paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
Action Recognition
벤치마크
Action Recognition on
RareAct
6개 결과 ·
⬇ CSV
·
JSON
mWAP
30.5
38.08
45.65
53.22
60.8
2019-12
2026-09
HT100M S3D — 30.5 (2019-12-13)
HT100M S3D — 30.5 (2019-12-13)
CLIP — 40.7 (2021-02-26)
CLIP — 40.7 (2021-02-26)
🦩 Flamingo — 60.8 (2022-04-29)
🦩 Flamingo — 60.8 (2022-04-29)
HT100M S3D — 30.5 (2019-12-13)
CLIP — 40.7 (2021-02-26)
🦩 Flamingo — 60.8 (2022-04-29)
2019-12-13 — HT100M S3D: mWAP 30.5
2021-02-26 — CLIP: mWAP 40.7
2022-04-29 — 🦩 Flamingo: mWAP 60.8
Rank
Model
mWAP
Paper
Code
Year
1
🦩 Flamingo
60.8
Flamingo: a Visual Language Model for Few-Shot Learning
mlfoundations/open_flamingo
·
lucidrains/flamingo-pytorch
·
unispac/visual-adversarial-examples-jailbreak-large-language-models
·
+2
2022
2
CLIP
40.7
Learning Transferable Visual Models From Natural Language Supervision
openai/CLIP
·
mlfoundations/open_clip
·
towhee-io/towhee
·
+79
2021
3
HT100M S3D
30.5
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
antoine77340/MIL-NCE_HowTo100M
·
antoine77340/milnce_howto100m
·
antoine77340/S3D_HowTo100M
·
+1
2019
4
🦩 Flamingo
60.8
Flamingo: a Visual Language Model for Few-Shot Learning
mlfoundations/open_flamingo
·
lucidrains/flamingo-pytorch
·
unispac/visual-adversarial-examples-jailbreak-large-language-models
·
+2
2022
5
CLIP
40.7
Learning Transferable Visual Models From Natural Language Supervision
openai/CLIP
·
mlfoundations/open_clip
·
towhee-io/towhee
·
+79
2021
6
HT100M S3D
30.5
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
antoine77340/MIL-NCE_HowTo100M
·
antoine77340/milnce_howto100m
·
antoine77340/S3D_HowTo100M
·
+1
2019
1–6 / 6
페이지당
10
20
50
100