One-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM

Rodriguez, Mario; Orrite, Carlos; Medrano, Carlos; Makris, Dimitrios

doi:10.1109/tcyb.2016.2558447

Cited by 30 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core idea of this type of method is to use the knowledge of the existing categories in the training set at the training stage, and to make some new classes could be possibly recognized at the recognition stage. For example, Rodriguez et al [23] proposed a method that uses a universal background model of local descriptors obtained from source databases available on-line and adapts it to a new sequence in the target scenario through maximum posteriori adaptation, thus achieving one-shot learning of human activity. Tan et al [24] combined the traditional convolutional features with the user's click features of an image, which significantly improved the accuracy and stability of image recognition in the task of one-shot learning.…”

Section: Related Workmentioning

confidence: 99%

TwinNet: A Symmetrically Structured Convolutional Architecture for Identifying Tibetan Characters

Hao

Wang

Lin

et al. 2022

Preprint

View full text Add to dashboard Cite

Although the Tibetan language is widely used, its intelligent application is seriously lagging behind. Most studies on character recognition have almost ignored minority languages like Tibetan. For the purpose of recognizing Tibetan characters, a convolutional architecture named TwinNet is proposed in this work. Specifically, two parallel convolutional sub-networks sharing the same parameters were firstly carefully designed and connected using an energy function, thus achieving Tibetan character recognition via one-shot verification task based on similarity metric. Second, a fuzzy c-means clustering module based on statistical laws of Tibetan characters was integrated into the pipeline of TwinNet, thus greatly reducing the search space at the recognition stage. Third, a Tibetan similar character dataset (TSCD) is constructed after sufficient amount of mining and analysis work, providing data support for training supervised models. The results of binary classification experiment demonstrate that TwinNet can differentiate the similar and dissimilar image pairs with a recall of 0.92, a precision of 0.89, an accuracy of 0.90, an F-1 score of 0.90 and a Kappa coefficient of 0.82. Furthermore, the consistency between the output TwinNet and the subjective evaluation by Tibetan-speaking volunteers is also evaluated. The experimental results support the idea that the similarity evaluation of Tibetan characters by TwinNet is highly consistent with that of humans, the indicator of SROCC, PLCC and RMSE are 0.68, 0.84 and 0.04, respectively. The results of character recognition experiments based on one-shot verification task show that the improved model with the integration of the fuzzy c-means clustering module has an average accuracy of 92% for regular characters and 80% for severely deformed characters.

show abstract

Section: Related Workmentioning

confidence: 99%

TwinNet: A Symmetrically Structured Convolutional Architecture for Identifying Tibetan Characters

Hao

Wang

Lin

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, the respective parameters of a probability distribution define the observation emission for a continuous observed symbol sequence. This is usually modelled by the Gaussian distribution that is defined by its mean and covariance matrix

ϰ = false(μ, normalΣ false)

[20, 29, 30]. Hence, a mixing matrix must be defined

bold-italicC = falsefalse{c_{i j} = P false(m_{t} = j | s_{t} = i false) falsefalse}

in the case of continuous HMM emission probability distribution where

j \in false[1, M false]

such that M is the number of mixture components in set

bold-italicL = falsefalse{m_{1}, \dots, m_{M} falsefalse}

.…”

Section: Variational Learning Of the Bl Hmmmentioning

confidence: 99%

Multimodal action recognition using variational‐based Beta‐Liouville hidden Markov models

Ali¹,

Bouguila

2020

IET image process

View full text Add to dashboard Cite

The visible spectrum is the most widely used modality for video media. Nonetheless, it is highly dependent on the lighting conditions. Hence, infrared (IR) imaging lower light sensitivity characterisation presents the untapped potential for robust automatic recognition systems. This is applicable to many applications including IR action recognition (AR), which is a relatively young field in IR. As such, in this study, the authors tackle IR and multimodal AR with the proposed utilisation of variational learning of Beta‐Liouville (BL) hidden Markov models (HMMs). Furthermore, to the best of the authors' knowledge, this is the first evaluation of the BL HMM in visible AR and in multimodal fusion for AR. They present the results of the proposed model on the infrared action recognition and the IOSB datasets. Experimental results demonstrate promising outcomes. The importance of using IR and multispectral fusion in AR is also highlighted by the results.

show abstract

“…The proposed method provides the best performance for DHA and KTH datasets, while provides a close second best results for Weizmann dataset. [16] 94.8 [17] 99.1 [18] 95 [19] 94.2 [19] 98.9 [20] 95.45 [21] 96.80 [10] 100 [22] 96.69 [23] 98.…”

Section: Performance Evaluationmentioning

confidence: 99%