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
Flagged first, then by citations
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 501–600 of 677
An Analysis of OpenSeeD for Video Semantic Labeling
Zhu, J. (2025) · Journal of Computer and Communications · doi:10.4236/jcc.2025.131005 · Cited by 1
Toward Realistic Hierarchical Object Detection: Problem, Benchmark, and Solution
Feng, J., Yang, Y., Lyu, M., Hao, T., Huang, Y.-J., Xie, Y., Li, Y., Han, J., Xiang, L., & Ding, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3552596 · Cited by 1
“To construct a benchmark for hierarchical object detection, we use three existing general object detection datasets: MS COCO [2], Open Images [33], and Objects365 [34] as data sources.”
Fdil, M., Levasseur, M., Létourneau, D., Maheux, M.-A., Lussier‐Therrien, M., & Michaud, F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-3519-1_17 · Cited by 1
A Concise Dataset for Intelligent Behaviors in Domestic Tasks
Vaz, M. D. O., Rohrich, R. F., Fabro, J. A., & de Oliveira, A. S. (2025) · IEEE Access · doi:10.1109/access.2025.3554607 · Cited by 1
“The performance of object detection models using the ODUTF dataset was evaluated through a comparison with established benchmarks: COCO, Object365, and Pascal VOC [30].”
RT-DEKT: real-time object detector with KAN-Transformer
Jin, Z., Li, C., & Lei, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04016-8 · Cited by 2
“After pretraining on the larger dataset like Objects365 [22], RT-DEKT-R101 further enhances to 58.5% AP, outperforming both RT-DETR and the YOLO series.”
InfluentialA prompt-free vision-language model for environmental perception in automated driving systems
Lin, C., Ying, S., Hu, Q. X., & Zhang, L. (2025) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070251327247 · Cited by 1
ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising
Chaubey, A., Agarwaal, A., Roy, S. S., Agrawal, A., & Ghose, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00589 · Cited by 1
“We use the YOLOv5 model [61], trained on the Ob-jects365 dataset [53], to detect objects within videos with an IOU threshold of 0.45 and a confidence threshold of 0.35.”
InfluentialMenjívar, P. J., Pino, A. F. S., Manzano, J. E. M., & Cabrera, E. V. R. (2025) · Microorganisms · doi:10.3390/microorganisms13040860 · Cited by 1
“The batch size of 4 images per iteration was chosen considering computational memory constraints in an environment such as Google Colab and the need for efficient gradient updates.”
Object Detection Algorithms for Digital Imaging Applications: A Review
Bello, R.-W., Owolawi, P. A., Wyk, E. V., & Tu, C. (2025) · IntechOpen eBooks · doi:10.5772/intechopen.1010205 · Cited by 1
Spatio SLAM: An Integrated Strategy for Robot Autonomy in Variable Indoor Luminance
Chaudhuri, R., Deb, S., & Das, A. (2025) · IEEE Access · doi:10.1109/access.2025.3595572 · Cited by 1
“The experiment has been carried out primarily on the COCO [62] (Common Object in Context) and ExDark [63] datasets for validating the performance of the proposed technique, no other real-time dataset is created or being used for the experiment.”
GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model
Han, Y., Zhang, J., Zhu, J., Hou, R., Ji, X., Lin, C., Hu, X., Xue, Z., & Liu, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00373 · Cited by 1
“And their region annotations typically come from detection datasets like COCO [29], Ob-jects365 [45], and SAM [22], which often treat the face as a whole or include only a few categories such as eyes, hair, and ears.”
A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
Wen, X., Zhao, B., Chen, Y., Pang, J., & Qi, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01134 · Cited by 1
Fine-Grained Open-Vocabulary Object Detection via Attribute Decomposition and Aggregation
Dou, B., Wu, T., & Guo, Z. (2025) · AI · doi:10.3390/ai6090201 · Cited by 1
Toward Effective Knowledge Distillation: Navigating Beyond Small-Data Pitfall
Hao, Z., Guo, J., Han, K., Hu, H., Xu, C., & Wang, Y. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3607982 · Cited by 2
“To further enhance its performance, the teacher is pretrained on the Object365 [63] dataset and subsequently undergoes fine-tuning on COCO 2017 and its subsets.”
