TSM: 2D-CNN mang hiệu suất của 3D-CNN trong bài toán action recognition

Video Understanding: Tổng quan

[Paper Explain] Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition - Bàn luận 1 chút về video augmentation.

[Paper Explain] Revisiting Skeleton-based Action Recognition - BKAI-NAVER Challenge 2022 Top1 Solution Baseline