Lyrics

Reported on 5 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Image Captioningonnocaps entire
CIDEr· 2023-12-08
126.8
SOTA
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects arXiv:2312.05278
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2023-12-08
58.2
best: 66.8 (PaLI-X-VPD)
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects arXiv:2312.05278
Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2023-12-08
62.4
best: 72.1 (CFR)
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects arXiv:2312.05278
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2023-12-08
81.2
best: 84.3 (PaLI)
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects arXiv:2312.05278
Image CaptioningonCOCO (Common Objects in Context)
CIDEr· 2023-12-08
121.1
best: 143.7 (ExpansionNet v2)
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects arXiv:2312.05278