{"url":"/method/paramcrop","slug":"paramcrop","name":"ParamCrop","full_name":"ParamCrop","full_name_withheld":false,"description_markdown":"**ParamCrop** is a parametric cubic cropping for video contrastive learning, where cubic cropping refers to cropping a 3D cube\r\nfrom the input video. The central component of ParamCrop is a differentiable spatio-temporal cropping operation, which enables ParamCrop to be trained simultaneously with the video backbone and adjust the cropping strategy on the fly. The objective of ParamCrop is set to be adversarial to the video backbone, which is to increase the contrastive loss. Hence, initialized with the simplest setting where two cropped views largely overlaps, ParamCrop gradually increases the disparity between two views.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning","paper":"/paper/paramcrop-parametric-cubic-cropping-for-video","first_author":"Zhiwu Qing","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/paramcrop-parametric-cubic-cropping-for-video"},"source":{"url":"https://arxiv.org/abs/2108.10501v3","title":"ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Self-Supervised Learning","url":"/methods/category/self-supervised-learning","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Video Models","url":"/methods/category/generative-video-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/paramcrop-parametric-cubic-cropping-for-video","title":"ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning","date":"2021-08-24","arxiv_id":"2108.10501","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1}],"tasks_shown":1,"n_tasks":1,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/paramcrop"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}