Papers › Detection in Crowded Scenes: One Proposal, Multiple Predictions

Detection in Crowded Scenes: One Proposal, Multiple Predictions

20 Mar 2020CVPR 2020 6arXiv:2003.09163archive 2025-07-28

Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, Jian Sun

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9\% AP gains on challenging CrowdHuman dataset and 1.0\% MR⁻² improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at https://github.com/megvii-model/CrowdDetection.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.09163")

Code

Syntology Ran 0 of 10 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run.

By repository: official repository: 4 samples from 1 repository, 0 ran; community (archive-listed): 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

megvii-model/CrowdDetection officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
Purkialo/CrowdDet mentioned on GitHubpytorchMIT report
tusimple/simpledet mentioned on GitHubmxnetApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

10unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

clip_boxes_opr megvii-model/CrowdDetection/lib/det_opr/bbox_opr.py official repository unverified Apache-2.0 (permissive) · 60ee506bd75880e6 · report
common_process megvii-model/CrowdDetection/evaluate/compute_JI.py official repository unverified Apache-2.0 (permissive) · 592f2e1c9759dfd8 · report
filter_boxes_opr megvii-model/CrowdDetection/lib/det_opr/bbox_opr.py official repository unverified Apache-2.0 (permissive) · 934447ae71c62cee · report
gather megvii-model/CrowdDetection/evaluate/compute_JI.py official repository unverified Apache-2.0 (permissive) · fabe07d7d0c3a52c · report
batch_clip_proposals Purkialo/CrowdDet/lib/det_oprs/bbox_opr.py community (archive-listed) unverified MIT (permissive) · 2727801e3134f32b · report
compute_APMR Purkialo/CrowdDet/lib/evaluate/compute_APMR.py community (archive-listed) unverified MIT (permissive) · 6924df036c046ae9 · report
focal_loss Purkialo/CrowdDet/lib/det_oprs/loss_opr.py community (archive-listed) unverified MIT (permissive) · f2466bea04ccb88b · report
get_padded_tensor Purkialo/CrowdDet/lib/det_oprs/utils.py community (archive-listed) unverified MIT (permissive) · 65810c1b0f4fb989 · report
smooth_l1_loss Purkialo/CrowdDet/lib/det_oprs/loss_opr.py community (archive-listed) unverified MIT (permissive) · 80e2e1c046be957c · report
subsample_masks Purkialo/CrowdDet/lib/det_oprs/fpn_roi_target.py community (archive-listed) unverified MIT (permissive) · d5547caab3c5568f · report

Tasks

Object DetectionPedestrian Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) CrowdDet AP 90.7 #11 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) CrowdDet mMR 41.4 #11 of 19 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus CrowdDet ALL (miss rate) 35.90 #2 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus CrowdDet HO (miss rate) 66.38 #2 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus CrowdDet R (miss rate) 25.73 #2 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus CrowdDet R+HO (miss rate) 33.63 #2 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus CrowdDet RS (miss rate) - #2 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic CrowdDet ALL (miss rate) 36.94 #3 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic CrowdDet HO (miss rate) 61.22 #3 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic CrowdDet R (miss rate) 20.82 #3 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic CrowdDet R+HO (miss rate) 25.28 #3 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic CrowdDet RS (miss rate) - #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections