Skip to content

This is the official implementation of the CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)

active 2023-08-152026-04-07 (UTC)

Complete coverage26,539 / 26,539 hourly files (100%) · 2 absent upstream2023-08-152026-08-24 (UTC)
Events
358
Pushes
0
Pull requests
0
Issues
52
Stars
235
Forks
27

Activity over time

Daily event counts in the loaded window

Line chart, 967 days from 2023-08-15 to 2026-04-07. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 52 total, peak 4 in a day. Comments: 44 total, peak 4 in a day. Stars: 235 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#26ll86572025-08-28 09:57
    onnx
  • Issue#55navidTerraNova2025-04-17 14:50
    The repository Doesn't work anymore. too old
  • Issue comment#54zzy75692025-03-27 08:16
    无法下载预训练权重文件,zoo无法访问
  • Issue#54zzy75692025-03-26 18:37
    无法下载预训练权重文件,zoo无法访问
  • Issue comment#38Zdmai2025-03-17 07:20
    Tokens to be integers
  • Issue#52Zdmai2025-03-15 20:36
    can't download the pretrain weight
  • Issue#53Zdmai2025-03-15 20:36
    can't download the pretrain weight
  • Issue#51Zdmai2025-03-15 20:36
    can't download the pretrain weight
  • Issue#53Zdmai2025-03-11 13:01
    can't download the pretrain weight
  • Issue#52Zdmai2025-03-11 13:01
    can't download the pretrain weight
  • Issue#42Tommy-Hsu2024-12-12 13:19
    Loss of keypoints or joints wasn't stable
  • Issue#50Tommy-Hsu2024-12-12 13:03
    class head for different backbone
  • Issue comment#30Tommy-Hsu2024-12-07 09:43
    When training a classifier, don't freeze the weights of the decoder and codebook?
  • Issue comment#30epleone2024-12-06 03:20
    When training a classifier, don't freeze the weights of the decoder and codebook?
  • Issue#49Ben-Park2024-11-25 01:46
    [Tip] Error in learning Tokenizer
  • Issue#48kristinbranson2024-11-21 15:25
    environment requirement versions
  • Issue#45gowhare2024-11-19 06:41
    KeyError: 'area'
  • Issue#47gowhare2024-11-19 06:40
    crowdpose测试
  • Issue#46bit-scientist2024-11-19 03:18
    Can training without image guidance help reducing false alarms as well
  • Issue#45gowhare2024-11-19 01:37
    KeyError: 'area'
  • Issue#44gowhare2024-11-14 03:17
    > Hi, thanks for your insightful work. I was able to reproduce the paper's results on Coco dataset, and I am attempting to reproduce the results with H36m. However, I do not find any sample code nor instructions on that. Would you please help and share code or instruct on how you conducted the experiments on h36m?
  • Issue#43Bavesh-B2024-09-10 21:25
    AttributeError: 'list' object has no attribute 'dataset_info'
  • Issue#42Tommy-Hsu2024-08-20 08:40
    Loss of keypoints or joints wasn't stable
  • Issue comment#30Tommy-Hsu2024-08-20 07:21
    When training a classifier, don't freeze the weights of the decoder and codebook?
  • Issue comment#11Kun-Ming2024-08-19 21:44
    How to inference 3D pose?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 235 stars here means stars gained during the window, not the repo's star count.