A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling

Human behavior is a continuous stochastic spatio-temporal process which is governed by semantic actions and affordances as well as latent factors. Therefore, video-based human activity modeling is ...

cs.CV Computer Science

View graph Source

Paper

References (40)

01A Structured Variational Autoencoder for Contextual Morphological InflectionLawrence Wolf-Sonkin, Jason Naradowsky, Sabrina J. Mielke et al.2018 · Annual Meeting of the Association for Computational Linguistics · 12 citations In Library

02SSNet: Scale Selection Network for Online 3D Action PredictionJun Liu, Amir Shahroudy, G. Wang et al.2018 · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 55 citations

03Disentangled Sequential AutoencoderYingzhen Li, S. Mandt2018 · International Conference on Machine Learning · 307 citations In Library

04Advances in Variational InferenceCheng Zhang, Judith Bütepage, H. Kjellström et al.2017 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 821 citations In Library

05RGB-D-based Human Motion Recognition with Deep Learning: A SurveyPichao Wang, W. Li, P. Ogunbona et al.2017 · Computer Vision and Image Understanding · 384 citations In Library

06Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM NetworksJun Liu, G. Wang, Ling-yu Duan et al.2017 · IEEE Transactions on Image Processing · 543 citations In Library

07A Recurrent Variational Autoencoder for Human Motion SynthesisI. Habibie, Daniel Holden, Jonathan Schwarz et al.2017 · British Machine Vision Conference · 181 citations

08Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust GatesJun Liu, Amir Shahroudy, Dong Xu et al.2017 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 504 citations In Library

09On Human Motion Prediction Using Recurrent Neural NetworksJulieta Martinez, Michael J. Black, J. Romero2017 · Computer Vision and Pattern Recognition · 1.1k citations In Library

10Interpretable 3D Human Action Analysis with Temporal Convolutional NetworksTae Soo Kim, A. Reiter2017 · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 662 citations In Library

11Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence TransductionChunting Zhou, Graham Neubig2017 · Annual Meeting of the Association for Computational Linguistics · 55 citations In Library

12View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton DataPengfei Zhang, Cuiling Lan, Junliang Xing et al.2017 · IEEE International Conference on Computer Vision · 620 citations In Library

Scroll for more · 28 remaining

Similar papers

Predicting the What and How - a Probabilistic Semi-Supervised Approach to Multi-Task Human Activity ModelingJudith Bütepage, H. Kjellström, D. Kragic2019 · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 3 citations In Library

Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modelingJudith Bütepage, D. Kragic2018 · arXiv.org · 0 citations In Library

Investigating Human Activity Patterns in Conference Hall Video SurveillancesAmira Rizvi, Liam Chen, Fatima Hassan et al.2021 · Zenodo (CERN European Organization for Nuclear Research) In Library

Investigating Human Activity Patterns in Conference Hall Video SurveillancesAmira Rizvi, Liam Chen, Fatima Hassan et al.2024 · Zenodo (CERN European Organization for Nuclear Research) In Library

Investigating Human Activity Patterns in Conference Hall Video SurveillancesAmira Rizvi, Liam Chen, Fatima Hassan et al.2022 · Zenodo (CERN European Organization for Nuclear Research) In Library

Investigating Human Activity Patterns in Conference Hall Video SurveillancesAmira Rizvi, Liam Chen, Fatima Hassan et al.2024 · Zenodo (CERN European Organization for Nuclear Research) In Library

Investigating Human Activity Patterns in Conference Hall Video SurveillancesAmira Rizvi, Liam Chen, Fatima Hassan et al.2021 · Zenodo (CERN European Organization for Nuclear Research) In Library

Patents near this paper

OBJECT ACTIVITY MODELING METHODUS 7,362,806 · SAMSUNG ELECTRONICS CO., LTD. · 2008 OBJECT ACTIVITY MODELING METHODUS 7,308,030 · REGENTS OF THE UNIVERSITY OF CALIFORNIA, THE, A CORP. OF CALIFORNIA · 2007 MULTI-SOURCE MULTI-MODAL ACTIVITY RECOGNITION IN AERIAL VIDEO SURVEILLANCEUS 9,934,453 · BAE SYSTEMS INFORMATION AND ELECTRONIC SYSTEMS INTEGRATION INC. · 2018 APPARATUS AND METHOD FOR VIDEO SENSOR-BASED HUMAN ACTIVITY AND FACIAL EXPRESSION MODELING AND RECOGNITIONUS 8,755,593 · SAMSUNG ELECTRONICS CO., LTD. · 2014 LEVERAGING TEMPORAL, CONTEXTUAL AND ORDERING CONSTRAINTS FOR RECOGNIZING COMPLEX ACTIVITIES IN VIDEOUS 8,165,405 · HONDA MOTOR CO., LTD. · 2012

Source of record

arXiv