Overview

We offer a benchmark suite together with an evaluation server, such that authors can upload their results and get a ranking. We offer a Dataset that contains 38280 pictures, including 28280 images for training set, 5000 images for validation set and 5000 images for test set. If you would like to submit your results, please register, login, and follow the instructions on our submission page.

Note: We only display the highest submission of each person.

Multi-Person Human Parsing Task

Metrics

For this task, we use two metrics for multi-human parsing evaluation. Mean IoU(%) for semantic part segmentation, reported by the FCN paper. And APr for instance-level human parsing, first introduced in Simultaneous Detection and Segmentation. The details show APr at various IoU thresholds.

User Id Method Mean IoU Mean APr Details Abbreviation Submit Time
377 99898989 48.91 27.88 Details Abbreviation 2019-05-28 17:41:04
381 test5 58.75 36.99 Details Abbreviation 2019-03-31 03:27:54
301 JD_BUPT 65.47 54.05 Details Abbreviation 2019-06-02 11:00:00
415 49.49 33.82 Details Abbreviation 2019-04-29 15:48:46
394 BAIDU-UTS 69.10 55.01 Details Abbreviation 2019-06-02 11:00:00
322 20_11w 53.07 36.46 Details Abbreviation 2019-04-28 10:01:00
236 CASIA_CEIEC 61.86 41.17 Details Abbreviation 2019-05-31 14:17:24
464 try 3 48.91 27.88 Details Abbreviation 2019-09-12 16:49:05