CFR

Reported on 4 benchmarks across 2 tasks · 2 papers · 2 SOTA

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

Natural Language Processing3 results

Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2021-10-06
72.1
SOTA
Coarse-to-Fine Reasoning for Visual Question Answering arXiv:2110.02526
Visual Question Answering (VQA)onVisual7W
Percentage correct· 2021-10-06
71.9
best: 72.53 (CMN)
Coarse-to-Fine Reasoning for Visual Question Answering arXiv:2110.02526
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2021-10-06
72.5
best: 84.3 (PaLI)
Coarse-to-Fine Reasoning for Visual Question Answering arXiv:2110.02526

Computer Vision1 result

Multispectral Object DetectiononKAIST Multispectral Pedestrian Detection Benchmark
Reasonable Miss Rate· 2020-09-26
6.13
best: 7.58 (MLPD)
SOTA
Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks arXiv:2009.12664