Imagen de Portada

SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ouyang, Liangyang, Liu, Ruicong, Kang, Caixin, Huang, Yifei, Sato, Yoichi
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions
por: Kang, Caixin, et al.
Publicado: (2025)

SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting
por: Liu, Ruicong, et al.
Publicado: (2025)

Multi-speaker Attention Alignment for Multimodal Social Interaction
por: Ouyang, Liangyang, et al.
Publicado: (2025)

Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions
por: Kang, Caixin, et al.
Publicado: (2025)

ActionVOS: Actions as Prompts for Video Object Segmentation
por: Ouyang, Liangyang, et al.
Publicado: (2024)

Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
por: Zhang, Mingfang, et al.
Publicado: (2025)

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
por: Kang, Caixin, et al.
Publicado: (2026)

Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition
por: Zhang, Mingfang, et al.
Publicado: (2024)

Leadership Assessment in Pediatric Intensive Care Unit Team Training
por: Ouyang, Liangyang, et al.
Publicado: (2025)

The N-Body Problem: Parallel Execution from Single-Person Egocentric Video
por: Zhu, Zhifan, et al.
Publicado: (2025)

LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editing
por: Ouyang, Liangyang, et al.
Publicado: (2025)

Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
por: Liu, Ruicong, et al.
Publicado: (2024)

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
por: Zhang, Mingfang, et al.
Publicado: (2026)

AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities
por: Banno, Tatsuro, et al.
Publicado: (2025)

Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation
por: Liu, Ruicong, et al.
Publicado: (2025)

EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking
por: Sakai, Yuki, et al.
Publicado: (2025)

Pre-Training for 3D Hand Pose Estimation with Contrastive Learning on Large-Scale Hand Images in the Wild
por: Lin, Nie, et al.
Publicado: (2024)

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
por: Peng, Yichen, et al.
Publicado: (2026)

FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation
por: Yagi, Takuma, et al.
Publicado: (2024)

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls
por: Xu, Qianxun, et al.
Publicado: (2026)

Egocentric Gaze Estimation via Neck-Mounted Camera
por: Huang, Haoyu, et al.
Publicado: (2026)

ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
por: Wu, Xiaoxue, et al.
Publicado: (2025)

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
por: Li, Guangzhao, et al.
Publicado: (2025)

DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation
por: Chen, Junhao, et al.
Publicado: (2025)

Seeking Flat Minima with Mean Teacher on Semi- and Weakly-Supervised Domain Generalization for Object Detection
por: Furuta, Ryosuke, et al.
Publicado: (2023)

HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
por: Tateno, Masatoshi, et al.
Publicado: (2025)

AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
por: Zhong, Zhizhou, et al.
Publicado: (2025)

Training-Free Robust Interactive Video Object Segmentation
por: Wei, Xiaoli, et al.
Publicado: (2024)

MotionClone: Training-Free Motion Cloning for Controllable Video Generation
por: Ling, Pengyang, et al.
Publicado: (2024)

UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
por: Chu, Xuangeng, et al.
Publicado: (2025)

Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
por: Huang, Qihan, et al.
Publicado: (2024)

FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion
por: Lu, Yu, et al.
Publicado: (2025)

Towards Interactive Intelligence for Digital Humans
por: Cai, Yiyi, et al.
Publicado: (2025)

VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
por: Li, Wenlong, et al.
Publicado: (2025)

LongDiff: Training-Free Long Video Generation in One Go
por: Li, Zhuoling, et al.
Publicado: (2025)

Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities
por: Mazzamuto, Michele, et al.
Publicado: (2024)

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
por: Kong, Zhe, et al.
Publicado: (2025)

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
por: Feng, X., et al.
Publicado: (2026)

ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation
por: Peng, Bo, et al.
Publicado: (2023)

SocialGen: Modeling Multi-Human Social Interaction with Language Models
por: Yu, Heng, et al.
Publicado: (2025)