Skip to content

[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition

active 2023-09-012025-10-18 (UTC)

Partial coverage20,547 / 26,300 hourly files (78%) · 2 absent upstream · 5,750 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
48
Pushes
0
Pull requests
0
Issues
14
Stars
18
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 779 days from 2023-09-01 to 2025-10-18. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 5 in a day. Comments: 12 total, peak 4 in a day. Stars: 18 total, peak 2 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

ContributorContributionsPushesPRsComments
Anirudh25712006
M778277004
caidhome2002
YeonYeonni2000
Dev-ori1000
lzjjia1000
CS-FantaC1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#41Anirudh2572025-07-08 04:34
    question about dataset setting
  • Issue#41Anirudh2572025-07-08 04:34
    question about dataset setting
  • Issue#42Dev-ori2025-02-06 03:48
    Question about the episode training
  • Issue#41lzjjia2025-01-18 13:05
    question about dataset setting
  • Issue#35Anirudh2572024-05-25 22:41
    Training environment issues
  • Issue comment#34Anirudh2572024-05-25 22:41
    Why did the target image change to 40 x 3 x 224 x 224 during training?
  • Issue#34Anirudh2572024-05-25 22:41
    Why did the target image change to 40 x 3 x 224 x 224 during training?
  • Issue comment#36Anirudh2572024-05-25 22:40
    Inconsistent dataset catalog structure from official UCF101
  • Issue#36Anirudh2572024-05-25 22:40
    Inconsistent dataset catalog structure from official UCF101
  • Issue#38Anirudh2572024-05-25 22:39
    ValueError: not enough values to unpack (expected 3, got 0)
  • Issue comment#38Anirudh2572024-05-25 22:39
    ValueError: not enough values to unpack (expected 3, got 0)
  • Issue#39Anirudh2572024-05-25 22:38
    Questions about validation sets
  • Issue comment#39Anirudh2572024-05-25 22:38
    Questions about validation sets
  • Issue#40YeonYeonni2024-05-20 04:11
    Preprocessing about UCF 101
  • Issue#40YeonYeonni2024-05-14 06:27
    Preprocessing about UCF 101
  • Issue comment#38M778272024-05-08 04:46
    ValueError: not enough values to unpack (expected 3, got 0)
  • Issue#39M778272024-05-08 04:45
    Questions about validation sets
  • Issue#36CS-FantaC2024-04-20 08:04
    Inconsistent dataset catalog structure from official UCF101
  • Issue#35M778272024-04-20 03:35
    Training environment issues
  • Issue comment#7M778272024-04-20 02:49
    There is a gap with the report in hmdb
  • Issue comment#21M778272024-04-20 02:45
    Accuracy issues
  • Issue comment#27Anirudh2572024-04-11 05:56
    Accuracy recurrence issues
  • Issue comment#27M778272024-04-11 02:09
    Accuracy recurrence issues
  • Issue#34M778272024-03-20 01:54
    Why did the target image change to 40 x 3 x 224 x 224 during training?
  • Issue comment#13caidhome2023-10-07 02:04
    Question about 1-shot

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 18 stars here means stars gained during the window, not the repo's star count.