Generative Video Models

ParamCrop is a parametric cubic cropping for video contrastive learning, where cubic cropping refers to cropping a 3D cube from 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.

Source: ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning

Papers


Paper Code Results Date Stars

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories