ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection

ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection

https://arxiv.org/abs/2304.08114v1

May 9, 2023

Human-Object Interaction, CLIP, ViT,

CVPR (2023)

概要

新規性・差分

アイデア

結果

一覧へ戻る