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/S-CNN

S-CNN

Reported on 28 benchmarks across 7 tasks · 4 papers · 18 SOTA

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

Computer Vision22 results

Person Re-IdentificationonMarket-1501
Rank-1· 2016-07-28
65.88
best: 98 (st-ReID(RE, RK))
SOTA
Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification arXiv:1607.08378
Person Re-IdentificationonMarket-1501
mAP· 2016-07-28
39.55
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
SOTA
Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification arXiv:1607.08378
VideoonMEXaction2
mAP· 2016-01-09
7.4
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
VideoonTHUMOS’14
mAP IOU@0.3· 2016-01-09
36.3
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
VideoonTHUMOS’14
mAP IOU@0.4· 2016-01-09
28.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
VideoonTHUMOS’14
mAP IOU@0.5· 2016-01-09
19
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonMEXaction2
mAP· 2016-01-09
7.4
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2016-01-09
36.3
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2016-01-09
28.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2016-01-09
19
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonMEXaction2
mAP· 2016-01-09
7.4
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2016-01-09
36.3
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2016-01-09
28.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2016-01-09
19
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Image ClassificationonSTL-10
Percentage correct· 2016-06-07
61.94
best: 99.64 (µ2Net+ (ViT-L/16))
Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)arXiv:1606.02210
VideoonTHUMOS’14
mAP IOU@0.1· 2016-01-09
47.7
best: 74.02 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
VideoonTHUMOS’14
mAP IOU@0.2· 2016-01-09
43.5
best: 72.29 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.1· 2016-01-09
47.7
best: 74.02 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.2· 2016-01-09
43.5
best: 72.29 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonTHUMOS’14
mAP IOU@0.1· 2016-01-09
47.7
best: 74.02 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Action LocalizationonTHUMOS’14
mAP IOU@0.2· 2016-01-09
43.5
best: 72.29 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Clothing Attribute RecognitiononClothing Attributes Dataset
Accuracy· 2016-01-04
90.43
best: 92.87 (Label2Label)
Multi-task CNN Model for Attribute Prediction arXiv:1601.00400

Methodology6 results

Zero-Shot LearningonMEXaction2
mAP· 2016-01-09
7.4
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· 2016-01-09
36.3
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· 2016-01-09
28.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· 2016-01-09
19
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.1· 2016-01-09
47.7
best: 74.02 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.2· 2016-01-09
43.5
best: 72.29 (TSP)
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs arXiv:1601.02129