Track 1: Video Object Segmentation
Leaderboard
Team Name | Overall | J_seen | J_unseen | F_seen | F_unseen | Ranking |
---|---|---|---|---|---|---|
wenhaowang | 0.856 (1) | 0.836 (1) | 0.811 (2) | 0.888 (1) | 0.889 (2) | 1 |
hkchengrex | 0.854 (2) | 0.828 (2) | 0.814 (1) | 0.883 (2) | 0.893 (1) | 2 |
qinghualiuyong | 0.842 (3) | 0.816 (4) | 0.799 (3) | 0.870 (4) | 0.881 (3) | 3 |
cncyww | 0.839 (4) | 0.823 (3) | 0.788 (6) | 0.874 (3) | 0.871 (5) | 4 |
cheng321284 | 0.836 (5) | 0.809 (6) | 0.798 (4) | 0.859 (6) | 0.877 (4) | 5 |
PixelKitty | 0.835 (6) | 0.814 (5) | 0.793 (5) | 0.866 (5) | 0.868 (6) | 6 |
Team Information
Team Name | Team Members | Organization | Technical Report |
---|---|---|---|
wenhaowang | Zongxin Yang [1,2], Jian Zhang [3], Wenhao Wang [1,4], Wenhua Han [3], Yue Yu [3], Yingying Li [3], Jian Wang [3], Yunchao Wei [4], Yifan Sun [1], Yi Yang [2] | [1] Baidu Research, [2] Zhejiang University, [3] Baidu Inc., [4] University of Technology Sydney | |
hkchengrex | Ho Kei Cheng [1,2], Yu-Wing Tai[3], Chi-Keung Tang[2] | [1] University of Illinois Urbana-Champaign, [2] The Hong Kong University of Science and Technology, [3] Kuaishou Technology | |
qinghualiuyong | Yong Liu[1], Ran Yu[1], Xinyuan Zhao[2], Yujiu Yang[1] | [1] Tsinghua Shenzhen International Graduate School, Tsinghua University, [2] Huawei Technologies | |
cncyww | Wangwang Yang[1], Zhengyi Lv[2], Jiangyu Liu[2], Di Huang[1] | [1] Beihang University, [2] Megvii Research | |
cheng321284 | Changhao Qiao [1], Haochen Wang [2], Cheng Chen [3], Yan Gao [4], Qimeng Wang [3] | [1] Harbin Institute of Technology, ShenZhen, [2] Beihang University, [3] Huazhong University of Science and Technology, [4] Institute of Computer Technology, Chinese Academy, [5] | |
PixelKitty | Zhixing Huang†, Junli Zha†, Fei Xie, Yuwei Zheng, Yuandong Zhong, Jinpeng Tang (†Equal contribution.) | Alibaba Group, Guangzhou, China |
Track 2: Video Instance Segmentation
Leaderboard
Team Name | mAP | AP50 | AP75 | AR1 | AR10 | Ranking |
---|---|---|---|---|---|---|
tuantng | 0.541 (1) | 0.742 (2) | 0.616 (1) | 0.433 (2) | 0.589 (2) | 1 |
eastonssy | 0.523 (2) | 0.767 (1) | 0.577 (2) | 0.439 (1) | 0.570 (3) | 2 |
vidit98 | 0.491 (3) | 0.681 (5) | 0.545 (3) | 0.410 (5) | 0.550 (4) | 3 |
linhj | 0.478 (4) | 0.693 (3) | 0.527 (5) | 0.422 (3) | 0.591 (1) | 4 |
hongsong.wang | 0.476 (5) | 0.684 (4) | 0.529 (4) | 0.414 (4) | 0.546 (5) | 5 |
gb7 | 0.473 (6) | 0.665 (6) | 0.511 (6) | 0.405 (6) | 0.516 (6) | 6 |
zfonemore | 0.461 (7) | 0.644 (7) | 0.510 (7) | 0.383 (7) | 0.506 (7) | 7 |
Suqi.lmh | 0.323 (8) | 0.488 (9) | 0.362 (8) | 0.302 (9) | 0.382 (8) | 8 |
qwe123 | 0.319 (9) | 0.515 (8) | 0.338 (9) | 0.312 (8) | 0.379 (9) | 9 |
