相关数据集
Multimodal-Fatima/DTD_parition1_test_embeddings
--- dataset_info: features: - name: image dtype: image - name: id dtype: int64 - name: vision_embeddings sequence: float32 splits: - name: openai_clip_vit_large_patch14 num
Hugging Face2023-01-29 更新130
Extracted Features of Cross-time Amsterdam Dataset
This collection contains feature files where the features are extracted on Cross-time Amsterdam dataset using various methods and models such as SIFT, LIFT, and pre-trained VGG-16, ResNets, NetVLAD, A
4TU.ResearchData2021-06-08 更新70
Day 3 003_srgb_1_to_day2 083_srgb_5_human
contains the L*a*b* and Gabor filter outputs of all 505 samples of bark, as seen by Human visual systems. Filename+photo= Name of image. rep= number of sample from each image (5 for each image). L= L
Dryad2017-01-01 更新50
alitourani/moviefeats_visual
该数据集包含从各种电影（全长）、镜头和免费预告片中提取的视觉特征，适用于推荐、信息检索、分类等任务。数据集统计信息包括电影总数、每部电影的平均帧数、总帧数/特征向量数等。此外，还提供了与MovieLenz 25M数据集结合后的统计信息，如累积类型数、平均电影评分、用户总数、累积交互次数等。数据集的模型特征信息包括使用不同模型（如incp3和vgg19）处理的全电影、电影镜头和预告片的文件数量和磁盘
Hugging Face2024-05-21 更新130
US_Film_Trailers_Barcodes_Sample
Explore this data set for yourself via a Shiny app here: http://nickredfern.shinyapps.io/colour_palletes_US_trailers This data set contains the smoothed barcodes of 173 trailers nominated for a Gold
NIAID Data Ecosystem60
