paper-with-me

image-sentence alignment 벤치마크

image-sentence alignment on VALSE existence

14개 결과 · ⬇ CSV · JSON

pairwise accuracy

39.7 53.67 67.65 81.62 95.6 2021-12 2026-09 ViLBERT 12-in-1 — 95.6 (2021-12-14) LXMERT — 78.6 (2021-12-14) CLIP — 66.9 (2021-12-14) ViLBERT — 66.5 (2021-12-14) GPT1 — 61.8 (2021-12-14) GPT2 — 58.0 (2021-12-14) VisualBERT — 39.7 (2021-12-14) ViLBERT 12-in-1 — 95.6 (2021-12-14) LXMERT — 78.6 (2021-12-14) CLIP — 66.9 (2021-12-14) ViLBERT — 66.5 (2021-12-14) GPT1 — 61.8 (2021-12-14) GPT2 — 58.0 (2021-12-14) VisualBERT — 39.7 (2021-12-14) ViLBERT 12-in-1 — 95.6 (2021-12-14)
RankModel pairwise accuracyAccuracy (%) PaperCodeYear
11 ViLBERT 66.52.4 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
12 GPT1 61.8– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
13 GPT2 58.0– VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
14 VisualBERT 39.749.3 VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena heidelberg-nlp/valse 2021
← 이전 11–14 / 14 페이지당 10 20 50 100