Cover Image

OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Yibin, Xu, Jilan, Di, Shangzhe, Wu, Haoning, Xie, Weidi
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 Streaming Video Representation via Multitask Training
by: Yan, Yibin, et al.
Published: (2025)

Grounded Question-Answering in Long Egocentric Videos
by: Di, Shangzhe, et al.
Published: (2023)

Revisiting Multi-Task Visual Representation Learning
by: Di, Shangzhe, et al.
Published: (2026)

Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos
by: Chen, Qirui, et al.
Published: (2024)

EchoSight: Advancing Visual-Language Models with Wiki Knowledge
by: Yan, Yibin, et al.
Published: (2024)

SoccerMaster: A Vision Foundation Model for Soccer Understanding
by: Yang, Haolin, et al.
Published: (2025)

Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation
by: Shi, Yudi, et al.
Published: (2024)

Count Anything at Any Granularity
by: Liu, Chang, et al.
Published: (2026)

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
by: Xie, Ming, et al.
Published: (2026)

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
by: Li, Zeqian, et al.
Published: (2025)

Action Emergence from Streaming Intent
by: Jing, Pengfei, et al.
Published: (2026)

SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass
by: Meng, Yanxu, et al.
Published: (2025)

MatchTime: Towards Automatic Soccer Game Commentary Generation
by: Rao, Jiayuan, et al.
Published: (2024)

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
by: Zhao, Ruixiang, et al.
Published: (2026)

Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting
by: Yan, Jinbo, et al.
Published: (2025)

StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
by: LI, Yang, et al.
Published: (2025)

Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
by: Di, Shangzhe, et al.
Published: (2025)

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding
by: Tian, Xueyun, et al.
Published: (2026)

Towards Universal Soccer Video Understanding
by: Rao, Jiayuan, et al.
Published: (2024)

Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
by: Liu, Chang, et al.
Published: (2023)

Multi-Agent System for Comprehensive Soccer Understanding
by: Rao, Jiayuan, et al.
Published: (2025)

Retrieval-Augmented Egocentric Video Captioning
by: Xu, Jilan, et al.
Published: (2024)

StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
by: Wu, Zike, et al.
Published: (2025)

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
by: Wang, Yuxuan, et al.
Published: (2025)

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
by: Cheng, Chong, et al.
Published: (2026)

MRGen: Segmentation Data Engine for Underrepresented MRI Modalities
by: Wu, Haoning, et al.
Published: (2024)

Dual-Stream Alignment for Action Segmentation
by: Gammulle, Harshala, et al.
Published: (2025)

Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning
by: Shi, Yudi, et al.
Published: (2026)

OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
by: Song, Yiren, et al.
Published: (2026)

MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction
by: Dong, Jiacheng, et al.
Published: (2026)

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
by: Shi, Yiran, et al.
Published: (2026)

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
by: Li, Ao, et al.
Published: (2026)

QUEST: Query Stream for Practical Cooperative Perception
by: Fan, Siqi, et al.
Published: (2023)

ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning
by: Nazarenus, Eric, et al.
Published: (2026)

D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
by: Fu, Bowen, et al.
Published: (2023)

Geometric Context Transformer for Streaming 3D Reconstruction
by: Chen, Lin-Zhuo, et al.
Published: (2026)

Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
by: Su, Rui, et al.
Published: (2019)

Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction
by: Jiang, Jianping, et al.
Published: (2024)

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
by: Kang, Hyolim, et al.
Published: (2024)

SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes
by: Qiu, Zhicheng, et al.
Published: (2026)