Software

Multi-Stage LSTM (MS-LSTM) for Action Anticipation

Commonwealth Scientific and Industrial Research Organisation

Aliakbarian, Mohammad Sadegh ; Saleh, Fatemeh Sadat ; Salzmann, Mathieu ; Fernando, Basura ; Petersson, Lars ; Andersson, Lars

Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]

ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.4225/08/5a8e0911ae52e&rft.title=Multi-Stage LSTM (MS-LSTM) for Action Anticipation&rft.identifier=https://doi.org/10.4225/08/5a8e0911ae52e&rft.publisher=Commonwealth Scientific and Industrial Research Organisation&rft.description=Multi-Stage LSTM (MS-LSTM) is a deep sequence learning architecture that leverage two types of descriptors, i.e., action-aware and context-aware features to determine the action label. To do it at early stages, MS-LSTM is trained with a novel loss function that encourages correct prediction as early as possible.\nLineage: Source code accompanying the publication of a conference paper at the 2017 International Conference on Computer Vision&rft.creator=Aliakbarian, Mohammad Sadegh &rft.creator=Saleh, Fatemeh Sadat &rft.creator=Salzmann, Mathieu &rft.creator=Fernando, Basura &rft.creator=Petersson, Lars &rft.creator=Andersson, Lars &rft.date=2018&rft.edition=v1&rft.relation=http://openaccess.thecvf.com/content_ICCV_2017/papers/Aliakbarian_Encouraging_LSTMs_to_ICCV_2017_paper.pdf&rft_rights=GPLv3 Licence with CSIRO Disclaimer https://research.csiro.au/dap/licences/gplv3-licence-with-csiro-disclaimer/&rft_rights=Data is accessible online and may be reused in accordance with licence conditions&rft_rights=All Rights (including copyright) CSIRO 2018.&rft_subject=Action Anticipation&rft_subject=Deep Learning&rft_subject=Long Short-Term Memory&rft_subject=Computer Vision&rft_subject=Computer vision&rft_subject=Computer vision and multimedia computation&rft_subject=INFORMATION AND COMPUTING SCIENCES&rft_subject=Machine learning not elsewhere classified&rft_subject=Machine learning&rft.type=Computer Program&rft.language=English Access the software

Cite Saved to MyRDA Save to MyRDA

Licence & Rights:

Open Licence view details

Gpl

GPLv3 Licence with CSIRO Disclaimer
https://research.csiro.au/dap/licences/gplv3-licence-with-csiro-disclaimer/

Data is accessible online and may be reused in accordance with licence conditions

All Rights (including copyright) CSIRO 2018.

Access:

Open view details

Accessible for free

Contact Information

Brief description

Multi-Stage LSTM (MS-LSTM) is a deep sequence learning architecture that leverage two types of descriptors, i.e., action-aware and context-aware features to determine the action label. To do it at early stages, MS-LSTM is trained with a novel loss function that encourages correct prediction as early as possible.
Lineage: Source code accompanying the publication of a conference paper at the 2017 International Conference on Computer Vision

Available: 2018-02-22

This dataset is part of a larger collection

Click to explore relationships graph

Subjects

Action Anticipation | Computer Vision | Computer Vision | Computer Vision and Multimedia Computation | Deep Learning | Information and Computing Sciences | Long Short-Term Memory | Machine Learning | Machine Learning Not Elsewhere Classified |

User Contributed Tags

Login to tag this record with meaningful keywords to make it easier to discover

Identifiers

DOI : 10.4225/08/5A8E0911AE52E
Local : 102.100.100/62874

Similar data you may be interested in: