公开(公告)号：US20240078816A1

公开(公告)日：2024-03-07

申请号：US18448345

申请日：2023-08-11

Applicant: NEC Laboratories America, Inc.

Inventor： Samuel Schulter ,  Vijay Kumar Baikampady Gopalkrishna ,  Yumin Suh ,  Shiyu Zhao

IPC: G06V20/58 ,  G06F40/30 ,  G06F40/40 ,  G06V10/82

CPC classification number: G06V20/584 ,  G06F40/30 ,  G06F40/40 ,  G06V10/82 ,  G06V2201/07

Abstract: A computer-implemented method for training a neural network to predict object categories without manual annotation is provided. The method includes feeding training datasets including at least images and data annotations to an object detection neural network, converting, by a text prompter, the data annotations into natural text inputs, converting, by a text embedder, the natural text inputs into embeddings, minimizing objective functions during training to adjust parameters of the object detection neural network, and predicting, by the object detection neural network, objects within images and videos.