paper-with-me

image-sentence alignment 벤치마크

image-sentence alignment on VALSE foil-it (noun phrases)

14개 결과 · ⬇ CSV · JSON

pairwise accuracy

48.5 58.58 68.65 78.72 88.8 2021-12 2026-09 CLIP — 88.8 (2021-12-14) LXMERT — 87.1 (2021-12-14) ViLBERT 12-in-1 — 86.9 (2021-12-14) ViLBERT — 86.9 (2021-12-14) GPT2 — 80.7 (2021-12-14) GPT1 — 77.5 (2021-12-14) VisualBERT — 48.5 (2021-12-14) CLIP — 88.8 (2021-12-14) LXMERT — 87.1 (2021-12-14) ViLBERT 12-in-1 — 86.9 (2021-12-14) ViLBERT — 86.9 (2021-12-14) GPT2 — 80.7 (2021-12-14) GPT1 — 77.5 (2021-12-14) VisualBERT — 48.5 (2021-12-14) CLIP — 88.8 (2021-12-14)
RankModel pairwise accuracyAccuracy (%) PaperCodeYear
1 CLIP 88.8– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
2 LXMERT 87.170.8 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
3 ViLBERT 12-in-1 86.971.5 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
3 ViLBERT 86.955.9 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
5 GPT2 80.7– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
6 GPT1 77.5– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
7 VisualBERT 48.546.6 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
8 CLIP 88.8– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
9 LXMERT 87.170.8 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
10 ViLBERT 12-in-1 86.971.5 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
10 ViLBERT 86.955.9 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
12 GPT2 80.7– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
13 GPT1 77.5– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
14 VisualBERT 48.546.6 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