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
Book ChapterDOI
Automatic Dense Annotation of Large-Vocabulary Sign Language Videos
TL;DR: This article proposed a scalable framework to increase the density of automatic annotations by making use of synonyms and subtitle-signing alignment, and showed the value of pseudo-labels from a sign recognition model as a way of sign spotting.
Proceedings ArticleDOI
Fingerspelling Recognition in the Wild with Fixed-Query based Visual Attention
TL;DR: In this paper, a multi-scale attention with fixed-queries model was proposed to recognize fingerspelling in the wild using RGB video sequences without any frame-level supervision, where the attention mechanism is intuitive from a human perspective.
Journal ArticleDOI
A multi-modal fusion framework for continuous sign language recognition based on multi-layer self-attention mechanism
TL;DR: A 3D convolution residual neural network (CR3D) and a multi-layer self-attention network (ML-SAN) for the feature extraction stage and a cross-modal spatial mapping loss function, which improves the precision of CSLR by studying the spatial similarity between the video and text domains.
Journal ArticleDOI
Continuous sign language recognition based on iterative alignment network and attention mechanism
Posted Content
Fingerspelling recognition in the wild with iterative visual attention
Bowen Shi,Aurora Martinez Del Rio,Jonathan Keane,Diane Brentari,Greg Shakhnarovich,Karen Livescu +5 more
TL;DR: The authors proposed an end-to-end model based on an iterative attention mechanism, without explicit hand detection or segmentation, which dynamically focuses on increasingly high-resolution regions of interest.
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.