Cover Image

OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Teng, Zhao, Mengyang, Niu, Ke, Peng, Kaixin, Li, Bin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios
by: Fu, Teng, et al.
Published: (2025)

Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs
by: Peng, Kaixin, et al.
Published: (2025)

Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
by: Li, Hengzhuang, et al.
Published: (2025)

IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
by: Zhao, Mengyang, et al.
Published: (2025)

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
by: Niu, Ke, et al.
Published: (2025)

PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models
by: Zhang, Yongjian, et al.
Published: (2025)

HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding
by: Zhao, Jiaxing, et al.
Published: (2025)

Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving
by: Gao, Haoxiang, et al.
Published: (2025)

Video-to-Text Pedestrian Monitoring (VTPM): Leveraging Computer Vision and Large Language Models for Privacy-Preserve Pedestrian Activity Monitoring at Intersections
by: Abdelrahman, Ahmed S., et al.
Published: (2024)

MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization
by: Yu, JiangYong, et al.
Published: (2025)

Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
by: Niu, Ke, et al.
Published: (2024)

EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models
by: Yu, Haiyang, et al.
Published: (2025)

VLM-PAR: A Vision Language Model for Pedestrian Attribute Recognition
by: Sellam, Abdellah Zakaria, et al.
Published: (2025)

OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding
by: Tao, Haoyi, et al.
Published: (2026)

Understanding Counting Mechanisms in Large Language and Vision-Language Models
by: Hasani, Hosein, et al.
Published: (2025)

PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Prediction
by: Mishra, Naman, et al.
Published: (2026)

DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
by: Wu, Yuchuan, et al.
Published: (2026)

Review of Hallucination Understanding in Large Language and Vision Models
by: Ho, Zhengyi, et al.
Published: (2025)

Unleashing the Capabilities of Large Vision-Language Models for Intelligent Perception of Roadside Infrastructure
by: Fu, Luxuan, et al.
Published: (2026)

CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
by: Niu, Ke, et al.
Published: (2025)

OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking
by: Gao, Jianjun, et al.
Published: (2023)

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
by: Niu, Ke, et al.
Published: (2025)

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
by: Liu, Yunze, et al.
Published: (2024)

InsightSee: Advancing Multi-agent Vision-Language Models for Enhanced Visual Understanding
by: Zhang, Huaxiang, et al.
Published: (2024)

DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
by: Feng, Hao, et al.
Published: (2023)

Multi-view Phase-aware Pedestrian-Vehicle Incident Reasoning Framework with Vision-Language Models
by: Zhen, Hao, et al.
Published: (2025)

OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
by: He, Xingxin, et al.
Published: (2025)

NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
by: Zhou, Gengze, et al.
Published: (2024)

Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
by: Jiang, Yankai, et al.
Published: (2024)

FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
by: Pan, Huitong, et al.
Published: (2024)

Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models
by: Zhao, Jianfei, et al.
Published: (2025)

Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
by: Wang, Xiao, et al.
Published: (2023)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
by: Liu, Jiahang, et al.
Published: (2025)

Unleash the Potential of CLIP for Video Highlight Detection
by: Han, Donghoon, et al.
Published: (2024)

OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
by: Fu, Ronghao, et al.
Published: (2026)

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
by: Wei, Zhixiang, et al.
Published: (2026)

Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction
by: Liu, Yu, et al.
Published: (2025)

Assessing Color Vision Test in Large Vision-language Models
by: Ye, Hongfei, et al.
Published: (2025)

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
by: Zhang, Haoyu, et al.
Published: (2026)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
by: Wang, Ruofan, et al.
Published: (2024)