paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
image-sentence alignment
벤치마크
image-sentence alignment on VALSE plurality
14개 결과 ·
⬇ CSV
·
JSON
pairwise accuracy
45.7
52.38
59.05
65.73
72.4
2021-12
2026-09
ViLBERT 12-in-1 — 72.4 (2021-12-14)
LXMERT — 64.4 (2021-12-14)
ViLBERT — 61.2 (2021-12-14)
CLIP — 56.2 (2021-12-14)
GPT1 — 53.1 (2021-12-14)
GPT2 — 51.9 (2021-12-14)
VisualBERT — 45.7 (2021-12-14)
ViLBERT 12-in-1 — 72.4 (2021-12-14)
LXMERT — 64.4 (2021-12-14)
ViLBERT — 61.2 (2021-12-14)
CLIP — 56.2 (2021-12-14)
GPT1 — 53.1 (2021-12-14)
GPT2 — 51.9 (2021-12-14)
VisualBERT — 45.7 (2021-12-14)
ViLBERT 12-in-1 — 72.4 (2021-12-14)
2021-12-14 — ViLBERT 12-in-1: pairwise accuracy 72.4
Rank
Model
pairwise accuracy
Accuracy (%)
Paper
Code
Year
1
ViLBERT 12-in-1
72.4
62.0
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
2
LXMERT
64.4
55.1
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
3
ViLBERT
61.2
50.3
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
4
CLIP
56.2
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
5
GPT1
53.1
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
6
GPT2
51.9
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
7
VisualBERT
45.7
46.5
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
8
ViLBERT 12-in-1
72.4
62.0
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
9
LXMERT
64.4
55.1
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
10
ViLBERT
61.2
50.3
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
11
CLIP
56.2
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
12
GPT1
53.1
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
13
GPT2
51.9
–
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
heidelberg-nlp/valse
2021
14
VisualBERT
45.7
46.5
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