SimoneRos | 0.121 (10) | 0.242 (10) | 0.103 (10) | 0.134 (10) | 0.153 (10) | 10 |
Team Information
Team Name | Team Members | Organization | Technical Report |
---|---|---|---|
tuantng | Thuy Nguyen, Tuan Tang, Nam Phan, Chuong Nguyen [1], Masayuki Yamazaki [2] | [1] CyberCore AI, [2] Toyota Motor Corporation | |
eastonssy | Shusheng Yang[1,2]*, Yuxin Fang[1]*, Xinggang Wang[1]†, Yu Li[2], Ying Shan[2], Bin Feng[1], Wenyu Liu[1]. (*Equal Contributions, †Corresponding Author.) | [1] School of EIC, Huazhong University of Science & Technology, [2] Applied Research Center (ARC), Tencent PCG. | |
vidit98 (PicsArt AI Research) | Vidit Goel, Jiachen Li, Shubhika Garg, Harsh Maheshwari, Humphrey Shi | PicsArt AI Research, Indian Institute of Technology Kharagpur, University of Oregon, University of Illinois at Urbana-Champaign | |
linhj | Huaijia Lin [1], Ruizheng Wu [1], Shu Liu [2], Jiangbo Lu [2], Jiaya Jia [1,2] | [1] The Chinese University of Hong Kong, [2] SmartMore | |
hongsong.wang | Hongsong Wang, Fang Zhao | Inception Institute of Artificial Intelligence | TXT |
gb7 | Gedas Bertasius, Lorenzo Torresani | Facebook AI | |
zfonemore | Feng Zhu [1,2], Zongxin Yang [1,2], Wu Yu [1,2], Wenguan Wang [3], Yunchao Wei [1], Yi Yang [1,2] | [1] University of Technology Sydney, [2] Baidu Research, [3] ETH Zurich | |
Suqi.lmh | Minghan Li | The Hong Kong Polytechnic University | |
qwe123 | Wenbo Li, Jianzhen Tang, Yujia Xie [1], Jian Lan [2] | [1] Chengdu Huapohen Technology Co., Ltd., [2] Shanghai University | |
SimoneRos | Simone Rossetti, Temirlan Zharbynbek and Fiora Pirri (prof) | Alcor LAB at Sapienza |
Track 3: Referring Video Object Segmentation
Leaderboard
Team Name | Overall | J | F | Ranking |
---|---|---|---|---|
leonnnop | 0.607 (1) | 0.594 (1) | 0.620 (1) | 1 |
nowherespyfly | 0.494 (2) | 0.484 (2) | 0.503 (2) | 2 |
Merci1 | 0.412 (3) | 0.406 (3) | 0.418 (3) | 3 |
Team Information
Team Name | Team Members | Organization | Technical Report |
---|---|---|---|
leonnnop | Chen Liang [1,3], Yu Wu [3,4], Tianfei Zhou [2], Wenguan Wang [2], Zongxin Yang [3,4], Yunchao Wei [4], Yi Yang [1] | [1] Zhejiang University, [2] ETH Zurich, [3] Baidu Research, [4] University of Technology Sydney | |
nowherespyfly | Zihan Ding [1], Tianrui Hui [2], Shaofei Huang [2], Si Liu [1], Xuan Luo [3], Junshi Huang [3], Xiaoming Wei [3] | [1] Institute of Artificial Intelligence, Beihang University, [2] Institute of Information Engineering, Chinese Academy of Sciences, [3] Meituan | |
Merci1 | Dezhuang Li, Ruoqi Li, Shu Yang, Zhenyu Chen, Lu Zhang, Jinqing Qi, Yifan Wang, Huchuan Lu | IIAU-LAB, Faculty of Electronic information and Electrical Engineering, Dalian University of Technology |