Cover Image

Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tezuka, Ryuki, Nakatani, Chihiro, Ukita, Norimichi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Group Activity Features Through Person Attribute Prediction
by: Nakatani, Chihiro, et al.
Published: (2024)

Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval
by: Nakatani, Chihiro, et al.
Published: (2026)

Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
by: Yokoyama, Kaname, et al.
Published: (2025)

End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement
by: Nakatani, Chihiro, et al.
Published: (2026)

Size-Variable Virtual Try-On with Physical Clothes Size
by: Yamashita, Yohei, et al.
Published: (2024)

SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios
by: Hirano, Shozaburo, et al.
Published: (2026)

Efficient Cost-and-Quality Controllable Arbitrary-scale Super-resolution with Fourier Constraints
by: Akita, Kazutoshi, et al.
Published: (2025)

Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks
by: Mori, Hiroshi, et al.
Published: (2024)

Inpainting-Driven Mask Optimization for Object Removal
by: Shimosato, Kodai, et al.
Published: (2024)

Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images
by: Kondo, Yuki, et al.
Published: (2023)

Test-time Cost-and-Quality Controllable Arbitrary-Scale Super-Resolution with Variable Fourier Components
by: Akita, Kazutoshi, et al.
Published: (2024)

Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
by: Oba, Takeru, et al.
Published: (2023)

Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching
by: Moriki, Takato, et al.
Published: (2026)

MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction
by: Tokoro, Kyotaro, et al.
Published: (2025)

Human Motion Prediction via Test-domain-aware Adaptation with Easily-available Human Motions Estimated from Videos
by: Shimbo, Katsuki, et al.
Published: (2025)

Depth Estimation fusing Image and Radar Measurements with Uncertain Directions
by: Kotani, Masaya, et al.
Published: (2024)

Burst Super-Resolution with Diffusion Models for Improving Perceptual Quality
by: Tokoro, Kyotaro, et al.
Published: (2024)

Selective Social-Interaction via Individual Importance for Fast Human Trajectory Prediction
by: Urano, Yota, et al.
Published: (2025)

CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
by: Maeda, Takahiro, et al.
Published: (2025)

Multimodal Active Measurement for Human Mesh Recovery in Close Proximity
by: Maeda, Takahiro, et al.
Published: (2023)

Efficient Burst Super-Resolution with One-step Diffusion
by: Kawai, Kento, et al.
Published: (2025)

Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
by: Taketsugu, Hiromu, et al.
Published: (2025)

NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI
by: Kondo, Yuki, et al.
Published: (2024)

SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition
by: Chappa, Naga VS Raviteja, et al.
Published: (2023)

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
by: Wang, Chengyao, et al.
Published: (2024)

DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
by: Tumanyan, Narek, et al.
Published: (2024)

AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding
by: Guo, Hao, et al.
Published: (2024)

EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild
by: Murrugarra-Llerena, Jeffri, et al.
Published: (2026)

Self-supervised Feature-Gate Coupling for Dynamic Network Pruning
by: Shi, Mengnan, et al.
Published: (2021)

DINO-Foresight: Looking into the Future with DINO
by: Karypidis, Efstathios, et al.
Published: (2024)

Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models
by: Soga, Masato, et al.
Published: (2026)

DINO-Tok: Adapting DINO for Visual Tokenizers
by: Jia, Mingkai, et al.
Published: (2025)

Back to the Features: DINO as a Foundation for Video World Models
by: Baldassarre, Federico, et al.
Published: (2025)

Multi-task Image Restoration Guided By Robust DINO Features
by: Lin, Xin, et al.
Published: (2023)

DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features
by: Huo, Jiayu, et al.
Published: (2026)

Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look
by: Zhang, Yong, et al.
Published: (2024)

Evaluating Stenosis Detection with Grounding DINO, YOLO, and DINO-DETR
by: Ansari, Muhammad Musab
Published: (2025)

Effective Feature Learning for 3D Medical Registration via Domain-Specialized DINO Pretraining
by: Kats, Eytan, et al.
Published: (2026)

Tri-path DINO: Feature Complementary Learning for Remote Sensing Multi-Class Change Detection
by: Zheng, Kai, et al.
Published: (2026)

Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion
by: Dominici, Edoardo A., et al.
Published: (2026)