Papers › Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

14 Aug 2023ICCV 2023 1arXiv:2308.07313archive 2025-07-28

Huan Liu, Qiang Chen, Zichang Tan, Jiang-Jiang Liu, Jian Wang, Xiangbo Su, Xiaolong Li, Kun Yao, Junyu Han, Errui Ding, Yao Zhao, Jingdong Wang

In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR. We present a simple yet effective transformer approach, named Group Pose. We simply regard K-keypoint pose estimation as predicting a set of N×K keypoint positions, each from a keypoint query, as well as representing each pose with an instance query for scoring N pose predictions. Motivated by the intuition that the interaction, among across-instance queries of different types, is not directly helpful, we make a simple modification to decoder self-attention. We replace single self-attention over all the N×(K+1) queries with two subsequent group self-attentions: (i) N within-instance self-attention, with each over K keypoint queries and one instance query, and (ii) (K+1) same-type across-instance self-attention, each over N queries of the same type. The resulting decoder removes the interaction among across-instance type-different queries, easing the optimization and thus improving the performance. Experimental results on MS COCO and CrowdPose show that our approach without human box supervision is superior to previous methods with complex decoders, and even is slightly better than ED-Pose that uses human box supervision. Paddle (https://github.com/Michel-liu/GroupPose-Paddle) and PyTorch (https://github.com/Michel-liu/GroupPose) code are available.

PaperPDFConference PDFCodeCode 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 22 code samples harvested from 2 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 2 repositories, 21 ran (13 with no instrument failure; 8 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 21 samples that ran has no recorded date.

michel-liu/grouppose officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
michel-liu/grouppose-paddle officialmentioned in papermentioned on GitHubpaddleApache-2.0Syntology: 16 samples, 15 ran (4 instrument-failed) · 1 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

22 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 1 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
3ran; the contract check could not run
10ran
1unverified

Licence: 1 of the 22 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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.

michel-liu/grouppose official repository 6 samples, 6 ran (4 instrument-failed) · 0 unverified
build_matcher in 13 papers models/grouppose/matcher.py ran Apache-2.0 (permissive) · b470cc20ddf04258 · report fixture: signature args:ArgsConfig/0/? · returned HungarianMatcher · level recorded 2026-09-24
gen_encoder_output_proposals in 10 papers models/grouppose/utils.py ran Apache-2.0 (permissive) · e3b2768e6a9c1cb5 · report fixture: signature memory:Tensor/3/float, memory_padding_mask:Tensor/2/bool, spatial_shapes:Tensor/2/int, learnedwh:Tensor/1/float · returned tuple · level recorded 2026-09-24
gen_sineembed_for_position in 29 papers models/grouppose/utils.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 4c82654ae6131ecc · report fixture: signature pos_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/grouppose/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/grouppose/backbones/swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · f9fd6241d935f07b · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/grouppose/backbones/swin_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · fb32094c6dbece71 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
michel-liu/grouppose-paddle official repository 16 samples, 15 ran (4 instrument-failed) · 1 unverified
dump_value in 5 papers ppdet/core/workspace.py ran · our draft was wrong Apache-2.0 (permissive) · 891281774f8942bd · report fixture: signature value:dict/0/? · returned str · level recorded 2026-09-24
generate_scale deploy/auto_compression/paddle_inference_eval.py ran Apache-2.0 (permissive) · c115c6190dd6b6d3 · report fixture: signature im:ndarray/3/int, target_shape:tuple/1/int, keep_ratio:bool/0/bool · returned tuple · level recorded 2026-09-24
get_affine_mat_kernel ppdet/modeling/keypoint_utils.py ran Apache-2.0 (permissive) · e9ea8d6169dd3c5a · report fixture: signature h:int/0/int, w:int/0/int, s:int/0/int, inv:bool/0/bool · returned tuple · level recorded 2026-09-24
get_affine_transform in 11 papers ppdet/modeling/keypoint_utils.py ran Apache-2.0 (permissive) · 2fc1e1b3d4511e08 · report fixture: signature center:ndarray/1/float, input_size:ndarray/1/float, rot:float/0/float, output_size:ndarray/1/float, shift:tuple/1/float, inv:bool/0/bool · returned ndarray · level recorded 2026-09-24
get_color_map_list deploy/auto_compression/paddle_inference_eval.py ran fingerprinted Apache-2.0 (permissive) · 6a8c58548a03d3a2 · report fixture: signature num_classes:int/0/int · returned list · level recorded 2026-09-24
get_warp_matrix ppdet/modeling/keypoint_utils.py ran Apache-2.0 (permissive) · 75f2a6d60178f80d · report fixture: signature theta:float/0/float, size_input:ndarray/1/float, size_dst:ndarray/1/float, size_target:ndarray/1/float · returned ndarray · level recorded 2026-09-24
get_weights_url ppdet/model_zoo/model_zoo.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e241ea7c12e86306 · report fixture: signature model_name:str/0/str · returned str · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
ppdet/modeling/ops.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9910e2fc297f8665 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
image_preprocess in 7 papers deploy/auto_compression/paddle_inference_eval.py ran Apache-2.0 (permissive) · 145a8b9a0a3f9d79 · report fixture: signature img_path:str/0/str, target_shape:tuple/1/int · returned tuple · level recorded 2026-09-24
load_config in 389 papers ppdet/core/workspace.py ran · our draft was wrong Apache-2.0 (permissive) · 7b71ca54a440c129 · report fixture: signature file_path:str/0/str · returned AttrDict · level recorded 2026-09-24
multiclass_nms in 7 papers ppdet/modeling/post_process.py ran Apache-2.0 (permissive) · 0cf81b30bc14579c · report fixture: signature bboxs:ndarray/2/float, num_classes:int/0/int, match_threshold:float/0/float, match_metric:str/0/str · returned list · level recorded 2026-09-24
nms in 65 papers ppdet/modeling/post_process.py ran Apache-2.0 (permissive) · c54757be76d21549 · report fixture: signature dets:ndarray/2/float, match_threshold:float/0/float, match_metric:str/0/str · returned ndarray · level recorded 2026-09-24
norm_angle ppdet/modeling/rbox_utils.py ran · violated contract Apache-2.0 (permissive) · 6c7db6948ecffd97 · report fixture: signature angle:float/0/float, range:list/1/float · returned float · level recorded 2026-09-24
poly2rbox_le135_np ppdet/modeling/rbox_utils.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 5b37cc101c76cbd0 · report fixture: signature poly:list/1/float · returned list · level recorded 2026-09-24
poly2rbox_oc_np ppdet/modeling/rbox_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 155145950e1115ca · report fixture: signature poly:list/1/float · returned list · level recorded 2026-09-24
dict_merge in 5 papers ppdet/core/workspace.py unverified Apache-2.0 (permissive) · 553169f24c2e1789 · report

Tasks

DecoderHuman DetectionMulti-Person Pose EstimationPose Estimation

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