Oct 27, 2023 · In this paper, we make the first attempt and propose a Lightweight Multi-modal Knowledge Distillation framework (Lite-MKD) for few-shot action recognition.

Lite-MKD adopts a multi-modal teacher knowledge learning and single-modal student knowledge distillation architecture.

Recently, Cross-Modal Knowledge Distillation (CMKD) has proven to be effective for multi-modal applications characterized by modalities mismatch [16] .

Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition. B. Liu, T. Zheng, P. Zheng, D. Liu, X. Qu, J. Gao, ...

... Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition. HuiGuanLab/Lite-MKD's past year of commit activity. Python 3 0 2 0 ...

Jul 20, 2024 · Few-shot action recognition aims to address the high cost and impracticality of manually labeling complex and variable video data in action recognition.

Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition. ACM international conference on Multimedia (ACM MM) ...

Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition · Baolong LiuTianyi Zheng +5 authors. Xun Wang. Computer ...

Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition · Author Picture Baolong Liu,; Author ...

Mar 28, 2024 · Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition. October 2023. Baolong Liu · Tianyi Zheng ...