Image de couverture de livre

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Choudhury, Rohan, Zhu, Guanglei, Liu, Sihan, Niinuma, Koichiro, Kitani, Kris M., Jeni, László
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SkipSR: Faster Super Resolution with Token Skipping
par: Choudhury, Rohan, et autres
Publié: (2025)

Gaussian Splatting Lucas-Kanade
par: Xie, Liuyue, et autres
Publié: (2024)

Accelerating Vision Transformers with Adaptive Patch Sizes
par: Choudhury, Rohan, et autres
Publié: (2025)

CoGS: Controllable Gaussian Splatting
par: Yu, Heng, et autres
Publié: (2023)

GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
par: Milacski, Zoltán Á., et autres
Publié: (2024)

Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
par: Valois, Pedro, et autres
Publié: (2023)

Don't Judge by the Look: Towards Motion Coherent Video Representation
par: Zhang, Yitian, et autres
Publié: (2024)

Tokenizing Semantic Segmentation with Run Length Encoding
par: Singh, Abhineet, et autres
Publié: (2026)

Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting
par: Chen, Haiwei, et autres
Publié: (2024)

Multi-Object Tracking by Hierarchical Visual Representations
par: Cao, Jinkun, et autres
Publié: (2024)

ExpertAF: Expert Actionable Feedback from Video
par: Ashutosh, Kumar, et autres
Publié: (2024)

Scalable Dynamic Origin-Destination Demand Estimation Enhanced by High-Resolution Satellite Imagery Data
par: Liu, Jiachao, et autres
Publié: (2025)

Joint Diffusion for Universal Hand-Object Grasp Generation
par: Cao, Jinkun, et autres
Publié: (2024)

Don't Look at the Camera: Achieving Perceived Eye Contact
par: Gao, Alice, et autres
Publié: (2024)

Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
par: Khirodkar, Rawal, et autres
Publié: (2024)

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis
par: Ye, Yufei, et autres
Publié: (2024)

CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
par: Maeda, Takahiro, et autres
Publié: (2025)

Vision Transformers Don't Need Trained Registers
par: Jiang, Nick, et autres
Publié: (2025)

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
par: Zou, Xin, et autres
Publié: (2025)

DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery
par: Gao, Jing, et autres
Publié: (2025)

Adaptive Caching for Faster Video Generation with Diffusion Transformers
par: Kahatapitiya, Kumara, et autres
Publié: (2024)

OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
par: Zhao, Yiwen, et autres
Publié: (2026)

REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image
par: Ma, Xiaoxuan, et autres
Publié: (2026)

MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
par: Chen, Jiahe, et autres
Publié: (2024)

Generalizable Neural Human Renderer
par: Masuda, Mana, et autres
Publié: (2024)

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
par: Liu, Shuming, et autres
Publié: (2026)

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos
par: Islam, Md Mohaiminul, et autres
Publié: (2024)

3D-LFM: Lifting Foundation Model
par: Dabhi, Mosam, et autres
Publié: (2023)

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
par: Xiong, Tianwei, et autres
Publié: (2026)

Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras
par: Li, Yu-Jhe, et autres
Publié: (2024)

NeIn: Telling What You Don't Want
par: Bui, Nhat-Tan, et autres
Publié: (2024)

Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera
par: Yu, Mukai, et autres
Publié: (2025)

Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
par: Baid, Ami, et autres
Publié: (2026)

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
par: Zhao, Min, et autres
Publié: (2025)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
par: Bagrov, Natan, et autres
Publié: (2025)

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
par: Peng, Yichen, et autres
Publié: (2026)

Don't let the information slip away
par: Li, Taozhe, et autres
Publié: (2026)

S2GO: Streaming Sparse Gaussian Occupancy Prediction
par: Park, Jinhyung, et autres
Publié: (2025)

Show, Don't Tell: Detecting Novel Objects by Watching Human Videos
par: Akl, James, et autres
Publié: (2026)

Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning
par: Dou, Zi-Yi, et autres
Publié: (2024)