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

Face, person and video benchmarks

2 papers in the last 7 days · 5 of its 5 datasets mentioned

← Most-used data

Faces, people, poses, facial expressions and human actions in images and video.

Key findings

  • Datasets in the category “Face, person and video benchmarks” were mentioned in 11 papers in the last 30 days (2026-09-27 to 2026-10-26), ranking #35 of the 58 data categories mentioned.
  • The most-mentioned were Action recognition (Kinetics, UCF101, HMDB51) (5), Person re-identification (Market-1501, DukeMTMC, MSMT17) (3), Face recognition (LFW, CelebA, VGGFace2) (1), Facial expression (FER2013, AffectNet, RAF-DB) (1) and Skeleton and pose (NTU RGB+D, Human3.6M) (1).
  • By journal category: AI (11).
  • Most of them appeared in Pattern Recognition (3), Applied Intelligence (2) and International Journal of Computer Vision (2).

Datasets

Datasets in this category · 2026-09-27 – 2026-10-26 (30 days)
DatasetPapersLast 7 daysNames searched for
Action recognition (Kinetics, UCF101, HMDB51)50Kinetics-400, Kinetics-600, Kinetics-700, UCF101, UCF-101, HMDB51, HMDB-51, Something-Something, ActivityNet
Person re-identification (Market-1501, DukeMTMC, MSMT17)31Market-1501, Market1501, DukeMTMC, MSMT17
Face recognition (LFW, CelebA, VGGFace2)11Labeled Faces in the Wild, LFW, CelebA, VGGFace2, CASIA-WebFace, MegaFace
Facial expression (FER2013, AffectNet, RAF-DB)10FER2013, FER-2013, AffectNet, RAF-DB
Skeleton and pose (NTU RGB+D, Human3.6M)10NTU RGB+D, NTU-RGB+D, NTU RGB-D, NTU60, NTU120, Human3.6M
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 TacomaPerson re-identification (Market-1501, DukeMTMC, MSMT17)
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 BelfastFace recognition (LFW, CelebA, VGGFace2)
2026-10-10LDOFormer: Low-rank and Decorrelation-regularized Transformer for 3D human pose estimationPattern RecognitionYu Zou, Zhigeng Pan, Xianxuan Lin et al.Nanjing University of Information Science and Technology; Jiangsu Open UniversitySkeleton and pose (NTU RGB+D, Human3.6M)
2026-10-06CRAFMark: Contrastive-driven robust adaptive frequency-aware video watermarking against H.265/HEVC compressionExpert Systems with ApplicationsShunzhe Zhu, Ke Niu, Jun Li et al.Chinese People's Armed Police Force Engineering UniversityAction recognition (Kinetics, UCF101, HMDB51)
2026-10-01EMM-CVT: An Efficient Multi-Modal Vision Transformer for compressed video action recognitionPattern RecognitionHong Wen, Bing Li, Liang Qian et al.Beijing Jiaotong University; Nankai UniversityAction recognition (Kinetics, UCF101, HMDB51)
2026-10-01A ConvNeXt-based facial expression recognition network integrating ALDS downsampling and SCSA semantic enhancementNeural Computing and ApplicationsYanqiu Li, Shengzhao Li, Guangling SunAnhui Jianzhu University; Anhui UniversityFacial expression (FER2013, AffectNet, RAF-DB)
2026-10-01Self-paced deep clustering: an attention model for unsupervised domain adaptive person re-identificationApplied IntelligenceQingyu Wang, Ruchun Jia, Bo Peng et al.Anhui Technical College of Industry and Economy; Sichuan UniversityPerson re-identification (Market-1501, DukeMTMC, MSMT17)
2026-10-01Multi-granularity contrastive learning for discovering categories of teacher instructional behavior indicatorsApplied IntelligenceTing Cai, Qingyuan Tang, Yu Xiong et al.Chongqing University of Posts and Telecommunications; University of PecsAction recognition (Kinetics, UCF101, HMDB51)
2026-10-01Blurring Modal Boundaries: A Unified Survey from Single- to Multi-modal Person Re-ldentificationInternational Journal of Computer VisionXiao Wang, Bing Wang, B Yang et al.Wuhan University of Science and Technology; Wuhan University; Anhui UniversityPerson re-identification (Market-1501, DukeMTMC, MSMT17)
2026-10-01Efficient Test-Time Prompt Tuning for Vision-Language ModelsInternational Journal of Computer VisionYuhan Zhu, Guozhen Zhang, Xu Chen et al.Nanjing University; Shanghai Artificial Intelligence LaboratoryAction recognition (Kinetics, UCF101, HMDB51)
2026-09-28Exploring the temporal consistency for point-level weakly-supervised temporal action localizationPattern RecognitionYunchuan Ma, Laiyun Qing, Guorong Li et al.University of Chinese Academy of Sciences; Macquarie UniversityAction recognition (Kinetics, UCF101, HMDB51)