Papers › Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

22 Jun 2021NeurIPS 2021 12arXiv:2106.11958archive 2025-07-28

Lei Ke, Xia Li, Martin Danelljan, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu

Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimension to address the association problem, while relying on single frame predictions for the segmentation mask itself. We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. PCAN first distills a space-time memory into a set of prototypes and then employs cross-attention to retrieve rich information from the past frames. To segment each object, PCAN adopts a prototypical appearance module to learn a set of contrastive foreground and background prototypes, which are then propagated over time. Extensive experiments demonstrate that PCAN outperforms current video instance tracking and segmentation competition winners on both Youtube-VIS and BDD100K datasets, and shows efficacy to both one-stage and two-stage segmentation frameworks. Code and video resources are available at http://vis.xyz/pub/pcan.

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="2106.11958")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: official repository: 5 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.

SysCV/pcan officialpytorchApache-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

5 samples harvested; 0 ran; 0 honoured the contract we drafted; 5 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.

5unverified

Licence: 0 of the 5 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 SysCV/pcan. “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.

cal_similarity SysCV/pcan/pcan/core/track/similarity.py official repository unverified Apache-2.0 (permissive) · ecbbdf2760634c6f · report
intersection_over_area SysCV/pcan/pcan/core/evaluation/mot.py official repository unverified Apache-2.0 (permissive) · 4cd14952230cdf84 · report
segtrack2result SysCV/pcan/pcan/core/track/transforms.py official repository unverified Apache-2.0 (permissive) · d58e5f0465880838 · report
track2result SysCV/pcan/pcan/core/track/transforms.py official repository unverified Apache-2.0 (permissive) · 8803773e1a105ac1 · report
xyxy2xywh SysCV/pcan/pcan/core/evaluation/mot.py official repository unverified Apache-2.0 (permissive) · 08df0b7800bb9cc2 · report

Tasks

Multi-Object Tracking and SegmentationMultiple Object Track and SegmentationMultiple Object TrackingObjectObject TrackingSegmentationVideo Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking and Segmentation BDD100K val PCAN mMOTSA 27.4 #3 of 8 Archive leaderboard report
Multi-Object Tracking and Segmentation BDD100K val QDTrack-mots-fix mMOTSA 23.5 #4 of 8 Archive leaderboard report
Multi-Object Tracking and Segmentation BDD100K val QDTrack-mots mMOTSA 22.5 #5 of 8 Archive leaderboard report
Multi-Object Tracking and Segmentation BDD100K val MaskTrackRCNN mMOTSA 12.3 #6 of 8 Archive leaderboard report
Multi-Object Tracking and Segmentation BDD100K val STEm-Seg mMOTSA 12.2 #7 of 8 Archive leaderboard report
Multi-Object Tracking and Segmentation BDD100K val SortIoU mMOTSA 10.3 #8 of 8 Archive leaderboard report
Multiple Object Track and Segmentation BDD100K val PCAN mMOTSA 27.4 #1 of 1 Archive leaderboard report
Video Instance Segmentation BDD100K val PCAN mMOTSA 27.4 #1 of 6 Archive leaderboard report
Video Instance Segmentation BDD100K val QDTrack-mots-fix mMOTSA 23.5 #2 of 6 Archive leaderboard report
Video Instance Segmentation BDD100K val QDTrack-mots mMOTSA 22.5 #3 of 6 Archive leaderboard report
Video Instance Segmentation BDD100K val MaskTrackRCNN mMOTSA 12.3 #4 of 6 Archive leaderboard report
Video Instance Segmentation BDD100K val STEm-Seg mMOTSA 12.2 #5 of 6 Archive leaderboard report
Video Instance Segmentation BDD100K val SortIoU mMOTSA 10.3 #6 of 6 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation PCAN(ResNet-50) AP50 54.9 #31 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation PCAN(ResNet-50) AP75 39.4 #31 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation PCAN(ResNet-50) AR1 36.3 #31 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation PCAN(ResNet-50) AR10 41.6 #31 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation PCAN(ResNet-50) mask AP 36.1 #31 of 44 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