Fusion or Confusion? A Look at Dataset Pooling for Infrared Object Detection
Becker, S., Grosselfinger, A.-K., Bayer, J., Münch, D., Hübner, W., & Arens, M. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00428 · Cited by 1
“These datasets, such as ImageNet [29], Object365 [30], MS COCO [19], or OpenImages [16], are designed to capture a broad spectrum of objects and scenes without targeting specific applications or domains.”
OV-VOD: Open-Vocabulary Video Object Detection
Zheng, Z., Cao, Y., Gao, J., & Wang, H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755402 · Cited by 1
DQ3D: Depth-guided Query for Transformer-Based 3D Object Detection in Traffic Scenarios
Wang, Z., Li, W., & Wu, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227159 · Cited by 1
“ViT-Large [32] pre-trained by Objects365 [33] and COCO [34] dataset is used to scale up our model.”
Unsupervised Object Localization driven by self-supervised foundation models: A comprehensive review
Papadopoulos, S., Patsiouras, E., Ioannidis, K., Vrochidis, S., Kompatsiaris, I. Y., & Patras, I. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105807 · Cited by 1
Amp: single-shot ultra-wide fisheye-to-cubemap PnP pose estimation
Raettig, R. M., Nyquist, R. R., Nykl, S. L., Taylor, C. N., & Kabban, C. M. S. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01768-8 · Cited by 1
“For this search, the YOLO low-augmentation, YOLO high-augmentation, and Object365 [39] (a widely used computer vision dataset) default hyperparameters were first trained for 300 epochs and compared.”
OVGrasp: Open-Vocabulary Intent Detection for Grasping Assistance using ExoGlove
Hu, C., Luo, S., & Gionfrida, L. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104676 · Cited by 1
Wang, F., Li, W., & Zhou, T. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00543-7 · Cited by 1
“We follow the standard Open World Object Detection evaluation protocol and conduct experiments under both the superclass-mixed (M-OWODB) (Joseph et al. 2021) and the superclass-separated (S-OWODB) (Gupta et (2019).”
RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
Neuwirth-Trapp, M., Bieshaar, M., Paudel, D. P., & Goo, L. V. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00543 · Cited by 1
“We initialize the backbone with weights finetuned on Objects365 [76] and MS COCO [53], while randomly initializing the detection head.”
Yemelianenko, T., Tkachenko, I., Masclef, T., Scuturici, M., & Miguet, S. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21443-y · Cited by 1
T-Rex2++: Toward Generic Object Perception via Text-Visual Prompt Synergy
Jiang, Q., Li, F., Zeng, Z., Ren, T., Liu, S., & Zhang, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3672908 · Cited by 1
“Data for text prompt: Following [5], [6], we utilize detection datasets Objects365 [71], OpenImages [76], along with the grounding dataset GoldG [11] for training.”
InfluentialEnhancing Numerical Prediction of MLLMS With Soft Labeling
Wang, P., Cai, Z., Yang, H., Modolo, D., & Swaminathan, A. D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00327 · Cited by 2
“…baseline, we use LLaVA-13B, pretrained on a 16M data mixture including LAION-5M for image captioning, GRIT-5M [47] for grounding, Ob-jects365 [55] and OpenImages [27] of 3M in total for object counting, and 3M plot or chart related datasets such as PlotQA [43], UniChart [41], FigureQA [24]…”
Beyond Pixel Uncertainty: Bounding the OoD Objects in Road Scenes
Zhu, H., Liu, Z., Sun, Z., Zou, Y., Xia, G.-S., & Xu, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00793 · Cited by 1
“To mitigate this challenge, some approaches [4, 32] adopt a data-driven strategy by cropping objects from external datasets such as COCO [25] and Obj365 [35] to serve as anomaly proxies, fine-tuning model’s sensitivity in anomalous regions and ambiguous areas.”
Unified Open-World Segmentation with Multi-Modal Prompts
Liu, Y. H., Yin, Y., Jing, C., Zhu, M., Chen, H., Xi, Y., Feng, B., Wang, H., Li, S., & Shen, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02002 · Cited by 2
Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?
Mütze, A., Ilyas, S., Dörpelkus, C., & Rottmann, M. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00079 · Cited by 1
“• We apply our generic inpainting procedures to Lo-stAndFound and NuImages, testing a number of open-vocabulary object detectors on a variety of unusual image content with rich semantic diversity.”
ORCA: Object Recognition and Comprehension for Archiving Marine Species
Wong, Y. K., Liang, H., Ma, Z., Chen, Y. H., Zheng, Z., Gotama, R., Sebastian, P., Sparks, L., & Yeung, S.-K. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00161 · Cited by 1
“These models combine visual encoders [13] with large language models [45, 46], trained on massive image–text corpora.”
