CROWD: A global dataset of continuous urban dashcam driving
cs.CV
Submitted: 2026-04-01
Updated: 2026-11-09
Code: https://github.com/Shaadalam9/pedestrians-in-youtube
Terminology
Sources
- A2D2: Audi Autonomous Driving Dataset
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- Joint Attention in Autonomous Driving (JAAD)
- D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios
- A Commute in Data: The comma2k19 Dataset
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
- One Million Scenes for Autonomous Driving: ONCE Dataset
- MAD: Motion Appearance Decoupling for efficient Driving World Models
- You Only Look Once: Unified, Real-Time Object Detection
- BoT-SORT: Robust Associations Multi-Pedestrian Tracking
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs