paper-with-me

홈 › Papers

3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding

2014-06-01 · CVPR 2014 6 · Ankur Gupta, Julieta Martinez, James J. Little, Robert J. Woodham

We describe a new approach to transfer knowledge across views for action recognition by using examples from a large collection of unlabelled mocap data. We achieve this by directly matching purely motion based features from videos to mocap. Our approach recovers 3D pose sequences without performing any body part tracking. We use these matches to generate multiple motion projections and thus add view invariance to our action recognition model. We also introduce a closed form solution for approximate non-linear Circulant Temporal Encoding (nCTE), which allows us to efficiently perform the matches in the frequency domain. We test our approach on the challenging unsupervised modality of the IXMAS dataset, and use publicly available motion capture data for matching. Without any additional annotation effort, we are able to significantly outperform the current state of the art.

📄 PDF Abstract BibTeX

Code (1)

jltmtz/mocap-dense-trajectories 공식 구현

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

MAVR-Net: Robust Multi-View Learning for MAV Action Recognition with Cross-View Attention

2025-10-17 · Nengbo Zhang, Hann Woei Ho arxiv

Recognizing the motion of Micro Aerial Vehicles (MAVs) is crucial for enabling cooperative perception and control in autonomous aerial swarms. Yet, vision-based recognition models relying only on RGB data often fail to c…

Action Recognition

Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions

2026-05-21 · Yannick Porto, Renato Martins, Thomas Chalumeau, Cedric Demonceaux arxiv

Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unse…

Zero-Shot Action RecognitionTransfer Learning

Cross-view Action Modeling, Learning and Recognition

2014-05-12 · CVPR 2014 6 · Jiang wang, Xiaohan Nie, Yin Xia, Ying Wu 외

Existing methods on video-based action recognition are generally view-dependent, i.e., performing recognition from the same views seen in the training data. We present a novel multiview spatio-temporal AND-OR graph (MST-…

Action RecognitionTemporal Action Localization

View-invariant Deep Architecture for Human Action Recognition using late fusion

2019-12-08 · Chhavi Dhiman, Dinesh Kumar Vishwakarma

Human action Recognition for unknown views is a challenging task. We propose a view-invariant deep human action recognition framework, which is a novel integration of two important action cues: motion and shape temporal …

Action RecognitionSSIMTemporal Action Localization

Unsupervised Learning of View-invariant Action Representations

2018-09-06 · NeurIPS 2018 12 · Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, la…

Action RecognitionRepresentation LearningTemporal Action Localization