Proceedings ArticleDOI
Re-Sign: Re-Aligned End-to-End Sequence Modelling with Deep Recurrent CNN-HMMs
Oscar Koller,Sepehr Zargaran,Hermann Ney +2 more
- pp 3416-3424
Reads0
Chats0
TLDR
This work proposes an algorithm that treats the provided training labels as weak labels and refines the label-to-image alignment on-the-fly in a weakly supervised fashion, and embedded into an HMM the resulting deep model continuously improves its performance in several re-alignments.Abstract:
This work presents an iterative re-alignment approach applicable to visual sequence labelling tasks such as gesture recognition, activity recognition and continuous sign language recognition. Previous methods dealing with video data usually rely on given frame labels to train their classifiers. However, looking at recent data sets, these labels often tend to be noisy which is commonly overseen. We propose an algorithm that treats the provided training labels as weak labels and refines the label-to-image alignment on-the-fly in a weakly supervised fashion. Given a series of frames and sequence-level labels, a deep recurrent CNN-BLSTM network is trained end-to-end. Embedded into an HMM the resulting deep model corrects the frame labels and continuously improves its performance in several re-alignments. We evaluate on two challenging publicly available sign recognition benchmark data sets featuring over 1000 classes. We outperform the state-of-the-art by up to 10% absolute and 30% relative.read more
Citations
More filters
Journal ArticleDOI
Graph-Based Multimodal Sequential Embedding for Sign Language Translation
TL;DR: A graph-based multimodal sequential embedding network (MSeqGraph), in which multiple sequential modalities are densely correlated, and a connectionist temporal decoding strategy is adopted to explore the entire video’s temporal transition and translate the sentence.
Journal ArticleDOI
Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network.
TL;DR: In this article, a generative adversarial network (GAN) is proposed for context-aware continuous sign language recognition using a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator's predictions by modeling text information at the sentence and gloss levels.
Journal ArticleDOI
An optimized Generative Adversarial Network based continuous sign language classification
TL;DR: A novel hyperparameter based optimized Generative Adversarial Networks to classify the sign gestures is introduced, and the experimental results reveal that the H-GANs improved the accuracy and recognition rate when compared with the state-of-the-art classification methods with reduced complexity.
Journal ArticleDOI
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
TL;DR: In this paper, a Progressive Transformer Network (PTN) is proposed to translate from spoken language sentences to continuous 3D multi-channel sign pose sequences in an end-to-end manner.
Journal ArticleDOI
A Comprehensive Study on Deep Learning-Based Methods for Sign Language Recognition
TL;DR: In this article , a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted by implementing the most recent deep neural network methods in this field, a thorough evaluation on multiple publicly available datasets is performed.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.