[ { "text-to-video Mean Rank": 86.8, "text-to-video Median Rank": 16, "text-to-video R@1": 10, "text-to-video R@10": 41.2, "text-to-video R@5": 29, "video-to-text Mean Rank": 38.1, "video-to-text Median Rank": 8.3, "video-to-text R@1": 15.6, "video-to-text R@10": 55.2, "video-to-text R@5": 40.9, "code_links": [ { "title": "albanie/collaborative-experts", "url": "https://github.com/albanie/collaborative-experts" } ], "date": "2019-07-31", "date2": 20190731, "model": "Collaborative Experts", "paper": { "title": "Use What You Have: Video Retrieval Using Representations From Collaborative Experts", "url": "https://cknow.io/lib/5831d49b387ec6be" }, "paper_data_uoa": "5831d49b387ec6be" }, { "text-to-video Mean Rank": 213.8, "text-to-video Median Rank": 29.7, "text-to-video R@1": 7, "text-to-video R@10": 29.7, "text-to-video R@5": 20.9, "video-to-text Mean Rank": 134, "video-to-text Median Rank": 16, "video-to-text R@1": 12.5, "video-to-text R@10": 42.2, "video-to-text R@5": 32.1, "code_links": [ { "title": "niluthpol/multimodal_vtt", "url": "https://github.com/niluthpol/multimodal_vtt" } ], "date": "2018-06-11", "date2": 20180611, "model": "JEMC", "paper": { "title": "Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval", "url": "https://cknow.io/lib/422bb62e3ec3d501" }, "paper_data_uoa": "422bb62e3ec3d501" } ]