paper-with-me

Papers

Representation Flow for Action Recognition

2018-10-02 · CVPR 2019 6 · AJ Piergiovanni, Michael S. Ryoo

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the flow' of any representation channel within a convolutional neural network for action recognition. Its parameters for iterative flow optimization are learned in an end-to-end fashion together with the other CNN model parameters, maximizing the action recognition performance. Furthermore, we newly introduce the concept of learning flow of flow' representations by stacking multiple representation flow layers. We conducted extensive experimental evaluations, confirming its advantages over previous recognition models using traditional optical flows in both computational speed and performance. Code/models available here: https://piergiaj.github.io/rep-flow-site/

📄 PDF Abstract BibTeX arXiv:1810.01455

Code (5)

piergiaj/representation-flow-cvpr19 공식 구현 pytorch
KiUngSong/Vision pytorch
chunfeng0301/Flow paddle
liu824/representation-flow-for-action-recognition-paddlepaddle paddle
nikankind/Reproduce-Article-Representation-Flow-for-Action-Recognition-with-PaddlePaddle paddle

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosActivity RecognitionActivity Recognition In VideosOptical Flow EstimationTemporal Action LocalizationVideo ClassificationVideo Understanding

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks

2017-02-28 · CVPR 2017 7 · Pichao Wang, Wanqing Li, Zhimin Gao, Yuyao Zhang 외

Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutio…

3D Action RecognitionAction RecognitionTemporal Action Localization

An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition

2024-11-27 · Song-Jiang Lai, Tsun-Hin Cheung, Ka-Chun Fung, Tian-Shan Liu 외

With the rapid advancements in deep learning, computer vision tasks have seen significant improvements, making two-stream neural networks a popular focus for video based action recognition. Traditional models using RGB a…

Action RecognitionOptical Flow EstimationTemporal Action Localization

Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data

2013-10-01 · Karla Brkić, Srđan Rašić, Axel Pinz, Siniša Šegvić 외

This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a …

Action RecognitionOptical Flow EstimationTemporal Action Localization

ActionFlowNet: Learning Motion Representation for Action Recognition

2016-12-09 · Joe Yue-Hei Ng, Jonghyun Choi, Jan Neumann, Larry S. Davis

Even with the recent advances in convolutional neural networks (CNN) in various visual recognition tasks, the state-of-the-art action recognition system still relies on hand crafted motion feature such as optical flow to…

Action RecognitionOptical Flow EstimationTemporal Action Localization

Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition

2017-11-29 · CVPR 2018 6 · Shuyang Sun, Zhanghui Kuang, Wanli Ouyang, Lu Sheng 외

Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), whi…

Action RecognitionAction Recognition In VideosOptical Flow EstimationTemporal Action Localization