Papers › Learning a Neural Solver for Multiple Object Tracking

Learning a Neural Solver for Multiple Object Tracking

16 Dec 2019arXiv:1912.07515archive 2025-07-28

Guillem Brasó, Laura Leal-Taixé

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such structured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT, and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. Our code is available at https://bit.ly/motsolv .

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 2 repositories, 16 ran (11 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dvl-tum/mot_neural_solver mentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (2 instrument-failed) · 2 unverified report
ocetintas/mpntrackseg mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (3 instrument-failed) · 2 unverified 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

20 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
9ran
4unverified

Licence: 0 of the 20 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

dvl-tum/mot_neural_solver community (archive-listed) 11 samples, 9 ran (2 instrument-failed) · 2 unverified
conv1x1 in 691 papers src/mot_neural_solver/models/resnet.py ran · our draft was wrong MIT (permissive) · 158bf4c3a5f11f04 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers src/mot_neural_solver/models/resnet.py ran · our draft was wrong MIT (permissive) · 29df79c9fdb0cee8 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
fast_compute_class_metric src/mot_neural_solver/utils/evaluation.py ran MIT (permissive) · cc0fc0becaa56966 · report fixture: signature test_preds:Tensor/1/int, test_sols:Tensor/1/int, class_metrics:tuple/1/str · returned dict · level recorded 2026-09-24
get_knn_mask src/mot_neural_solver/utils/graph.py ran MIT (permissive) · a94a431843c7a13d · report fixture: signature pwise_dist:Tensor/1/float, edge_ixs:Tensor/2/int, num_nodes:int/0/int, top_k_nns:int/0/int, use_cuda:bool/0/bool, reciprocal_k_nns:bool/0/bool, symmetric_edges:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_run_str src/mot_neural_solver/utils/misc.py ran MIT (permissive) · c49058482b5bb7d3 · report fixture: signature run_id:str/0/str, cross_val_split:NoneType/0/?, add_date:bool/0/bool · returned str · level recorded 2026-09-24
get_time_valid_conn_ixs src/mot_neural_solver/utils/graph.py ran MIT (permissive) · ae5092810a565f70 · report fixture: signature frame_num:Tensor/1/int, max_frame_dist:int/0/int, return_undirected:bool/0/bool, use_cuda:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_time_valid_conn_ixs_old src/mot_neural_solver/utils/graph.py ran MIT (permissive) · 30814309bf2c67a4 · report fixture: signature frame_num:Tensor/1/int, max_frame_dist:int/0/int, use_cuda:bool/0/bool, return_undirected:bool/0/bool · returned Tensor · level recorded 2026-09-24
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
src/mot_neural_solver/utils/iou.py ran fingerprinted MIT (permissive) · 6d5874069afb5da1 · report fixture: signature boxA:ndarray/2/float, boxB:ndarray/2/float · returned ndarray · level recorded 2026-09-24
load_pickle in 115 papers src/mot_neural_solver/utils/misc.py ran MIT (permissive) · 077d777092baa347 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
iou_pairs src/mot_neural_solver/utils/iou.py unverified MIT (permissive) · 0816e9deea80e29e · report
resnet18 in 432 papers src/mot_neural_solver/models/resnet.py unverified MIT (permissive) · 132de39f1f8d09d3 · report
ocetintas/mpntrackseg community (archive-listed) 9 samples, 7 ran (3 instrument-failed) · 2 unverified
geometric_mean in 8 papers TrackEval/trackeval/plotting.py ran · violated contract fingerprinted MIT (permissive) · 06d2be4ac9d0e95b · report fixture: signature x:ndarray/1/float, y:ndarray/1/float · returned ndarray · level recorded 2026-09-26
init_config in 12 papers TrackEval/trackeval/utils.py ran MIT (permissive) · 0ce058e665602da2 · report fixture: signature config:dict/0/?, default_config:dict/0/?, name:str/0/str · returned dict · level recorded 2026-09-24
jaccard in 33 papers TrackEval/trackeval/plotting.py ran · honoured contract fingerprinted MIT (permissive) · 00c662d6d9709fe4 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-26
load_multiple_tracker_summaries in 7 papers TrackEval/trackeval/plotting.py ran · our draft was wrong MIT (permissive) · e9f7b2829ca9731b · report fixture: signature tracker_folder:str/0/str, tracker_list:list/1/str, cls:str/0/str · returned dict · level recorded 2026-09-26
run_metrics MOTChallengeEvalKit/src/MOTChallengeEvalKit/Evaluator.py ran MIT (permissive) · 3cf91b63ac86aee7 · report fixture: signature metricObject:MockMetricObject/0/?, args:dict/0/? · returned MockMetricObject · level recorded 2026-09-24
time in 9 papers TrackEval/trackeval/_timing.py ran · our draft was wrong MIT (permissive) · df1bd31f4da1bed6 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-26
update_config in 54 papers TrackEval/trackeval/utils.py ran · our draft was wrong MIT (permissive) · 5ef3f617efb9ddc4 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
resnet18 in 432 papers src/mot_neural_solver/models/resnet.py unverified MIT (permissive) · 568db0eea3d5a93a · report
validate_metrics_list in 5 papers TrackEval/trackeval/utils.py unverified MIT (permissive) · 9792bf1150d36891 · report

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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