Imagen de Portada

It's a Matter of Time: Three Lessons on Long-Term Motion for Perception

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Davison, Willem, Hao, Xinyue, Sevilla-Lara, Laura
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

Telling Stories for Common Sense Zero-Shot Action Recognition
por: Gowda, Shreyank N, et al.
Publicado: (2023)

Principles of Visual Tokens for Efficient Video Understanding
por: Hao, Xinyue, et al.
Publicado: (2024)

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship
por: Gowda, Shreyank N, et al.
Publicado: (2023)

Continual Learning Improves Zero-Shot Action Recognition
por: Gowda, Shreyank N, et al.
Publicado: (2024)

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
por: Jiang, Jianwen, et al.
Publicado: (2024)

Motion Mamba: Efficient and Long Sequence Motion Generation
por: Zhang, Zeyu, et al.
Publicado: (2024)

Coarse or Fine? Recognising Action End States without Labels
por: Moltisanti, Davide, et al.
Publicado: (2024)

Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training
por: Sathiyanarayanan, Shriram M, et al.
Publicado: (2025)

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
por: Shen, Fei, et al.
Publicado: (2025)

When and Where to Reset Matters for Long-Term Test-Time Adaptation
por: Lim, Taejun, et al.
Publicado: (2026)

GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting
por: Agarwal, Madhav, et al.
Publicado: (2025)

T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences
por: Lee, Taeryung, et al.
Publicado: (2024)

MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
por: Jiang, Lei, et al.
Publicado: (2025)

Predicting Implicit Arguments in Procedural Video Instructions
por: Batra, Anil, et al.
Publicado: (2025)

Mask2IV: Interaction-Centric Video Generation via Mask Trajectories
por: Li, Gen, et al.
Publicado: (2025)

InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation
por: Zhang, Zeyu, et al.
Publicado: (2024)

VMBench: A Benchmark for Perception-Aligned Video Motion Generation
por: Ling, Xinran, et al.
Publicado: (2025)

Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
por: Zhu, Tianrui, et al.
Publicado: (2025)

L-LBVC: Long-Term Motion Estimation and Prediction for Learned Bi-Directional Video Compression
por: Zhai, Yongqi, et al.
Publicado: (2025)

Lagrangian Motion Fields for Long-term Motion Generation
por: Yang, Yifei, et al.
Publicado: (2024)

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
por: Xu, Guangkai, et al.
Publicado: (2024)

MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
por: Murai, Riku, et al.
Publicado: (2024)

KV-Tracker: Real-Time Pose Tracking with Transformers
por: Taher, Marwan, et al.
Publicado: (2025)

Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition
por: Gu, Jihao, et al.
Publicado: (2025)

Rethinking Inductive Biases for Surface Normal Estimation
por: Bae, Gwangbin, et al.
Publicado: (2024)

COMO: Compact Mapping and Odometry
por: Dexheimer, Eric, et al.
Publicado: (2024)

Generative Perception of Shape and Material from Differential Motion
por: Han, Xinran Nicole, et al.
Publicado: (2025)

Eye Motion Matters for 3D Face Reconstruction
por: Wang, Xuan, et al.
Publicado: (2024)

Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
por: Guo, Zhengrui, et al.
Publicado: (2025)

LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
por: Qiu, Jihao, et al.
Publicado: (2026)

Infinite Motion: Extended Motion Generation via Long Text Instructions
por: Li, Mengtian, et al.
Publicado: (2024)

Unforgettable Lessons from Forgettable Images: Intra-Class Memorability Matters in Computer Vision
por: Jing, Jie, et al.
Publicado: (2024)

Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction
por: Wang, Haolin, et al.
Publicado: (2025)

SuperPrimitive: Scene Reconstruction at a Primitive Level
por: Mazur, Kirill, et al.
Publicado: (2023)

Towards Consistent Long-Term Pose Generation
por: Li, Yayuan, et al.
Publicado: (2025)

OWL: A Novel Approach to Machine Perception During Motion
por: Raviv, Daniel, et al.
Publicado: (2026)

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation
por: Wang, Xinshun, et al.
Publicado: (2026)

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
por: He, Shuting, et al.
Publicado: (2024)

AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction
por: Idrees, Sarmad, et al.
Publicado: (2024)

LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model
por: Wang, Xiaodong, et al.
Publicado: (2025)