DAL

Reported on 5 benchmarks across 3 tasks · 2 papers · 5 SOTA

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

Computer Vision5 results

Scene Text DetectiononICDAR2015
F-Measure· uses extra data· 2020-12-08
82.4
SOTA
Dynamic Anchor Learning for Arbitrary-Oriented Object Detection arXiv:2012.04150
Multi-Oriented Scene Text DetectiononICDAR2015
F-Measure· uses extra data· 2020-12-08
82.4
SOTA
Dynamic Anchor Learning for Arbitrary-Oriented Object Detection arXiv:2012.04150
Person Re-IdentificationonPRID2011
Rank-1· 2018-08-22
85.3
best: 96.6 (B-BOT + Attention and CL loss*)
SOTA
Deep Association Learning for Unsupervised Video Person Re-identification arXiv:1808.07301
Person Re-IdentificationonPRID2011
Rank-20· 2018-08-22
99.6
best: 100 (FGReID)
SOTA
Deep Association Learning for Unsupervised Video Person Re-identification arXiv:1808.07301
Person Re-IdentificationonPRID2011
Rank-5· 2018-08-22
97
best: 99.3 (Snippet (Supervised))
SOTA
Deep Association Learning for Unsupervised Video Person Re-identification arXiv:1808.07301