Papers › Joint-task Self-supervised Learning for Temporal Correspondence

Joint-task Self-supervised Learning for Temporal Correspondence

26 Sep 2019NeurIPS 2019 12arXiv:1909.11895archive 2025-07-28

Xueting Li, Sifei Liu, Shalini De Mello, Xiaolong Wang, Jan Kautz, Ming-Hsuan Yang

This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions \emph{and} establishing fine-grained pixel-level associations between consecutive video frames. We exploit the synergy between both tasks through a shared inter-frame affinity matrix, which simultaneously models transitions between video frames at both the region- and pixel-levels. While region-level localization helps reduce ambiguities in fine-grained matching by narrowing down search regions; fine-grained matching provides bottom-up features to facilitate region-level localization. Our method outperforms the state-of-the-art self-supervised methods on a variety of visual correspondence tasks, including video-object and part-segmentation propagation, keypoint tracking, and object tracking. Our self-supervised method even surpasses the fully-supervised affinity feature representation obtained from a ResNet-18 pre-trained on the ImageNet.

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="1909.11895")

Code

Syntology Ran 4 of 23 code samples harvested from 1 repository linked to this paper; 19 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 23 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Liusifei/UVC officialpytorchMIT report
pacifinapacific/PixelFlow mentioned on GitHubpytorch 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

23 samples harvested; 4 ran; 1 honoured the contract we drafted; 19 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.

1ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
19unverified

Licence: 0 of the 23 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 Liusifei/UVC. “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.

conv1x1 Liusifei/UVC/libs/resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 Liusifei/UVC/libs/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
fast_hist Liusifei/UVC/eval_vip.py official repository ran · fixture could not drive it MIT (permissive) · d86fb168246b16a4 · report
featureL2Norm Liusifei/UVC/libs/net_utils.py official repository ran · honoured contract fingerprinted MIT (permissive) · cf9656ffec66503c · report
adjust_learning_rate Liusifei/UVC/track_match_v1.py official repository unverified MIT (permissive) · efe9d4fd3e733289 · report
aff2coord Liusifei/UVC/libs/concentration_loss.py official repository unverified MIT (permissive) · 9058715f5ac3cb5b · report
compute_hist Liusifei/UVC/eval_vip.py official repository unverified MIT (permissive) · 384eac2f5e92af52 · report
coords2bbox Liusifei/UVC/model.py official repository unverified MIT (permissive) · c3e082f966f8d659 · report
create_flat_grid Liusifei/UVC/model.py official repository unverified MIT (permissive) · c032af918144806e · report
create_grid Liusifei/UVC/libs/concentration_loss.py official repository unverified MIT (permissive) · 58402808d405db23 · report
create_grid Liusifei/UVC/libs/track_utils.py official repository unverified MIT (permissive) · 2bfe1a16c66739f6 · report
draw_bbox Liusifei/UVC/libs/train_utils.py official repository unverified MIT (permissive) · a5d852d21a97fde4 · report
framepair_loader Liusifei/UVC/libs/loader.py official repository unverified MIT (permissive) · e15375d29905159e · report
resnet18 Liusifei/UVC/libs/resnet.py official repository unverified MIT (permissive) · 1ccbb405b8feeb4f · report
sample_patch Liusifei/UVC/libs/train_utils.py official repository unverified MIT (permissive) · fcd7eaa2c70cfcd8 · report
seg2bbox_v2 Liusifei/UVC/libs/track_utils.py official repository unverified MIT (permissive) · a336a612bbbc899a · report
switch_L1_thr Liusifei/UVC/libs/loss.py official repository unverified MIT (permissive) · 13a19c9c06357b8b · report
to_one_hot Liusifei/UVC/libs/track_utils.py official repository unverified MIT (permissive) · 64adabd58edb62ca · report
transform Liusifei/UVC/model.py official repository unverified MIT (permissive) · 98d9c87973a0354e · report
video_frame_counter Liusifei/UVC/libs/loader.py official repository unverified MIT (permissive) · bfd0529a5407cf64 · report
video_loader Liusifei/UVC/libs/loader.py official repository unverified MIT (permissive) · 01111e0ea262be80 · report
weight_L1 Liusifei/UVC/libs/loss.py official repository unverified MIT (permissive) · 9d2097efd0543d8a · report
weightsingle_L1 Liusifei/UVC/libs/loss.py official repository unverified MIT (permissive) · facf9894c353245d · report

Tasks

Object TrackingSelf-Supervised LearningSemi-Supervised Video Object SegmentationUnsupervised Video Object Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) UVC F-measure (Mean) 61.3 #74 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) UVC F-measure (Recall) 69.8 #74 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) UVC J&F 59.5 #74 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) UVC Jaccard (Mean) 57.7 #74 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) UVC Jaccard (Recall) 68.3 #74 of 81 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