Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Clothing

Benchmarks

Task NameDataset NameSOTA ResultTrend
RecommendationClothing
Recall@106.88
40
Multimodal RecommendationClothing (test)
Recall@106.75
24
Cold-start RecommendationClothing Cold (test)
Recall@2014.86
13
Sequential RecommendationClothing (test)
HR@50.0197
13
Label Noise DetectionClothing1M (val)
Average Error Rate15.77
11
Multimodal RecommendationClothing
Memory (GB)2.16
9
Cross-domain RecommendationClothing Leisure Scenario (test)
Recall@52.88
8
Generative RecommendationClothing
Recall@101.8
7
Multimodal Recommendation UnlearningClothing (user-level)
Recall@20 (R)9.45
7
Rating PredictionClothing
RMSE0.6099
6
Multimodal Recommendation UnlearningClothing
Balanced Accuracy94.52
6
RecommendationClothing
nDCG@1017.15
6
Multimodal RecommendationClothing
NDCG@205.13
5
Explanation-rating coherence evaluationClothing
GPT Score0.8679
4
Multi-label Attribute RecognitionClothing
Accuracy92.87
3
Product SearchClothing Coarse-grained Query
R@576.65
2
Product SearchClothing Fine-grained Query
R@50.7048
2
Sequential RecommendationClothing
HR@11.71
2
Showing 18 of 18 rows