- 博客(35)
- 收藏
- 关注
原创 VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
VideoMAE
2023-07-11 20:50:02 916
原创 【Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representa】
MVD
2023-05-31 11:24:42 938
原创 DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
DearKD
2023-05-23 20:54:39 450
原创 【MARS: Motion-Augmented RGB Stream for Action Recognition】
MARS: Motion-Augmented RGB Stream for Action Recognition
2023-03-22 15:00:52 361
原创 Revisiting Knowledge Distillation via Label Smoothing Regularization
Revisiting Knowledge Distillation via Label Smoothing Regularization
2023-03-15 19:48:22 467
原创 【Knowledge distillation: A good teacher is patient and consistent】
Knowledge distillation:A good teacher is patient and consistent
2023-03-03 16:52:10 547
原创 【迁移学习综述】
迁移学习的目标是将某个领域或任务上学习到的知识应用到不同的但相关的领域或问题中。迁移学习的研究来源于一个观测:人类可以将以前的学到的知识应用于解决新的问题,更快的解决问题或取得更好的效果。迁移学习被赋予这样一个任务:从以前的任务当中去学习知识(knowledge)或经验,并应用于新的任务当中。换句话说,迁移学习目的是从一个或多个源任务(source tasks)中抽取知识、经验,然后应用于一个目标领域(target domain)当中去。
2023-02-12 10:31:17 3793
原创 【Knowledge Distillation with the Reused Teacher Classifier】
Knowledge Distillation with the Reused Teacher Classifier
2023-01-11 17:27:01 218
原创 SlowFast Networks for Video Recognition
SlowFast Networks for Video Recognition
2022-10-28 22:55:48 730
原创 TSM: Temporal Shift Module for Efficient Video Understanding
TSM: Temporal Shift Module for Efficient Video Understanding
2022-10-21 14:46:38 1154 1
原创 【Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition】
Optical Flow Guided Feature
2022-10-13 17:23:21 144
原创 【X3D: Expanding Architectures for Efficient Video Recognition】
X3D: Expanding Architectures for Efficient Video Recognition
2022-09-16 16:32:13 863
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人