Processing...

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

Tools Click here to view this collection in the new DAP user interface

show summary fields  |   show all    
Tools



About this Collection

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


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.


Computer Vision Knowledge Representation and Machine Learning


https://doi.org/10.4225/08/5a8e0911ae52e


Mohammad Sadegh Aliakbarian
Mohammadsadegh.Aliakbarian@data61.csiro.au

Action Anticipation Deep Learning Long Short-Term Memory Computer Vision


:

Encouraging LSTMs To Anticipate Actions Very Early

Attribution

Source code accompanying the publication of a conference paper at the 2017 International Conference on Computer Vision


Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson, 2017, Encouraging LSTMs To Anticipate Actions Very Early. In Proc. 2017 Int. Conf. Comput. Vision (ICCV), IEEE


GPLv3 Licence with CSIRO Disclaimer


CSIRO (Australia), Australian Centre For Robotic Vision (Australia), Australian National University (Australia)


Aliakbarian, Mohammad Sadegh; Saleh, Fatemeh Sadat; Salzmann, Mathieu; Fernando, Basura; Petersson, Lars; Andersson, Lars (2018): Multi-Stage LSTM (MS-LSTM) for Action Anticipation. v1. CSIRO. Software Collection. https://doi.org/10.4225/08/5a8e0911ae52e


All Rights (including copyright) CSIRO 2018.


The metadata and files (if any) are available to the public.

show all

About this Project

Legacy





Mohammad Sadegh Aliakbarian


Fatemeh Sadat Saleh


Mathieu Salzmann


Basura Fernando


Lars Petersson


Lars Andersson


Others were also interested in

  • The Globally-Optimal Pose And Correspondences (GOPAC) Algorithm....
    view
  • Synthetic Data for Non-rigid 3D Reconstruction using a Moving RGB-D Camera....
    view
  • Data61 Pedestrian Dataset....
    view