paper-with-me

Papers

Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors

2015-11-10 · Chang Tang, Pichao Wang, Wanqing Li

Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based on the evidence accumulation over time to make predictions from stream videos. This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence. In particular, a fast incremental updating method for the weighted covariance descriptor is developed for accumulation of temporal information and online prediction. The weighted covariance descriptor takes the following principles into consideration: past frames have less contribution for recognition and recent and informative frames such as key frames contribute more to the recognition. The online recognition is achieved using a simple nearest neighbor search against a set of offline trained action models. Experimental results on MSC-12 Kinect Gesture dataset and our newly constructed online action recognition dataset have demonstrated the efficacy of the proposed method.

📄 PDF Abstract BibTeX arXiv:1511.03028

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionIncremental LearningTemporal Action Localization

Similar Papers 제목 키워드 기반

Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition

2013-03-25 · Andres Sanin, Conrad Sanderson, Mehrtash T. Harandi, Brian C. Lovell

We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by …

General ClassificationGesture RecognitionInterest Point Detection

General Purpose Incremental Covariance Update and Efficient Belief Space Planning via Factor-Graph Propagation Action Tree

2019-06-05 · Dmitry Kopitkov, Vadim Indelman

Fast covariance calculation is required both for SLAM (e.g.~in order to solve data association) and for evaluating the information-theoretic term for different candidate actions in belief space planning (BSP). In this pa…

Covariance-based Space Regularization for Few-shot Class Incremental Learning

2024-11-02 · Yijie Hu, Guanyu Yang, Zhaorui Tan, Xiaowei Huang 외

Few-shot Class Incremental Learning (FSCIL) presents a challenging yet realistic scenario, which requires the model to continually learn new classes with limited labeled data (i.e., incremental sessions) while retaining …

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

2025-02-11 · Fangwen Wu, Lechao Cheng, Shengeng Tang, Xiaofeng Zhu 외

Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability remains a significant challenge, partic…

class-incremental learningClass Incremental LearningIncremental Learning

Incremental Nonparametric Weighted Feature Extraction for OnlineSubspace Pattern Classification

2016-10-26 · Hamid Abrishami Moghaddam, Elaheh Raisi

In this paper, a new online method based on nonparametric weighted feature extraction (NWFE) is proposed. NWFE was introduced to enjoy optimum characteristics of linear discriminant analysis (LDA) and nonparametric discr…

ClassificationGeneral Classification