GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

arXiv:2607.13569 · cs.CV, cs.AI · Submitted 2026-07-15 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-07-15

Updated: 2026-08-28

Terminology

• Grounding — 13× in this paper · explained in 3 episodes
• Visual Grounding — 6× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Alignment — 1× in this paper · explained in 1 episode
• F1 Score — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen3-VL Technical Report
• SAM 3: Segment Anything with Concepts
• TransitReID: Transit OD Data Collection with Occlusion-Resistant Dynamic Passenger Re-Identification
• iPay: Integrated Payment Action Recognition via Multimodal Networks and Adaptive Spatial Prior Learning
• Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
• A Deep Neural Network Approach to Fare Evasion
• ActionCLIP: A New Paradigm for Video Action Recognition

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models