Spatio-temporal Aware Non-negative Component Representation for Action Recognition
This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR). The proposed STANNCR is based on action component and incorporates the spatial-temporal information. We first introduce a spatial-temporal distribution vector (STDV) to model the distributions of local feature locations in a compact and discriminative manner. Then we employ non-negative matrix factorization (NMF) to learn the action components and encode the video samples. The action component considers the correlations of visual words, which effectively bridge the sematic gap in action recognition. To incorporate the spatial-temporal cues for final representation, the STDV is used as the part of graph regularization for NMF. The fusion of spatial-temporal information makes the STANNCR more discriminative, and our fusion manner is more compact than traditional method of concatenating vectors. The proposed approach is extensively evaluated on three public datasets. The experimental results demonstrate the effectiveness of STANNCR for action recognition.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Language Model Empowered Spatio-Temporal Forecasting via Physics-Aware Reprogramming
Spatio-temporal forecasting is pivotal in numerous real-world applications, including transportation planning, energy management, and climate monitoring. In this work, we aim to harness the reasoning and generalization a…
energy managementLanguage ModelingLanguage ModellingSpatio-Temporal Forecasting+2Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding
Nowadays, navigation and ride-sharing apps have collected numerous images with spatio-temporal data. A core technology for analyzing such images, associated with spatiotemporal information, is Traffic Scene Understanding…
Scene UnderstandingFew-Shot LearningPersonalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) methods to model the spatio-temporally varian…
Contrastive LearningFederated LearningPersonalized Federated LearningSemantic Similarity+2DARTs: A Dual-Path Robust Framework for Anomaly Detection in High-Dimensional Multivariate Time Series
Multivariate time series anomaly detection (MTSAD) aims to accurately identify and localize complex abnormal patterns in the large-scale industrial control systems. While existing approaches excel in recognizing the dist…
Time Series Anomaly DetectionSuccessive POI Recommendation via Brain-inspired Spatiotemporal Aware Representation
POI vector representation (embedding) is the core of successive POI recommendation. However, existing approaches only rely on basic discretization and interval analyses and fail to fully exploit complicated spatiotempora…
General Knowledge