Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition

no code implementations • 1 May 2022 • Yang Zhou, Zhanhao He, Keyu Lu, Guanhong Wang, Gaoang Wang

Video-based action recognition is one of the most popular topics in computer vision.

Action Recognition Representation Learning +1

Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training

no code implementations • 27 Apr 2022 • Guanhong Wang, Keyu Lu, Yang Zhou, Zhanhao He, Gaoang Wang

Recently, much progress has been made for self-supervised action recognition.

Contrastive Learning Human Parsing +5

Learning Sports Camera Selection from Internet Videos

no code implementations • 8 Sep 2018 • Jianhui Chen, Keyu Lu, Sijia Tian, James J. Little

This work addresses camera selection, the task of predicting which camera should be "on air" from multiple candidate cameras for soccer broadcast.

Light Cascaded Convolutional Neural Networks for Accurate Player Detection

no code implementations • 29 Sep 2017 • Keyu Lu, Jianhui Chen, James J. Little, Hangen He

Vision based player detection is important in sports applications.

General Classification

Generalized Haar Filter based Deep Networks for Real-Time Object Detection in Traffic Scene

no code implementations • 30 Oct 2016 • Keyu Lu, Jian Li, Xiangjing An, Hangen He

This paper presents a generalized Haar filter based deep network which is suitable for the object detection tasks in traffic scene.

Object object-detection +2