Scholar4AI Updated 2026-10-26 12:13 UTC+09:00

Object detection and segmentation benchmarks

3 papers in the last 7 days · 7 of its 7 datasets mentioned

← Most-used data

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

Key findings

  • Datasets in the category “Object detection and segmentation benchmarks” were mentioned in 26 papers in the last 30 days (2026-09-27 to 2026-10-26), ranking #10 of the 58 data categories mentioned.
  • The most-mentioned were MS COCO (11), nuScenes / Waymo Open / Argoverse (8), KITTI (5), PASCAL VOC (4) and ADE20K (3).
  • By journal category: AI (24) and Operations Research (2).
  • Most of them appeared in Pattern Recognition (7), Information Processing & Management (4) and Knowledge-Based Systems (3).

Datasets

Datasets in this category · 2026-09-27 – 2026-10-26 (30 days)
DatasetPapersLast 7 daysNames searched for
MS COCO112MS COCO, MS-COCO, Microsoft COCO, COCO dataset, COCO benchmark, Common Objects in Context, COCO
nuScenes / Waymo Open / Argoverse82nuScenes, Waymo Open, Argoverse
KITTI50KITTI
PASCAL VOC40PASCAL VOC, VOC2007, VOC2012, VOC 2007, VOC 2012
ADE20K30ADE20K
Cityscapes30Cityscapes
Open Images10Open Images dataset, OpenImages, Open Images V4, Open Images V6
Papers mentioning these datasets, newest first.
DateTitleJournalAuthorsAffiliationsDatasets mentioned
2026-10-22Beyond the survey: a systematic empirical study of detection and association in visual MOTArtificial Intelligence ReviewLinh Van Ma, Juhua Hu, Wei Cheng et al.Gwangju Institute of Science and Technology; University of Washington TacomaMS COCO, nuScenes / Waymo Open / Argoverse
2026-10-22Measuring the state of open science in transportation using large language modelsTransportation Research Part C Emerging TechnologiesJunyi Ji, Ruth Lu, Linda Belkessa et al.Vanderbilt University; Massachusetts Institute of Technology; Université Gustave Eiffel; …nuScenes / Waymo Open / Argoverse
2026-10-20Weighted UnLearning from Experience for Improved Spurious Correlation RobustnessMachine LearningJeff Mitchell, Jesus; id_orcid 0000-0002-9574-4138 Martinez-del-Rincon, Niall McLaughlinQueen's University BelfastMS COCO
2026-10-19A low-rank consensus method for vision language model hallucination mitigation in autonomous drivingTransportation Research Part C Emerging TechnologiesKeke Long, Jiacheng Guo, Tianyun Zhang et al.University of Wisconsin System; University of Wisconsin–Madison; Cleveland State University; …nuScenes / Waymo Open / Argoverse
2026-10-19Evidence-grounded multimodal knowledge graph for Dunhuang mural description generationExpert Systems with ApplicationsZhigang Xu, Chen ZhaoLanzhou University of TechnologyMS COCO
2026-10-17CorrCLIPv2: Harnessing Unlabeled Images for Open-Vocabulary Semantic SegmentationInternational Journal of Computer VisionD H Zhang, Fagui Liu, Quan Tang et al.South China University of Technology; Peng Cheng LaboratoryMS COCO, PASCAL VOC, Cityscapes, ADE20K
2026-10-17MonoPRIO: Adaptive prior conditioning for unified monocular 3D object detectionPattern RecognitionLeon Davies, Qinggang Meng, Mohamad Saada et al.Loughborough University; University of Southern DenmarkKITTI, nuScenes / Waymo Open / Argoverse
2026-10-16NISNet: Efficient native dense prediction via symmetric boundary-preserving coupling–decouplingExpert Systems with ApplicationsFengjun WU, Kafeng Wang, Xinai Xu et al.Nanchang Normal University; Jiangxi Normal University; Chinese Academy of Sciences; …ADE20K
2026-10-15Frequency–spatial dual-domain imperceptible watermarking for robust image datasets copyright protectionInformation Processing & ManagementXiaojie Du, Yedi Chen, Kai Ma et al.Guizhou Normal UniversityPASCAL VOC
2026-10-15VLGRA: Visual-Language Semantic Optimization and Graph Reasoning for cross-modal retrievalInformation Processing & ManagementShiyuan Yang, Zhixin Li, 尤忠祥 et al.Guangxi Normal UniversityMS COCO
