Papers › Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer

Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer

19 Apr 2022CVPR 2022 1arXiv:2204.08680archive 2025-07-28

Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Ping Luo, Wanli Ouyang, Xiaogang Wang

Vision transformers have achieved great successes in many computer vision tasks. Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token. However, not all regions are equally important in human-centric vision tasks, e.g., the human body needs a fine representation with many tokens, while the image background can be modeled by a few tokens. To address this problem, we propose a novel Vision Transformer, called Token Clustering Transformer (TCFormer), which merges tokens by progressive clustering, where the tokens can be merged from different locations with flexible shapes and sizes. The tokens in TCFormer can not only focus on important areas but also adjust the token shapes to fit the semantic concept and adopt a fine resolution for regions containing critical details, which is beneficial to capturing detailed information. Extensive experiments show that TCFormer consistently outperforms its counterparts on different challenging human-centric tasks and datasets, including whole-body pose estimation on COCO-WholeBody and 3D human mesh reconstruction on 3DPW. Code is available at https://github.com/zengwang430521/TCFormer.git

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2204.08680")

Code

Syntology Ran 6 of 7 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zengwang430521/tcformer officialmentioned in papermentioned on GitHubpytorchApache-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

7 samples harvested; 6 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

6ran
1unverified

Licence: 0 of the 7 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 zengwang430521/tcformer. “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.

drop_block_2d zengwang430521/tcformer/tcformer_module/transformer_utils.py official repository ran Apache-2.0 (permissive) · e3c853a7511a411a · report
drop_block_fast_2d zengwang430521/tcformer/tcformer_module/transformer_utils.py official repository ran Apache-2.0 (permissive) · 4162565de6ffa9da · report
drop_path zengwang430521/tcformer/tcformer_module/transformer_utils.py official repository ran fingerprinted Apache-2.0 (permissive) · 9d3c18b6f3ac3dc1 · report
flops_to_string zengwang430521/tcformer/tcformer_module/custom_flops_counter.py official repository ran Apache-2.0 (permissive) · 428c8cc732ef3657 · report
get_grid_index zengwang430521/tcformer/tcformer_module/tcformer_utils.py official repository ran Apache-2.0 (permissive) · 306896b703835e2c · report
params_to_string zengwang430521/tcformer/tcformer_module/custom_flops_counter.py official repository ran Apache-2.0 (permissive) · e0247439ad10578e · report
build_transform zengwang430521/tcformer/classification/datasets.py official repository unverified Apache-2.0 (permissive) · 3bc74137ab36aa79 · report

Tasks

2D Human Pose Estimation3D Human Pose EstimationAllClusteringPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody TCFormer WB 64.2 #5 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody TCFormer body 71.8 #5 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody TCFormer face 79.0 #5 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody TCFormer foot 74.4 #5 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody TCFormer hand 61.4 #5 of 15 Archive leaderboard report
3D Human Pose Estimation 3DPW TCFormer MPJPE 80.6 #71 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCFormer PA-MPJPE 49.3 #71 of 119 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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