localization Gaps in Pipe Crack Detection
Biasbas, M. K., Flores, F. M., Gatchalian, C. C., Velasco, L. A., Yadao, D. M., Pangaliman, M. M. S., & Bautista, A. J. (2026) · International Conference on Robotics and Automation Sciences (ICRAS) · doi:10.1109/icras70064.2026.11717991
“Models pre-trained on large datasets like COCO [12] and Objects365 [13] learn features that transfer to new tasks.”
ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection
Zhang, Y., Han, R., Zhou, F., Feng, W., & Wan, L. (2026) · doi:10.1109/cvprf71909.2026.00638
“1) General-category detection : Cli-part [17], Watercolor [17], Comic [17], and MSOSB [75], with artistic styles; MS COCO [34], Objects365 [47], ODinW [30] and LVIS [13] consisting of common images with LVIS offering a more extensive set of categories often used for OV tasks.”
Advancing Open-Set Detection and Segmentation via Disentangled Representations
Zhang, H., Guan, Y., Cheng, R., & Yang, Y. (2026) · doi:10.1109/cvprf71909.2026.00636
“These include COCO [19], LVIS [8], Object365 [25], OID [15] and V3Det [29].”
A Survey on the Challenges of Semi-Supervised Object Detection
da Silva, L. T., & Batista, G. (2026) · IEEE Access · doi:10.1109/access.2026.3743924
“In addition to the previously discussed datasets, some SSOD methods also use the Objects365 [101] dataset, which includes 638K annotated training images with bounding-box labels for 365 object categories.”
Huang, X., Zhao, J., Liu, X., Xu, J., Zhang, Z., Luo, Z., & Chen, X. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729404
Metadata
- Authors
- Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., & Sun, J.
- Affiliations
- Megvii (China) (CN)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 8429-8438
- OpenAlex
- W2983943451
- Cited by
- 673
- References
- 42
- Citations by year
- 2026: 70 · 2025: 155 · 2024: 180 · 2023: 132 · 2022: 67 · 2021: 50 · 2020: 17 · 2019: 2
- FWCI
- 11.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- bounding box annotation, annotation pipeline, pre-trained models, representation learning, semantic segmentation, benchmark, COCO benchmark, CityPersons, ADE20K
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
