AI City Challenge CVPR Virtual Workshop 2021

Due to the COVID-19 circumstance, this year’s AI City Challenge workshop remains to be completely virtual same as the CVPR main conference. To better accommodate people attending the workshop online from all over the world, we squeeze most interaction contents in a shorter time window suitable for most potential workshop attendees and we will have the pre-recorded oral presentations playing back before the main interaction section.

We have the section time marked in multiple time zones and please use time zone map for assistance if needed.

Great thanks to all that make this workshop successful. Stay safe.

11:00 – 11:30 PDT – LA

14:00 – 14:30 EDT – NY

02:00 – 02:30 CST – Beijing

20:00 – 20:30 CEST – Belgium


Recorded Oral Presentations – Track1 (5 minutes presentation each)

(1) Robust and Online Vehicle Counting at Crowded Intersections (paper, poster, slides, presentation)

Jincheng Lu; Meng Xia; Xu Gao; Xipeng Yang; Tianran Tao; Hao Meng; Wei Zhang; Xiao Tan; Yifeng Shi; Guanbin Li; Errui Ding

(2) Tiny-PIRATE: A Tiny model with Parallelized Intelligence for Real-time Analysis as a Traffic countEr (paper, poster, slides, presentation)

Synh Viet-Uyen Ha; Nhat Minh Chung; Tien-Cuong Nguyen; Hung Ngoc Phan

(3) A Region-and-Trajectory Movement Matching for Multiple Turn-counts at Road Intersection on Edge Device (paper, poster, slides, presentation)

Duong Nguyen-Ngoc Tran; Long Hoang Pham; Huy-Hung Nguyen;
Tai Huu-Phuong Tran; Hyung-Joon Jeon; Jae Wook Jeon

(4) Real-time and Robust System for Counting Movement-Specific Vehicle at Crowded Intersections (paper, poster, slides, presentation)

Vu-Hoang Tran; Le-Hoai-Hieu Dang; Chinh-Nghiep Nguyen; Ngoc-Hoang-Lam Le; Khanh-Phong Bui; Lam-Truong Dam; Quang-Thang Le; Dinh-Hiep Huynh

(5) Fast Vehicle Turning-Movement Counting using Localization-based Tracking (paper, poster, slides, presentation)

Derek Gloudemans; Daniel B. Work

(6) Multi-Class Multi-Movement Vehicle Counting Based on CenterTrack (paper, poster, slides, presentation)

Viktor Kocur; Milan Ftacnik

11:30 – 12:00 PDT – LA

14:30 – 15:00 EDT – NY

02:30 – 03:00 CST – Beijing

20:30 – 21:00 CEST – Belgium


Recorded Oral Presentations – Track2 (5 minutes presentation each)

(1) An Empirical Study of Vehicle Re-Identification on the AI City Challenge (paper, poster, slides, presentation)

Hao Luo; Weihua Chen; Xianzhe Xu; Jianyang Gu; Yuqi Zhang; Chong Liu; Shuting He; Fan Wang; Hao Li

(2) Robust Vehicle Re-identification via Rigid Structure Prior (paper, poster, slides, presentation)

Minyue Jiang; Xuanmeng Zhang; Yue Yu; Zechen Bai; Zhedong Zheng; Zhigang Wang; Jian Wang; Xiao Tan; Hao Sun; Errui Ding; Yi Yang

(3) Progressive Data Mining and Adaptive Weighted Multi-Model Ensemble for Vehicle Re-Identification (paper, poster, slides, presentation)

Yongli Sun; Wenpeng Li; Hua Wei; Longtao Zhang; Jiahao Tian; Guangze Sun; Gang Wang; Junliang Cao; Zhifeng Zhao; Junfeng Ding

(4) A Strong Baseline for Vehicle Re-Identification (paper, poster, slides, presentation)

Su V. Huynh; Nam H. Nguyen; Ngoc T. Nguyen; Vinh TQ. Nguyen; Chau Huynh; Chuong H.Nguyen

