公开(公告)号：US20240005663A1

公开(公告)日：2024-01-04

申请号：US17853671

申请日：2022-06-29

Applicant: Adobe Inc.

Inventor： Joon-Young LEE ,  Seoung Wug OH ,  Sanghyun WOO ,  Kwanyong PARK

IPC: G06V20/40 ,  G06F16/783 ,  G06F16/735 ,  G06T7/11 ,  H04N21/472

CPC classification number: G06V20/49 ,  G06F16/784 ,  G06F16/735 ,  G06T7/11 ,  H04N21/47205 ,  G06T2207/10021

Abstract: Embodiments are disclosed for performing per-clip object segmentation of objects in a video sequence using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a query video sequence and memory data, the memory data including a memory video frame from the query video sequence and an annotated memory video frame including an object mask for an object in the memory video frame, segmenting the query video sequence into a plurality of query video clips and passing a first set of query video frames of a first query video clip and the memory data through a trained encoder-decoder network, predicting a modified set of query video frames, including predictions of object masks for the object, and updating the memory data to include one or more frames of the first set of query video frames and the modified set of query video frames.