friedrichor/DiDeMo download history
friedrichor/DiDeMo is a text to video dataset on the Hugging Face Hub. In the last 30 days it was downloaded 781 times (125 in the last 7 days), and 15,627 times in total. It ranks #23,343 among datasets by monthly downloads.
About DiDeMo contains 10K long-form videos from Flickr. For each video, ~4 short sentences are annotated in temporal order. We follow the existing works to concatenate those short sentences and evaluate ‘paragraph-to-video’ retrieval on this benchmark. We adopt the official split: Trai