Challenge Winners

  • Teams need to submit workshop paper to be eligible for awards
  • Teams need to open-source full code for result reproduction to be eligible for awards

Track 1:

Winner: Team28 matcher

Box-Grained Reranking Matching for Multi-Camera Multi-Target Tracking

Runner-up: Team59 BOE

Multi-camera vehicle tracking system for AI City Challenge 2022

The following table shows the top teams (that have submitted papers) from the public leader board of Track 1 by the challenge submission deadline.

RankTeam IDTeam NameScore
128matcher0.8486
259BOE0.8437
337TAG0.8371
450FraunhoderIOSB0.8348
1094SKKU0.8129
184HCMIU0.7255

Track 2:

Winner: Team183 MegVideo

Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrieval

Runner-up: Team91 HCMUS

Text Query based Traffic Video Event Retrieval with Global-Local Fusion Embedding

The following table shows the top teams from the public leader board of Track 2 by the challenge submission deadline.

  • Team176 used track1 data for training that gives a significant advantage. Using track1 data for training in track2 is specifically prohibited in the data readme file thus we have to disqualify team176 for winning the award. 
  • Team4 did not open-source their code for result reproduction thus per challenge rule we have to disqualify team4 for winning the award.
RankTeam ID TeamScore (MRR)
1176Must Win0.6606
34HCMIU-CVIP0.4773
4183MegVideo0.4392
591HCMUS0.3611
710Terminus-AI0.3320
924BUPT_MCPRL_T20.3012

Track 3:

Due to some resource issues, we are still working on the code evaluation and the final award winners will be decided later between Team1, Team16, Team43, Team72, Team95 , and Team97.

Track 4:

Winner: Team9 CyberCore

Improving Domain Generalization by Learning without Forgetting: Application in Retail Checkout

Runner-up: Team117 GRAPH@FIT

Image inpainting for automated checkout solution

  • Team55 did not submit paper to reveal their work thus per challenge rule we have to disqualify team55 for winning the award.

The following chart shows the performance of submitted codes from top teams on Dataset B. All submitted codes were tested on the same testing machine with the following specs:

•GPU: 4 NVIDIA TITAN RTX, 24 GB RAM
•CPU: 12-core Intel(R) Core(TM) i9-7920X  @ 2.90GHz
•Memory: 128 GB DDR4 RAM
•Drive:  2 NVMe RAID