SDPT: Synchronous Dual Prompt Tuning for Visual-Language Pre-Trained Models
Zhou, Y., Wu, Y., Saiyin, J., Wei, B., & Xu, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3692711 · Cited by 1
“We transferred a GLIP-L pre-trained on Object365 [53] to MSCOCO [22] using several mainstream single-and dual-modal PT methods and LoRA as benchmarks.”
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
Zhou, Y., Zhao, S., Chen, Y., Wang, Z., Jin, C., Zhao, M., & Metaxas, D. N. (2026) · doi:10.1109/cvprf71909.2026.00923 · Cited by 1
“To maximize the quality of the adaptation prompts provided by LLMs, we employ In-ternVL ViT and its pre-trained weights as the vision encoder for models such as InternVL2-1B, 2B, and 8B.”
A Simple Approach and Benchmark for 21,000-Category Object Detection
Lin, Y., Li, C., Cao, Y., Zhang, Z., Wang, J., Wang, L., Liu, Z., & Hu, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20083-0_1 · Cited by 1
“The Objects365 [33] object detection dataset and the ImageNet-21K image classification datasets are used for training.”
BackgroundMethodInfluentialMixing Domains for Smartly Picking and Using Limited Datasets in Industrial Object Detection
Akar, C. A., Semaan, A., Haddad, Y., Kamradt, M., & Makhoul, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44137-0_23 · Cited by 1
A Dataset for Object Detection in Night Rainy Scenes
Zhang, H., Liu, T., Wu, Z., & Wang, D. (2023) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram55796.2023.10370963 · Cited by 1
“Recently, researchers propose higher quality dataset for object detection [10].”
BackgroundObject Knowledge Integration for Skeleton-Based Action Recognition
Moutik, O., Sekkat, H., Tchakoucht, T. A., kari, B. E., & Alaoui, A. E. H. (2024) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-1967 · Cited by 1
Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners
Yin, Y., Yin, P., Xiao, X., Liang, Y. C., Sun, S., & An, X. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100237 · Cited by 1
POPCat: Propagation of Particles for Complex Annotation Tasks
Yang, A. S., Khanna, D., & Zelek, J. (2024) · doi:10.21428/d82e957c.3da7f032 · Cited by 1
“Recall% mAP50% mAP% GlobalTrack [34]GMOT-40[1] - 15.65 - Z-GMOT GLIP[20] - 66.20 36.10 Z-GMOT iGLIP[20] - 66.90 40.00 Siamese-DETR (COCO[35])[36] 49.90 63.60 - Siamese-DETR (Objects365[37])[36] 55 [1], [2], [20], [36] [30], [31].”
InfluentialABC-Trans: a novel adaptive border-augmented cross-attention transformer for object detection
Zhang, Q., Wang, P., Wu, Z., Yang, B., & Yuan, J. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19405-3 · Cited by 1
“We conduct experiments on three object detection datasets including Pascal VOC [34, 35], MS-COCO [36] and Objects365 [37] to verify our proposed ABC-Trans.”
A Benchmark and Baseline for Open-Set Incremental Object Detection
Wan, Q., & Wang, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650826 · Cited by 1
“For a concrete implementation of the OSIOD setting, we consider images from existing object detection datasets, including VOC [33], COCO [34], Objects365 [35], Open Images [36], and LVIS [37].”
MethodZhao, R., Wang, J., Chen, Y., Zheng, Z., Cui, K., & Su, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8858-3_6 · Cited by 1
Ambiguous Boundary Uncertainty Reduction in Single Stage Detector Models
Bharti, D., Puneeth, B., & Venkatesh, K. S. (2024) · IEEE International Conference on Computer Vision and Machine Intelligence (CVMI) · doi:10.1109/cvmi61877.2024.10782711 · Cited by 1
“The datasets like MS-COCO [1], Objects365 [2], ImageNet [3], and CrowdHuman [4] are large-scale object detection datasets that define ground truth bounding boxes as precisely as possible.”
Enhancing object detection in low-light conditions with adaptive parallel networks
Fu, G., Chu, H., & Tu, X. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.1.013007 · Cited by 1
Authorship Detection on Classical Chinese Text Using Deep Learning
Zhao, L., Shi, J., Zhang, C., & Liu, Z. (2025) · Applied Sciences · doi:10.3390/app15041677 · Cited by 1
“A high‑quality dataset provides sufficient information for the model 1982 and edited by Feng Qiyong et al. The first 80 chapters are based on the Gengchen book with the Cheng book used as a reference.”
