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
Multi-phase Fine-Tuning: A New Fine-Tuning Approach for Sign Language Recognition
TL;DR: In this article , a multi-phase fine-tuning approach was proposed for transfer learning from typical object recognition to sign language recognition (SLR) by fine-tuning the network's weights over several phases.
Journal ArticleDOI
Multi-view motion modelled deep attention networks (M2DA-Net) for video based sign language recognition
TL;DR: The proposed multi stream CNN mixes spatial and motion modelled video sequences to create a low dimensional feature vector at multiple stages in the CNN pipeline to solve the view invariance problem into a video classification problem using attention model CNNs.
Proceedings ArticleDOI
Towards Computer-Aided Sign Language Recognition Technique: A Directional Review
Liwei Yang,Yiduo Zhu,Tao Li +2 more
TL;DR: The research status and progress in the field of SL recognition is reviewed, based on the analysis of off-the-shelf SL translation methods and systems, and a number of recognition methods are described.
Proceedings ArticleDOI
Data-driven development of Virtual Sign Language Communication Agents
TL;DR: This study proves the sequence to sequence neural network model trainable and possibly applicable in real-life with an extended dataset, which shall be tested for deployment in virtual translation assistants in the following.
Proceedings ArticleDOI
Two-Stream Network for Sign Language Recognition and Translation
TL;DR: Wei et al. as mentioned in this paper introduced a dual visual encoder containing two separate streams to model both the raw videos and the keypoint sequences generated by an off-the-shelf keypoint estimator.
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.