Mar 8, 2024 · We introduce LaGTran, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to unlabeled ...

We introduce LaGTran, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to unlabeled ...

Aug 17, 2024 · Today's paper introduces LaGTran, a novel framework that uses text supervision to improve transfer learning across domains for image and ...

LaGTran is introduced, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to ...

We propose a novel framework called LaGTrAn, which leverages natural language to guide the transfer of discriminative knowledge from labeled source to unlabeled ...

LaGTran is introduced, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to ...

Sep 2, 2024 · Bibliographic details on Tell, Don't Show: Language Guidance Eases Transfer Across Domains in Images and Videos.

Jun 6, 2024 · This paper explores how language guidance can help transfer learning between different visual domains, such as images and videos. The ...

本论文旨在解决具有领域转移的目标数据无标签的情况下，如何从有标签的源数据中传递歧视性知识的问题。同时，该论文也尝试在视频领域中解决自我-外部转移的问题。

My PhD research focuses on learning label-efficient representations from large-scale images and videos that are useful and transferable across a wide range of ...