Language-Guided Object Localization via Refined Spotting Enhancement in Remote Sensing Imagery
Zhang, P., Zhang, Y., Wu, H., Liu, X., Hou, Y., & Wang, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3562439 · Cited by 4
“The datasets included Object365 [42], COCO2017 [43], and CrowdHuman [44], which focus on identifying and locating objects within images.”
Garg, S., & Aich, A. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00058 · Cited by 1
“However, when compared to DINOv2 [13]—where category features were extracted using external data from Object365 [14]—DINOv2 consistently outperformed all VLM variants.”
Duong, V. H., Truong, V. D., Dinh, D. K., Vu, H., Luong, T. V., & Nguyen, T. C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00555 · Cited by 1
“Thus, we replace the conventional COCO initialization with weights pre-trained on Ob-jects365 [31].”
InfluentialNguyen, H. H., Pham, H. D. T., Le, K. M., & Nguyen, C. T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00569 · Cited by 1
“Every model is initialized from weights pre-trained on COCO[7] and Objects365[14], then exported to Ten-sorRT FP16 for evaluation, Co-DETR[22].”
Hao, H., Han, J., Li, C., Li, Y.-F., & Yue, X. (2024) · Qeios · doi:10.32388/95w7kc · Cited by 2
CerberusDet: Unified Multi-Dataset Object DetectionPreprint
Tolstykh, I., Chernyshov, M., & Kuprashevich, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5382647 · Cited by 1
“We conducted experiments on two publicly available datasets: PASCAL VOC [17] and Objects365 [39].”
MethodWeb-Scale Generic Object Detection at Microsoft Bing
Chen, S. X., Mukherjee, S., Phadke, U., Wang, T., Park, J., & Yada, R. T. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467122
“Some large-scale datasets [6, 16, 30] have been collected to facilitate further research in this scenario, in which challenges and solutions to data collection have been discussed.”
BackgroundGAIA: A Transfer Learning System of Object Detection that Fits Your NeedsPreprint
Bu, X., Peng, J., Yan, J., Tan, T., & Zhang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11346
“With the advent of larger datasets of object detection such as Objects365 [53], Open Images [34], and Robust Vision [1], there are works [46] focusing on solving”
BackgroundInfluentialApproximate Training of Object Detection on Large-Scale Datasets
Zarichkovyi, O., & Mukha, I. P. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-80472-5_32
Estratégia de alcance para próteses de membro superior baseada em visão neuromórfica
Gouveia, E. B. (2022) · doi:10.14393/ufu.di.2022.106
“Porém, os bons resultados registrados na literatura, só puderam atingir o nível de maturidade atual com o advento da colaboração internacional na criação de grandes conjuntos de dados e da utilização de Unidades de Processamento Gráfico (GPU), que permitiram um alto poder computacional dedicado no tratamento desses gr…”
BackgroundInfluentialComputer Vision-based Monitoring of Harvest Quality
Rasmussen, C. B. (2021) · doi:10.54337/aau468596652
Dual-Stream Feature Fusion Network for Detection and ReID in Multi-object Tracking
He, Q.-Y., & Li, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20862-1_18
Applying Positional Encoding to Enhance Vision-Language Transformers
Liu, X., Delany, S. J., & McKeever, S. (2023) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0011796100003417
“Oscar also pre-trained the transformer with a larger group of datasets, including Open Images (Kuznetsova et al., 2020) and Object365 (Shao et al., 2019).”
Visual Question Answering for Response Synthesis Based on Spatial Actions
Kiselev, G., Weizenfeld, D., & Gorbunova, Y. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-30648-8_5
Sun, R., & Xiong, H. (2023) · Journal of Image and Graphics · doi:10.11834/jig.210337
Golroudbari, A. A., & Sabour, M. H. (2023) · doi:10.22541/au.168727976.63672670/v1 · Cited by 1
Covid-19 Detection Based on Chest X-Ray Images Using Multiple Transfer Learning CNN Models
Silva, B. R. D. S., Cortez, P. C., Motta, P. C., & Marques, J. A. L. (2023) · Springer eBooks · doi:10.1007/978-3-031-30788-1_4
Universal Object Detection Under Unconstrained Environments
Kaur, N., Swaroopa, K. M., & Chetty, G. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-5088-1_34
YOLOv5-based Fatigued Driving Detection
Guan, L. (2023) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece58870.2023.10263342
Automatic label assignment object detection mehtod on only one feature map
Ma, T., Huang, Z., Yang, N., Zhu, C., & Deng, P. (2023) · Machine Vision and Applications · doi:10.1007/s00138-023-01481-4
“In contrast, DINO [20] achieves the state-of-the-art result with a publicly available SwinL [21] backbone and the Objects365 [13] dataset (1.7M annotated images) only.”
