Method, device and equipment for generating timing sequence action nomination and storage medium

Abstract

The invention discloses a method, a device and equipment for generating a timing sequence action nomination and a storage medium. The method comprises the following steps: acquiring a plurality of video frames in a video; calling a time sequence action nomination generation model to predict the plurality of video frames to obtain a time sequence boundary confidence map and an action integrity probability map corresponding to the video, and fusing the time sequence boundary confidence map and the action integrity probability map to obtain a fused feature map; and outputting the timing sequenceaction nomination of the video according to the fusion feature map. The two time sequence boundary confidence maps and the action integrity probability map based on the dense boundary are used for predicting the boundary of time sequence action nomination based on global nomination level information (L * L dimension), and is not similar to the method that the BMN predicts the boundary of the timing sequence action nomination only based on the local information, so that the accurate boundary can be predicted in the generation task of the timing sequence action nomination.

Description

technical field [0001] The present application relates to the field of machine learning, and in particular to a method, device, device and storage medium for generating time-series action nominations. Background technique [0002] The task of generating temporal action nominations refers to generating a certain number of temporal action nominations for uncropped long videos. A temporal action nomination is a temporal interval (from the start boundary to the end boundary) that may contain action segments. High-quality timing action nominations should have several characteristics: (1) flexible timing length; (2) precise timing boundaries; (3) reliable confidence scores. Temporal action proposal is a crucial step for various tasks such as action detection and video analysis. [0003] In related technologies, boundary-based methods are used to complete the generation task. Typical boundary-based methods include: Boundary-Sensitive Network (BSN) and Boundary-Matching Network (B...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a method, device, device, and storage medium for generating time-series

Images