(5) Vehicle Re-Identification based on Ensembling Deep Learning Features including a Synthetic Training Dataset, Orientation and Background Features, and Camera Verification (paper, poster, slides, presentation)

Marta Fernandez; Paula Moral; Alvaro Garcia-Martin; Jose M. Martinez

12:00 – 12:40 PDT – LA

15:00 – 15:40 EDT – NY

03:00 – 03:40 CST – Beijing

21:00 – 21:40 CEST – Belgium


Recorded Oral Presentations – Track3 (5 minutes presentation each)

(1) City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones (paper, poster, slides, presentation)

Chong Liu; Yuqi Zhang; Hao Luo; Jiasheng Tang; Weihua Chen; Xianzhe Xu; Fan Wang; Hao Li; Yi-Dong Shen

(2) A Robust MTMC Tracking System for AI-City Challenge 2021 (paper, poster, slides, presentation)

Jin Ye; Xipeng Yang; Shuai Kang; Yue He; Weiming Zhang; Leping Huang; Wei Zhang; Yifeng Shi; Xiao Tan

(3) A Multi-Camera Vehicle Tracking System based on City-Scale Vehicle Re-ID and Spatial-Temporal Information (paper, poster, slides, presentation)

Minghu Wu; Yeqiang Qian; Chunxiang Wang; Ming Yang

(4) An Occlusion-aware Multi-target Multi-camera Tracking System (paper, poster, slides, presentation)

Andreas Specker; Daniel Stadler; Lucas Florin; Jurgen Beyerer

(5) Multi-Camera Vehicle Tracking System Based on Spatial-Temporal Filtering (paper, poster, slides, presentation)

Pengfei Ren; Kang Lu; Yu Yang; Yun Yang; Guangze Sun; Wei Wang; Gang Wang; Junliang Cao; Zhifeng Zhao; Wei Liu

(6) Tracklet-Refined Multi-Camera Tracking based on Balanced Cross-Domain Re-Identification for Vehicles (paper, poster, slides, presentation)

Kai-Siang Yang; Yu-Kai Chen; Tsai-Shien Chen; Chih-Ting Liu; Shao-Yi Chien

(7) Multi-Target Multi-Camera Vehicle Tracking for City-Scale Traffic Management (paper, poster, slides, presentation)

Kyujin Shim; Sungjoon Yoon; Kangwook Ko; Changick Kim

(8) Multi-Camera Tracking By Candidate Intersection Ratio Tracklet Matching (paper, poster, slides, presentation)

Yun-Lun Li; Zhi-Yi Chin; Ming-Ching Chang; Chen-Kuo Chiang

12:40 – 13:10 PDT – LA

15:40 – 16:10 EDT – NY

03:40 – 04:10 CST – Beijing

21:40 – 22:10 CEST – Belgium


Recorded Oral Presentations – Track4 (5 minutes presentation each)

(1) Good Practices and A Strong Baseline for Traffic Anomaly Detection (paper, poster, slides, presentation)

Yuxiang Zhao; Wenhao Wu; Yue He; Yingying Li; Xiao Tan; Shifeng Chen

(2) Box-Level Tube Tracking and Refinement for Vehicles Anomaly Detection (paper, poster, slides, presentation)

Jie Wu; Xionghui Wang; Xuefeng Xiao; Yitong Wang

(3) Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing (paper, poster, slides, presentation)

Jingyuan Chen; Guanchen Ding; Yuchen Yang; Wenwei Han; Kangmin Xu; Tianyi Gao; Zhe Zhang; Wanping Ouyang; Hao Cai; Zhenzhong Chen

(4) An Efficient Approach for Anomaly Detection in Traffic Videos (paper, poster, slides, presentation)

Keval Doshi; Yasin Yilmaz

(5) A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Trees (presentation)

Armstrong Aboah; Maged Shoman; Vishal Mandal; Sayedomidreza Davami; Yaw Adu-Gyamfi; Anuj Sharma