Hong, Y., Song, H., Li, X., Yang, S.-J., & Hong, T. (2023) · Advances in transdisciplinary engineering · doi:10.3233/atde231008
Alexsah, R. P., Peter, P., Muliono, Y., & Prasetyo, S. Y. (2023) · IEEE International Conference on Communication, Networks and Satellite (COMNETSAT) · doi:10.1109/comnetsat59769.2023.10420556
“They used evolutionary algorithms for the first 10% of periods and a cosine annealing scheduler [23] to modify the learning rate while training to find the ideal hyper-parameters.”
MethodVirtual Handwriting Based Smart Board Using Deep Learning
Malathi, P., Gayathri, B. S., Lakshmi, S., Sahitya, E., & Rupa, J. S. (2023) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact58649.2023.10434425
“This localization is performed once the palm is identified across the entire image [9].”
BackgroundPD-UVU: Prompts-Driven Unified Visual Understanding Model Based on Specific Queries
Lu, X., & Zhang, C. (2023) · IEEE Smart World Congress (SWC) · doi:10.1109/swc57546.2023.10448966
“Since Objects365 [21] does not provide mask annotations, we additionally incorporate two auxiliary losses proposed by BoxInst [22] to train the mask branch.”
MethodInfluentialCredible Teacher for Semi-Supervised Object Detection in Open Scene
Zhuang, J., Wang, K., Lin, L., & Li, G. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446485
“We evaluate our method on two famous object detection datasets: the MS-COCO dataset [17] and the Ob-jects365 Baselines and Evaluation Criteria.”
MethodLeveraging Task-Specific Pre-Training to Reason across Images and Videos
Sadhu, A., & Nevatia, R. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00569
Language-Aware Multiple Datasets Detection Pretraining for DetrsPreprint
Hao, J., & Song, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4806931
Object detection for helping visually impaired
Makkar, S., Joshi, S., Gupta, T., Rajchandar, K., & Dhandapani, K. (2024) · AIP conference proceedings · doi:10.1063/5.0195919
Eliminating and mining strategies for open-world object proposal
Wang, C., Wang, G., Zhang, Q., Guo, P., Liu, W., & Xing-gang, W. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128026
Component Selection for Craft Assembly Tasks
Isume, V. H., Kiyokawa, T., Yamanobe, N., Domae, Y., Wan, W., & Harada, K. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3440847 · Cited by 1
“Specifically, we use the weights pretrained on the COCO dataset [21] with Object365 [22] intermediate fine-tuning, and fine-tune it for the parts of the truck, chair, table and bus object classes, resulting in nine possible part classes.”
MethodTransformer-Based Human Interaction Detection: A Survey
管, 尹. (2024) · Computer Science and Application · doi:10.12677/csa.2024.148175
Instance Segmentation with a Novel Tree Log Detection Dataset
Haasis, J., Bonenberger, C. M. A., & Schneider, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70893-0_23
Investigating Neural Networks and Transformer Models for Enhanced Comic Decoding
Kouletou, E., Papavassiliou, V., & Katsouros, V. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70645-5_10
Local-to-Global Point Supervised Object Detector via Aggregation of Discriminative Parts
Zhang, Y., Hou, Y., Liu, X., Li, X., Mou, F., Zhang, P., Qi, X., Jia, J., Wang, L., & Zhao, X. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-71716-1_12
Memory-based Error Label Suppression for Embodied Self-Improving Object Detection
Deng, J., Zhang, H., Hu, J., & Wang, Y. (2024) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case59546.2024.10711352
“The Grounding DINO used in our experiments is pre-trained on Objects365[14], GoldG[15], and Cap4M[15].”
