paper-with-me

홈 › Papers

The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos

2020-03-22 · Marcos Baptista Rios, Roberto J. López-Sastre, Fabian Caba Heilbron, Jan van Gemert, Francisco Javier Acevedo-Rodríguez, Saturnino Maldonado-Bascón

The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find few works and no consensus on the evaluation protocols to be used. In this paper we introduce a novel online metric, the Instantaneous Accuracy ($IA$), that exhibits an \emph{online} nature, solving most of the limitations of the previous (offline) metrics. We conduct a thorough experimental evaluation on TVSeries dataset, comparing the performance of various baseline methods to the state of the art. Our results confirm the problems of previous evaluation protocols, and suggest that an IA-based protocol is more adequate to the online scenario for human behaviour understanding. Code of the metric available https://github.com/gramuah/ia

📄 PDF Abstract BibTeX arXiv:2003.09970

Code (1)

gramuah/ia 공식 구현

Tasks

Action DetectionOnline Action Detection

Similar Papers 제목 키워드 기반

Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol

2020-03-26 · Marcos Baptista Rios, Roberto J. López-Sastre, Fabian Caba Heilbron, Jan van Gemert 외

The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find very few wo…

Action DetectionOnline Action Detection

Online Voltage Control for Unbalanced Distribution Networks Using Projected Newton Method

2022-01-11 · Rui Cheng, Zhaoyu Wang, Yifei Guo, Qianzhi Zhang

This paper proposes an online voltage control strategy of distributed energy resources (DERs), based on the projected Newton method (PNM), for unbalanced distribution networks. The optimal Volt/VAr control (VVC) problem …

SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs

2026-02-02 · Sourajit Das, Dibyajyoti Chakraborty, Romit Maulik arxiv

Discovering causal structures from multivariate time series is a key problem because interactions span across multiple lags and possibly involve instantaneous dependencies. Additionally, the search space of the dynamic g…

Motion and Structure from Event-based Normal Flow

2024-07-17 · Zhongyang Ren, Bangyan Liao, Delei Kong, Jinghang Li 외

Recovering the camera motion and scene geometry from visual data is a fundamental problem in the field of computer vision. Its success in standard vision is attributed to the maturity of feature extraction, data associat…

Online Learning and Equilibrium Computation with Ranking Feedback

2026-03-19 · Mingyang Liu, Yongshan Chen, Zhiyuan Fan, Gabriele Farina 외 arxiv

Online learning in arbitrary, and possibly adversarial, environments has been extensively studied in sequential decision-making, and it is closely connected to equilibrium computation in game theory. Most existing online…