6 Hits in 4.7 sec

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [article]

Shreyank N Gowda, Laura Sevilla-Lara, Frank Keller, Marcus Rohrbach
2021 arXiv   pre-print
Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes.  ...  We optimize theclustering using Reinforcement Learning which we show iscritical for our approach to work.  ...  We call our proposed method CLASTER, for CLustering for Action recognition in zero-ShoT lEaRning, and show that it significantly outperforms all existing methods across all standard zero-shot action recognition  ... 
arXiv:2101.07042v2 fatcat:w5qvvnv3rjdotaqadf5k4v6fvq

A New Split for Evaluating True Zero-Shot Action Recognition [article]

Shreyank N Gowda, Laura Sevilla-Lara, Kiyoon Kim, Frank Keller, Marcus Rohrbach
2021 arXiv   pre-print
In this paper, we propose a new split for true zero-shot action recognition with no overlap between unseen test classes and training or pre-training classes.  ...  zero-shot action recognition.  ...  CLASTER [7] uses clustering of visual-semantic embeddings optimised by reinforcement learning.  ... 
arXiv:2107.13029v2 fatcat:dirm6mbfajardfxmi3fjgxkhfy

Zero-Shot Action Recognition with Transformer-based Video Semantic Embedding [article]

Keval Doshi, Yasin Yilmaz
2022 arXiv   pre-print
While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction.  ...  Specifically, we advocate for a concrete formulation for zero-shot action recognition that avoids an exact overlap between the training and testing classes and also limits the intra-class variance; and  ...  , 44] for zero-shot action recognition.  ... 
arXiv:2203.05156v1 fatcat:ny7p72hia5govbg2g6qboew3da

Tell me what you see: A zero-shot action recognition method based on natural language descriptions [article]

Valter Estevam and Rayson Laroca and David Menotti and Helio Pedrini
2021 arXiv   pre-print
Recently, several approaches have explored the detection and classification of objects in videos to perform Zero-Shot Action Recognition with remarkable results.  ...  The projection onto this space is straightforward for both types of information, visual and semantic, because they are sentences, enabling the classification with nearest neighbour rule in this shared  ...  CLASTER: clustering with reinforcement learning for zero-shot [33] Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J., 2013.  ... 
arXiv:2112.09976v1 fatcat:5bvci2dyjnbyjbvo7qagnuzbpy

Morphed vertical tailplane assessment for certification requirements

Miguel Angel Castillo-Acero
2015 Zenodo  
The results, opinions, conclusions, etc. presented in this work are those of the author(s) only and do not necessarily represent the position of the JU; the JU is not responsible for any use made of the  ...  For the base year clasterization to 9 clusters has been made by city populations, city GDP and GDP per capita.  ...  The paper will include: Detailed justification for choosing the normal mixture approach for clusterization, clustering parameters and number of clusters; Description of cluster dynamic approach; Cities  ... 
doi:10.5281/zenodo.3905083 fatcat:jegirrd5jbgeho7qtr7o3sfzpi

Inferring social behavior and interaction on twitter by combining metadata about users & messages

Marc Cheong
Rarely are metadata from both the user and message domains analyzed in tandem with each other.  ...  In doing so, I contributed to the development of novel inference algorithms, and frameworks to harvest raw metadata from Twitter for the provision of ample data for the evaluation of my [...]  ...  a SOM for "to provide a richer understanding of the data" [Claster et al., 2010] .  ... 
doi:10.4225/03/58b5009d3726a fatcat:x7xi2espbbd73jlg4s45hifclu