paper-with-me

홈 › Papers

Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving

2025-01-12 · Haoxiang Gao, Yu Zhao

Autonomous driving (AD) has experienced significant improvements in recent years and achieved promising 3D detection, classification, and localization results. However, many challenges remain, e.g. semantic understanding of pedestrians' behaviors, and downstream handling for pedestrian interactions. Recent studies in applications of Large Language Models (LLM) and Vision-Language Models (VLM) have achieved promising results in scene understanding and high-level maneuver planning in diverse traffic scenarios. However, deploying the billion-parameter LLMs to vehicles requires significant computation and memory resources. In this paper, we analyzed effective knowledge distillation of semantic labels to smaller Vision networks, which can be used for the semantic representation of complex scenes for downstream decision-making for planning and control.

📄 PDF Abstract BibTeX arXiv:2501.06680

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDecision MakingKnowledge DistillationLanguage ModelingLanguage ModellingScene Understanding

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

PSI: A Pedestrian Behavior Dataset for Socially Intelligent Autonomous Car

2021-12-05 · Tina Chen, Taotao Jing, Renran Tian, Yaobin Chen 외

Prediction of pedestrian behavior is critical for fully autonomous vehicles to drive in busy city streets safely and efficiently. The future autonomous cars need to fit into mixed conditions with not only technical but a…

Autonomous Vehicles

Capturing the Dynamics of Pedestrian Traffic Using a Machine Vision System

2015-07-26 · Louie Vincent A. Ngoho, Jaderick P. Pabico

We developed a machine vision system to automatically capture the dynamics of pedestrians under four different traffic scenarios. By considering the overhead view of each pedestrian as a digital object, the system proces…

ObjectPosition

Intend-Wait-Perceive-Cross: Exploring the Effects of Perceptual Limitations on Pedestrian Decision-Making

2023-02-08 · Iuliia Kotseruba, Amir Rasouli

Current research on pedestrian behavior understanding focuses on the dynamics of pedestrians and makes strong assumptions about their perceptual abilities. For instance, it is often presumed that pedestrians have omnidir…

Decision Making

Understanding Pedestrian Behaviors From Stationary Crowd Groups

2015-06-01 · CVPR 2015 6 · Shuai Yi, Hongsheng Li, Xiaogang Wang

Pedestrian behavior modeling and analysis is important for crowd scene understanding and has various applications in video surveillance. Stationary crowd groups are a key factor influencing pedestrian walking patterns bu…

Event DetectionScene Understanding

Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval

2026-08-13 · Huu-An Vu, Cam Tu Tran Thi, Thanh Toan Le Ngo, Hoang Vo 외 arxiv

Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions. Compared with conventional text-based person retrieval, this…

Multimodal ReasoningPerson Retrieval