Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CRAFT

CRAFT

Reported on 33 benchmarks across 11 tasks · 4 papers · 14 SOTA

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

Computer Vision25 results

Object Detectiononnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
3D Object Detectiononnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
Scene Text DetectiononTotal-Text
Precision· 2019-04-03
87.6
best: 93 (MixNet)
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2013
H-Mean· 2019-04-03
95.2
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2013
Precision· 2019-04-03
97.4
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2013
Recall· 2019-04-03
93.1
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2017 MLT
H-Mean· 2019-04-03
73.9
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononMSRA-TD500
F-Measure· 2019-04-03
82.9
best: 89.4 (MixNet)
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononMSRA-TD500
Precision· 2019-04-03
88.2
best: 92.1 (FAST-B-736)
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononMSRA-TD500
Recall· 2019-04-03
78.2
best: 88.1 (MixNet)
SOTA
Character Region Awareness for Text Detection arXiv:1904.01941
Image Super-ResolutiononSet14 - 4x upscaling
PSNR· 2023-08-09
28.85
best: 29.54 (DRCT-L)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
Image Super-ResolutiononSet14 - 4x upscaling
SSIM· 2023-08-09
0.7872
best: 0.894 (Edge-informed SR)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
3D Object Super-ResolutiononSet14 - 4x upscaling
PSNR· 2023-08-09
28.85
best: 29.54 (DRCT-L)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
3D Object Super-ResolutiononSet14 - 4x upscaling
SSIM· 2023-08-09
0.7872
best: 0.894 (Edge-informed SR)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
Optical Flow EstimationonKITTI 2015 (train)
EPE· 2022-03-31
4.88
best: 13.17 (HD3)
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow arXiv:2203.16896
Optical Flow EstimationonKITTI 2015 (train)
F1-all· 2022-03-31
17.5
best: 33.7 (PWC-Net)
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow arXiv:2203.16896
Scene Text DetectiononTotal-Text
Recall· 2019-04-03
79.9
best: 88.1 (MixNet)
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononSCUT-CTW1500
F-Measure· 2019-04-03
83.5
best: 89.8 (MixNet)
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononSCUT-CTW1500
Precision· 2019-04-03
86
best: 91.7 (DPText-DETR (ResNet50))
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononSCUT-CTW1500
Recall· 2019-04-03
81.1
best: 88.3 (MixNet)
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2017 MLT
Precision· 2019-04-03
80.6
best: 84.42 (PMTD*)
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2017 MLT
Recall· 2019-04-03
68.2
best: 76.44 (SBD)
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2015
F-Measure· 2019-04-03
86.9
best: 92.23 (TextFuseNet (ResNeXt-101))
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2015
Precision· 2019-04-03
89.8
best: 93.96 (TextFuseNet (ResNeXt-101))
Character Region Awareness for Text Detection arXiv:1904.01941
Scene Text DetectiononICDAR 2015
Recall· 2019-04-03
84.3
best: 91.98 (CharNet H-88 (single-scale))
Character Region Awareness for Text Detection arXiv:1904.01941

Methodology6 results

3Donnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
2D Classificationonnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
2D Object Detectiononnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
16konnuscenes Camera-Radar
NDS· 2022-09-14
52.3
best: 69.9 (SpaRC)
SOTA
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer arXiv:2209.06535
16konSet14 - 4x upscaling
PSNR· 2023-08-09
28.85
best: 29.54 (DRCT-L)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
16konSet14 - 4x upscaling
SSIM· 2023-08-09
0.7872
best: 0.894 (Edge-informed SR)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022

Graphs2 results

Super-ResolutiononSet14 - 4x upscaling
PSNR· 2023-08-09
28.85
best: 29.54 (DRCT-L)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022
Super-ResolutiononSet14 - 4x upscaling
SSIM· 2023-08-09
0.7872
best: 0.894 (Edge-informed SR)
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution arXiv:2308.05022