Leveraging Temporal Contextualization for Video Action Recognition

We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we introduce Temporal Contextualization (TC), a layer-wise tem...

Full description

Saved in:
Bibliographic Details
Main Authors Kim, Minji, Han, Dongyoon, Kim, Taekyung, Han, Bohyung
Format Journal Article
LanguageEnglish
Published 15.04.2024
Subjects
Online AccessGet full text

Cover

Loading…