This year's AI City Challenge CVPR workshop will take place on Monday, June 17th.

This year's event will be held in hybrid mode, allowing attendees to participate either in person or remotely. 

Please find tentative the workshop schedule below (Pacific Time):  

07:30 AM – 08:00 AM



Breakfast (served starting from 7:30 AM)

08:00 AM – 08:30 AM



Opening – Workshop Organization Presentation

08:30 AM – 09:15AM




Speaker: Prof. Daniel Cremers

Topic: Large-Scale Dynamic Scene Understanding

09:15 AM – 10:10 AM



Paper Presentations and Q&A – Track1

(1) Paper_ID 32: Overlap Suppression Clustering for Offline Multi-Camera People Tracking

(2) Paper_ID 1: A Robust Online Multi-Camera People Tracking System With Geometric Consistency and State-aware Re-ID Correction

(3) Paper_ID 39: Cluster Self-Refinement for Enhanced Online Multi-Camera People Tracking

(4) Paper_ID 46: OCMCTrack: Online Multi-Target Multi-Camera Tracking with Corrective Matching Cascade

(5) Paper_ID 6: An Online Approach and Evaluation Method for Tracking People Across Cameras in Extremely Long Video Sequence

(6) Paper_ID 40: Online Multi-camera People Tracking with Spatial-temporal Mechanism and Anchor-feature Hierarchical Clustering

(7) Paper_ID 43: Efficient Online Multi-Camera Tracking with Memory-Efficient Accumulated Appearance Features and Trajectory Validation

10:10 AM – 10:25AM


Morning Coffee (served from 10:00 to 10:45)

10:25 AM – 11:10 AM


Paper Presentations and Q&A – Track2

(1) Paper_ID 38: CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario

(2) Paper_ID 10: Divide and Conquer Boosting for Enhanced Traffic Safety Description and Analysis with Large Vision Language Model

(3) Paper_ID 28: TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning

(4) Paper_ID 27: Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis

(5) Paper_ID 15: Multi-perspective Traffic Video Description Model with Fine-grained Refinement Approach

11:10 AM – 11:50 AM


Paper Presentations and Q&A – Track3

(1) Paper_ID 24: Augmented Self-Mask Attention Transformer for Naturalistic Driving Action Recognition

(2) Paper_ID 31: Multi-View Spatial-Temporal Learning for Understanding Unusual Behaviors in Untrimmed Naturalistic Driving Videos

(3) Paper_ID 37: Multi-View Action Recognition for Distracted Driver Behavior Localization

(4) Paper_ID 51: DeepLocalization: Using change point detection for Temporal Action Localization

11:50 AM – 13:00 PM


Lunch (served from 11:45 AM to 13:30 PM)

13:00 PM – 13:55 PM


Paper Presentations and Q&A – Track4

(1) Paper_ID 4: Robust Data Augmentation and Ensemble Method for Object Detection in Fisheye Camera Images

(2) Paper_ID 50: Road Object Detection Robust to Distorted Objects at the Edge Regions of Images

(3) Paper_ID 20: Improving Object Detection to Fisheye Cameras with Open-Vocabulary Pseudo-Label Approach

(4) Paper_ID 44: Enhancing Road Object Detection in Fisheye Cameras: An Effective Framework Integrating SAHI and Hybrid Inference

(5) Paper_ID 12: Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets

(6) Paper_ID 19: FE-Det: An Effective Traffic Object Detection Framework for Fish-Eye Cameras

(7) Paper_ID 42: Simple Inplace Data Augmentation for Surveillance Object Detection

13:55 PM – 14:35 PM


Paper Presentations and Q&A – Track5

(1) Paper_ID 36: Robust Motorcycle Helmet Detection in Real-World Scenarios: Using Co-DETR and Minority Class Enhancement

(2) Paper_ID 17: An Effective Method for Detecting Violation of Helmet Rule for Motorcyclists

(3) Paper_ID 5: Motorcyclist Helmet Violation Detection Framework by Leveraging Robust Ensemble and Augmentation Methods

(4) Paper_ID 13: A Coarse-to-fine Two-stage Helmet Detection Method for Motorcyclists

14:35 PM – 15:00 PM


Paper Presentations and Q&A – Independent

(1) Paper_ID 14: PV-Cap: 3D Dynamic Scene Understanding Through Open Physics-based Vocabulary

(2) Paper_ID 26: KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Agent Trajectory Forecasting at Signalized Intersections.

15:00 PM – 15:15 PM



Afternoon Coffee Break (served from 15:00 PM to 15:45 PM)

15:15 PM – 16:15 PM



Panel Discussion on Ethical AI & Intelligent Traffic System (ITS)

  • Panel members on Ethical AI: 

Thomas Tang, Shuo Wang, David Anastasiu, Liang Zheng, Daniel Cremers

  • Panel members on Intelligent Traffic Systems (ITS): 

Norimasa Kobori, Anuj Sharma, Shuo Wang, Pranamesh Chakraborty, Munkhjargal Gochoo, David Kuehn

16:15 PM – 16:30 PM



Award Ceremony

16:30 PM – 17:30 PM



Poster Session

17:30 PM