MethodPrivacy-Decision Assisting Techniques
Kqiku, L. (2024) · doi:10.53846/goediss-10852
Kumar, H., & Singh, V. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-6318-4_8
DCI-Net: Remote Sensing Image-Based Object Detector
Cui, Q. H., & Lu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78113-1_1
Efficient Training of Lightweight Multimodal Models and Their Application to Downstream Tasks
梁瀬, 和., JIKUYA, K., OMOTE, H., TSUCHIDA, H., & Kato, K. (2025) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.91.81
RelFormer: Advancing contextual relations for transformer-based dense captioning
Jin, W., Qu, M., Shi, C., Zhao, Y., & Wei, Y. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104300
Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
Ganguly, D., Gupta, D., & Chaudhary, V. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8702-9_15
Field of View Invariant Object Recognition Using Non-Linear Transformation Augmentation
Alaran, M., Balgabekova, Z., & Varol, H. A. (2024) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon55916.2024.10905287
“This is done by applying eight (8) different transformations to Objects365 [26] dataset.”
InfluentialMulti-Point Positional Insertion Tuning for Small Object Detection
Goto, K., Karasawa, T., Hirose, T., Kawakami, R., & Inoue, N. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888925 · Cited by 1
“Parameter efficient finetuning experiments were conducted using the MM-Grounding DINO [10] model, which is pre-trained on the union of the following four datasets: O365 [39], GoldG [40], GRIT [41] and V3Det [42].”
Zhou, J., Zhou, Z., & Zhang, P. (2025) · IEEE Access · doi:10.1109/access.2025.3552796
“The Objects365 dataset [71] is one of the most challenging OOD detection datasets.”
Federated fine-grained prompts for vision-language models based on open-vocabulary object detection
Li, Y. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06527-w
Enhancing open-vocabulary object detection through region-word and region-vision matching
Chen, Y., Wang, C., Li, Z., Lin, S., Xiang, J., Li, Y., & Qian, J. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01806-5 · Cited by 1
“Specifically, we evaluate the model trained on OV-LVIS directly on the COCO [55] and Objects365 [67] datasets by inserting the vocabulary of the test datasets, without further fine-tuning the model.”
Self-citationLet Images Speak More: An Efficient Method for Detecting Image Manipulation History
Yang, W., Liu, H., Yuan, X., Bi, X., & Xiao, B. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3571767
“…with di ff erent scales and resolutions, we conducted ablation experiments on two representative datasets: the BossBase dataset [45], which has fewer images but higher resolution per image, and the Objects365 dataset [46], which contains a larger number of images but with lower resolution per image.”
A Curriculum Learning Framework to Boost Object Detection of Unmanned Aerial Vehicles
Aslan, E. S., Naddeo, K., Bouhsine, T., Robi Polikar, A., & Ditzler, G. (2025) · doi:10.1109/cisdb64969.2025.11010781 · Cited by 1
“In this work, we use a YOLOv7 model that was pre-trained using the COCO dataset [22].”
Research on a traffic flow statistical algorithm based on YBOVDT and SAM2
Wang, Y., Ding, Z., Liu, J., Wu, K., Dipu, M. S. K., Ma, T., Ma, Y., & Zhang, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-04336-2
Interaction-Aware Scene Debiasing for Action Recognition
Wihandika, R. C., Mendonça, I., & Aritsugi, M. (2025) · IEEE Access · doi:10.1109/access.2025.3581931
Visopendet: Open-Set Object Detection Via Interactive Visual PromptsPreprint
tan, M., Ling, L., Liu, R., Zhou, S., & Qiu, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5365102
MonoDeMB: Comprehensive Monocular DepthMap Benchmark
Chopuryan, V., Kuznetsov, M. D., Latonov, V., Mashurov, V., & Semenova, N. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737394
Learning Compositionality from Multifaceted Synthetic Data for Language-based Object Detection
Park, K., An, S., Lee, Y. J., & Kim, D. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02554-9 · Cited by 1
YOLO-VG: Enhancing Multi-Stage Feature Interaction for Visual Grounding
Liu, Y., Jiang, L., Li, G., Ye, X., & Ouyang, Y. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11083972
Frozen Network Few-Shot Object Detection
Nagano, K., Sato, F., Hachiuma, R., Tsutsukawa, K., & Sekii, T. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084624
Sun, F., Yu, J., Zhang, Y., Hou, J., Lu, X., Song, H., & Gao, F. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128326
“For detection and grounding tasks, we leverage datasets like Objects365 [62], RefCOCO [63] All-Seeing [64].”
Li, T., Li, Y., Hu, Y., & Ma, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-0988-1_4
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