2026-10-14SDDF-BEV: Uncertainty-aware spatio-temporal fusion for pure vision Bird’s-Eye-View 3D object detectionKnowledge-Based SystemsWei Zhang, Xulu Xia, Xingliang Zhu et al.University of Science and Technology of China; Hefei Institutes of Physical Science; Institute of Intelligent Machines; …nuScenes / Waymo Open / Argoverse
2026-10-12Beyond pairwise alignment: Hypergraph-based semantic calibration for image-text matchingInformation Processing & ManagementJin Chen, Xiang Shen, Dezhi Han et al.Shanghai Maritime University; The University of Sydney; Australian e-Health Research Centre; …MS COCO
2026-10-12P2L-CA: An effective parameter tuning framework for rehearsal-free Multi-Label Class-Incremental LearningPattern RecognitionSonglin Dong, Jiangyang Li, Chenhao Ding et al.Shenzhen University of Advanced Technology; Xi'an Jiaotong UniversityMS COCO, PASCAL VOC
2026-10-06AURORA-KITTI: Any-weather depth completion and denoisingInformation FusionYiting Wang, Tim Brödermann, Hamed Haghighi et al.Queen Mary University of London; American Society for Photogrammetry and Remote Sensing; University of Warwick; …KITTI
2026-10-05OAGDet: Dense occupancy-aware geometry for multi-view 3D object detection in autonomous drivingPattern RecognitionZhaojie Sun, Lu Shi, Du Qinhong et al.Beijing Jiaotong UniversityKITTI, nuScenes / Waymo Open / Argoverse
2026-10-01SteRGAN: An Improvised Framework based on Generative Adversarial Network for Image SteganographyNeural Computing and ApplicationsYatendra Sharma, Gopa BhaumikNational Institute of Technology Sikkim; National Institute of Technology JamshedpurMS COCO
2026-10-01High-frequency depth distillation from foundation models for multi-view 3D object detectionPattern RecognitionJingxin Wang, Shuang Li, Mingpi Tan et al.Chongqing University of Posts and TelecommunicationsnuScenes / Waymo Open / Argoverse
2026-10-01D2OM: Depth-aware dynamic matching for DETR-based monocular 3D detectionKnowledge-Based SystemsChenfeng Wei, Si Zuo, Chang Li et al.KITTI
2026-10-01RDD: Improving Structure from Motion with a Robust Feature Detector and DescriptorInternational Journal of Computer VisionG Chen, Tianwen Fu, Haiwei Chen et al.University of Southern California; Creative Technologies (United States)ADE20K
2026-10-01Label-Corrected Weighted Multi-Similarity Loss for noisy cross-modal retrievalInformation Processing & ManagementShuni Jiang, Shiyuan Yang, Zhixin LiGuangxi Normal UniversityMS COCO
2026-09-30TIC: Co-optimization of training and inference for efficient image-text retrievalNeural Networks尤忠祥, Shiyuan Yang, Zhixin LiGuangxi Normal UniversityMS COCO
2026-09-30MFPA-Net: A Multi-scale Frequency-aware Pyramid Aggregation Network for real-time semantic segmentationPattern RecognitionKao Ge, Qing-Bang HanHohai UniversityCityscapes
2026-09-29CoDIF: Conditional diffusion fusion with soft alignment for robust multimodal 3D object detectionInformation FusionPan Gao, Jianmei Cheng, Chun Fei et al.University of Electronic Science and Technology of China; Sichuan Police CollegeKITTI, nuScenes / Waymo Open / Argoverse
2026-09-29Debiasing scene graph generation with Context-Aware Peer NetworksPattern RecognitionLiguang Zhou, Yuhongze Zhou, Junjie Hu et al.McGill University; Chinese University of Hong Kong; Chinese University of Hong Kong, ShenzhenOpen Images
2026-09-29IDNet: Instance-level background disentanglement for few-shot object detection with parallel matchingKnowledge-Based SystemsDongyi Kong, Zhaobin Chang, Xiong Gao et al.Lanzhou UniversityMS COCO, PASCAL VOC
2026-09-28A Multi-task Sparse Adversarial Training framework for autonomous driving in harsh conditionsPattern RecognitionJiacheng Guo, Mingxuan Cui, Haochen Yang et al.Cleveland State University; Agency for Science, Technology and Research; University of Tennessee at Knoxville; …Cityscapes