2021 Challenge Winners
Track 1:
Winner: Team37 V-Group from Baidu
Robust and Online Vehicle Counting at Crowded Intersections
Runner-up: Team5 HCMIU-CVIP from HCM
Tiny-PIRATE: A Tiny model with Parallelized Intelligence for Real-time Analysis as a Traffic counter
The following chart shows the performance of submitted codes from top teams on Dataset B (4.5 hours). All submitted codes were tested on the same NV jetson device with the following specs:
Track 2:
Winner: Team47 DMT from Alibaba
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
Runner-up: Team9 NewGeneration from Baidu & UTS
Robust Vehicle Re-identification via Rigid Structure Prior
The following table shows the top teams from the public leader board of Track 2 by the challenge submission deadline.
| Rank | Team ID | Team Name | Score |
| 1 | 47 | DMT | 0.7445 |
| 2 | 9 | NewGeneration | 0.7151 |
| 3 | 29 | fivefive | 0.7119 |
| 4 | 7 | CyberHu | 0.6650 |
| 5 | 35 | For Azeroth | 0.6555 |
| 6 | 125 | IDo | 0.6373 |
| 7 | 44 | KeepMoving | 0.6364 |
| 8 | 122 | MegVideo | 0.6252 |
| 9 | 71 | aiem2021 | 0.6216 |
| 10 | 61 | CybercoreAI | 0.6134 |
Track 3:
Winner: Team75 mcmt from CAS & Alibaba
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Runner-up: Team29 fivefive from Baidu
A Robust MTMC Tracking System for AI-City Challenge 2021
The following table shows the top teams from the public leader board of Track 3 by the challenge submission deadline.
| Rank | Team ID | Team Name | Score |
| 1 | 75 | mcmt | 0.8095 |
| 2 | 29 | fivefive | 0.7787 |
| 3 | 7 | CyberHu | 0.7651 |
| 4 | 144 | track_mtmc | 0.7061 |
| 5 | 85 | FraunhoferIOSB | 0.6910 |
| 6 | 42 | starwars | 0.6575 |
| 7 | 15 | aiforward | 0.5812 |
| 8 | 27 | Janus Wars | 0.5763 |
| 9 | 48 | BUPT-MCPRL2 | 0.5534 |
| 10 | 79 | oOIAMAOo | 0.5458 |
Track 4:
Winner: Team76 KillerSeven from Baidu & CAS
Good Practices and A Strong Baseline for Traffic Anomaly Detection
Runner-up: Team158 BD from ByteDance
Box-Level Tube Tracking and Refinement for Vehicles Anomaly Detection
The following table shows the top teams from the public leader board of Track 4 by the challenge submission deadline.
| Rank | Team ID | Team Name | Score |
| 1 | 76 | KillerSeven | 0.9355 |
| 2 | 158 | BD | 0.9220 |
| 3 | 92 | WHU_IIP | 0.9197 |
| 4 | 90 | SIS Lab | 0.8597 |
| 5 | 153 | Titan Mizzou | 0.5686 |
| 6 | 48 | BUPT-MCPRL2 | 0.3010 |
| 7 | 26 | Attention Please! | 0.2184 |
| 8 | 154 | Alchera | 0.1418 |
| 9 | 12 | CET | 0.1401 |
Track 5:
Winner: Team132 Alibaba-UTS from Alibaba & UTS & Zhejiang U
Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
Runner-up: Team17 TimeLab from Shangdo U & Xidian U & Shandong Jianzhu U
DUN: Dual-path Temporal Matching Network for Natural Language-based Vehicle Retrieval
The following table shows the top teams from the public leader board of Track 5 by the challenge submission deadline.
| Rank | Team ID | Team Name | Score |
| 1 | 132 | Alibaba-UTS | 0.1869 |
| 2 | 13 | HCMUS | 0.1741 |
| 3 | 17 | TimeLab | 0.1613 |
| 4 | 36 | SBUK | 0.1594 |
| 5 | 20 | SNLP | 0.1571 |
| 6 | 147 | HUST | 0.1564 |
| 7 | 53 | VCA | 0.1548 |
| 8 | 62 | yongman | 0.1449 |
| 9 | 71 | aiem2021 | 0.1364 |
| 10 | 87 | Enablers | 0.1314 |