Recommendation on MovieLens latest (test)
10.7084Recall@10Visual+Textual (ST)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Visual+Textual (ST)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=Sentence Transformers (ST)2025.06 | 10.7084 | 26.8102 | 9.5418 | 17.4363 | 495.5 | |
| Visual+Textual (ST)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=Sentence Transformers (ST)2025.06 | 9.7654 | 24.6567 | 8.9355 | 15.9758 | 427.1 | |
| OpenAI UnimodalPipeline Type=LLM-based Pipeline, Visual Modality=false, Textual Modality=true, Backbone=OpenAI2025.06 | 8.9671 | 17.9811 | 5.7714 | 10.1169 | 284.4 | |
| ST UnimodalPipeline Type=Manual Pipeline, Visual Modality=false, Textual Modality=true, Backbone=Sentence Transformers (ST)2025.06 | 8.4321 | 16.7488 | 5.0541 | 7.9941 | 272 | |
| ST UnimodalPipeline Type=LLM-based Pipeline, Visual Modality=false, Textual Modality=true, Backbone=Sentence Transformers (ST)2025.06 | 7.73 | 16.9313 | 5.1284 | 8.6847 | 262 | |
| OpenAI UnimodalPipeline Type=Manual Pipeline, Visual Modality=false, Textual Modality=true, Backbone=OpenAI2025.06 | 7.5686 | 16.6709 | 5.9188 | 10.4077 | 270.3 | |
| Visual+Textual (Llama3.0)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=Llama3.02025.06 | 4.8338 | 14.1869 | 3.4597 | 7.9539 | 203.3 | |
| Visual+Textual (Llama3.0)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=Llama3.02025.06 | 4.7614 | 14.5944 | 4.1977 | 9.262 | 224.2 | |
| Visual+Textual (ST)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=Sentence Transformers (ST)2025.06 | 4.3374 | 12.483 | 3.5712 | 8.0947 | 177.3 | |
| Visual+Textual (OpenAI)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=OpenAI2025.06 | 4.025 | 8.4531 | 2.919 | 6.3593 | 80.7 | |
| Llama3.0 UnimodalPipeline Type=Manual Pipeline, Visual Modality=false, Textual Modality=true, Backbone=Llama3.02025.06 | 3.982 | 9.1084 | 3.4442 | 6.2854 | 102.3 | |
| Visual+Textual (Llama3.0)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=Llama3.02025.06 | 3.8048 | 11.8645 | 2.8749 | 7.8329 | 153.7 | |
| Visual+Textual (OpenAI)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=OpenAI2025.06 | 3.7374 | 11.5342 | 3.6908 | 7.8362 | 156.2 | |
| Visual+Textual (Llama3.0)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=Llama3.02025.06 | 3.7333 | 11.4743 | 3.2583 | 7.5561 | 154.9 | |
| Visual+Textual (OpenAI)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=OpenAI2025.06 | 3.6987 | 10.1464 | 3.4161 | 7.2735 | 116.9 | |
| Visual+Textual (ST)Pipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=PCA, Backbone=Sentence Transformers (ST)2025.06 | 3.513 | 12.0745 | 3.0523 | 6.666 | 158.1 | |
| Llama3.0 UnimodalPipeline Type=LLM-based Pipeline, Visual Modality=false, Textual Modality=true, Backbone=Llama3.02025.06 | 3.3492 | 8.3699 | 3.2395 | 6.6655 | 78.9 | |
| Visual+Textual (OpenAI)Pipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=true, Fusion Method=CCA, Backbone=OpenAI2025.06 | 2.8301 | 7.8006 | 2.5079 | 5.9463 | 73.3 | |
| Visual UnimodalPipeline Type=LLM-based Pipeline, Visual Modality=true, Textual Modality=false2025.06 | 1.734 | 4.6774 | 0.847 | 2.7337 | 0 | |
| Visual UnimodalPipeline Type=Manual Pipeline, Visual Modality=true, Textual Modality=false2025.06 | 1.611 | 4.5019 | 1.198 | 3.0501 | 0 |