paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
image-sentence alignment
벤치마크
image-sentence alignment on VALSE action replacement
14개 결과 ·
⬇ CSV
·
JSON
pairwise accuracy
49.2
55.8
62.4
69
75.6
2021-12
2026-09
CLIP — 75.6 (2021-12-14)
ViLBERT — 70.7 (2021-12-14)
GPT2 — 66.8 (2021-12-14)
ViLBERT 12-in-1 — 65.9 (2021-12-14)
GPT1 — 65.4 (2021-12-14)
LXMERT — 54.8 (2021-12-14)
VisualBERT — 49.2 (2021-12-14)
CLIP — 75.6 (2021-12-14)
ViLBERT — 70.7 (2021-12-14)
GPT2 — 66.8 (2021-12-14)
ViLBERT 12-in-1 — 65.9 (2021-12-14)
GPT1 — 65.4 (2021-12-14)
LXMERT — 54.8 (2021-12-14)
VisualBERT — 49.2 (2021-12-14)
CLIP — 75.6 (2021-12-14)
2021-12-14 — CLIP: pairwise accuracy 75.6
Rank
Model
pairwise accuracy
Accuracy (%)
Paper
Code
Year
1
CLIP
75.6
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
2
ViLBERT
70.7
52.6
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
3
GPT2
66.8
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
4
ViLBERT 12-in-1
65.9
57.3
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
5
GPT1
65.4
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
6
LXMERT
54.8
51.1
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
7
VisualBERT
49.2
48.8
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
8
CLIP
75.6
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
9
ViLBERT
70.7
52.6
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
10
GPT2
66.8
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
11
ViLBERT 12-in-1
65.9
57.3
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
12
GPT1
65.4
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
13
LXMERT
54.8
51.1
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
14
VisualBERT
49.2
48.8
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
1–14 / 14
페이지당
10
20
50
100