13:10 – 14:00 PDT – LA

16:10 – 17:00 EDT – NY

04:10 – 05:00 CST – Beijing

22:10 – 23:00 CEST – Belgium


Recorded Oral Presentations – Track5 (5 minutes presentation each)

(1) Connecting Language and Vision for Natural Language-Based Vehicle Retrieval (paper, poster, slides, presentation)

Shuai Bai; Zhedong Zheng; Xiaohan Wang; Junyang Lin; Zhu Zhang; Chang Zhou; Hongxia Yang; Yi Yang

(2) DUN: Dual-path Temporal Matching Network for Natural Language-based Vehicle Retrieval (paper, poster, slides, presentation)

Ziruo Sun; Xinfang Liu; Xiaopeng Bi; Xiushan Nie; Yilong Yin

(3) Keyword-based Vehicle Retrieval (paper, poster, slides, presentation)

Eun-Ju Park; Hoyoung Kim; Seonghwan Jeong; Byungkon Kang; YoungMin Kwon

(4) Contrastive Learning for Natural Language-Based Vehicle Retrieval (paper, poster, slides, presentation)

Tam Minh Nguyen; Quang Huu Pham; Linh Bao Doan; Hoang Viet Trinh; Viet-Anh Nguyen

(5) Traffic Video Event Retrieval via Text Query using Vehicle Appearance and Motion Attributes (paper, poster, slides, presentation)

Tien-Phat Nguyen; Ba-Thinh Tran-Le; Xuan-Dang Thai; Tam V. Nguyen; Minh N. Do; Minh-Triet Tran

(6) TIED: A Cycle Consistent Encoder-Decoder Model for Text-to-Image Retrieval (paper, poster, slides, presentation)

Clint Sebastian; Raffaele Imbriaco; Panagiotis Meletis; Gijs Dubbelman; Egor Bondarev; Peter H.N. de With

(7) Towards Accurate Visual and Natural Languaged-Based Vehicle Retrieval Systems (paper, poster, slides, presentation)

Pirazh Khorramshahi; Sai Saketh Rambhatla; Rama Chellappa

(8) SBNet: Segmentation-based Network for Natural Language-based Vehicle Search (paper, poster, slides)

Sangrok Lee; Taekang Woo; Sang Hun Lee

(9) All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers (paper, poster, slides, presentation)

Carmelo Scribano; Davide Sapienza; Giorgia Franchini; Micaela Verucchi; Marko Bertogna

14:00 – 14:30 PDT – LA

17:00 – 17:30 EDT – NY

05:00 – 05:30 CST – Beijing

23:00 – 23:30 CEST – Belgium


Challenge Summary (workshop recording_part1, recording_part2)

14:30 – 15:00 PDT – LA

17:30 – 18:00 EDT – NY

05:30 – 06:00 CST – Beijing

23:30 – 00:00 CEST – Belgium



Title: The NIST PSCR Analytics Technical Challenge and Data: Building real-time AI technology to support emergency response where every second counts!

Speaker: John Garofolo​​​

15:00 – 15:30 PDT – LA

18:00 – 18:30 EDT – NY

06:00 – 06:30 CST – Beijing

00:00 – 00:30 CEST – Belgium


Panel Discussion on AI Ethics

Panel members: John Garofolo , Dave Ness, Anuj Sharma, Milind Naphade and Liang Zheng

15:30 – 16:30 PDT – LA

18:30 – 19:30 EDT – NY

06:30 – 07:30 CST – Beijing

00:30 – 01:30 CEST – Belgium


Open Discussions

16:30 – 17:00 PDT – LA

19:30 – 20:00 EDT – NY

07:30 – 08:00 CST – Beijing

01:30 – 02:00 CEST – Belgium


Challenge Awards Announcement

17:00 PDT – LA

20:00 EDT – NY

08:00 CST – Beijing

02:00 CEST – Belgium