paper-with-me

홈 › Papers

Action Selection Learning for Multi-label Multi-view Action Recognition

2024-10-04 · Trung Thanh Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide

Multi-label multi-view action recognition aims to recognize multiple concurrent or sequential actions from untrimmed videos captured by multiple cameras. Existing work has focused on multi-view action recognition in a narrow area with strong labels available, where the onset and offset of each action are labeled at the frame-level. This study focuses on real-world scenarios where cameras are distributed to capture a wide-range area with only weak labels available at the video-level. We propose the method named Multi-view Action Selection Learning (MultiASL), which leverages action selection learning to enhance view fusion by selecting the most useful information from different viewpoints. The proposed method includes a Multi-view Spatial-Temporal Transformer video encoder to extract spatial and temporal features from multi-viewpoint videos. Action Selection Learning is employed at the frame-level, using pseudo ground-truth obtained from weak labels at the video-level, to identify the most relevant frames for action recognition. Experiments in a real-world office environment using the MM-Office dataset demonstrate the superior performance of the proposed method compared to existing methods. The source code is available at https://github.com/thanhhff/MultiASL/.

📄 PDF Abstract BibTeX arXiv:2410.03302

Code (1)

thanhhff/MultiASL 공식 구현 pytorch

Tasks

Action Recognition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget

2025-09-20 · Qi Zhang, Bin Li, Antoni B. Chan, Hui Huang arxiv

Multi-view crowd counting and localization fuse the input multi-views for estimating the crowd number or locations on the ground. Existing methods mainly focus on accurately predicting on the crowd shown in the input vie…

Crowd Counting

Adaptive Collaborative Sot Label Learning for Unsupervised Multi-view Feature Selection

2018-07-13 · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) 2018 7 · Dan Shi, Shandong Normal University, China

Unsupervised multi-view feature selection aims to select informative features with multi-view features and unsupervised learning. It is a challenging problem due to the absence of explicit semantic supervision. Recently…

feature selectiongraph constructionPseudo Label

Redundancy-optimized Multi-head Attention Networks for Multi-View Multi-Label Feature Selection

2025-11-16 · Yuzhou Liu, Jiarui Liu, Wanfu Gao arxiv

Multi-view multi-label data offers richer perspectives for artificial intelligence, but simultaneously presents significant challenges for feature selection due to the inherent complexity of interrelations among features…

Joint Learning of Unsupervised Multi-view Feature and Instance Co-selection with Cross-view Imputation

2025-12-17 · Yuxin Cai, Yanyong Huang, Jinyuan Chang, Dongjie Wang 외 arxiv

Feature and instance co-selection, which aims to reduce both feature dimensionality and sample size by identifying the most informative features and instances, has attracted considerable attention in recent years. Howeve…

Multi-view Unsupervised Feature Selection by Cross-diffused Matrix Alignment

2017-05-02 · Xiaokai Wei, Bokai Cao, Philip S. Yu

Multi-view high-dimensional data become increasingly popular in the big data era. Feature selection is a useful technique for alleviating the curse of dimensionality in multi-view learning. In this paper, we study unsupe…

feature selectionMULTI-VIEW LEARNING