OV-Bench
Emerging8papers using it
2025first seen
OV-Bench is a benchmark dataset used to evaluate the performance of models on various tasks related to online video understanding.
Papers using OV-Bench (8)
- SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and PlanningThink While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language ModelsWAT: Online Video Understanding Needs Watching Before ThinkingFreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video UnderstandingAnnotation-Free Visual Reasoning for High-Resolution Large Multimodal Models via Reinforcement LearningGuiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded ReasoningGrounded Reinforcement Learning For Visual ReasoningGam-agent: Game-theoretic And Uncertainty-aware Collaboration For Complex Visual Reasoning