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
Posted Content
Visual Alignment Constraint for Continuous Sign Language Recognition
TL;DR: Wang et al. as discussed by the authors proposed a Visual Alignment Constraint (VAC) to enhance the feature extractor with more alignment supervision, which is composed of two auxiliary losses: one makes predictions based on visual features only, and the other aligns short-term visual and long-term contextual features.
Proceedings ArticleDOI
Translation of Sign Language Glosses to Text Using Sequence-to-Sequence Attention Models
TL;DR: This is the first work that used Sequence to Sequence models with attention mechanism to translate American gloss sentences to English, and the results are very promising and can be useful for the further implementation of a full sign language recognition system.
Posted Content
BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues.
Samuel Albanie,Gül Varol,Liliane Momeni,Triantafyllos Afouras,Joon Son Chung,Neil Fox,Andrew Zisserman +6 more
TL;DR: The BSL-1K dataset as discussed by the authors is a collection of British Sign Language (BSL) signs of unprecedented scale, which can be used to train strong sign recognition models for co-articulated signs in BSL and additionally form excellent pretraining for other sign languages.
Proceedings ArticleDOI
Fingerspelling Detection in American Sign Language
TL;DR: In this article, a multi-task learning model was proposed to detect fingerspelling in raw, untrimmed sign language videos, incorporating pose estimation and fingerspelling recognition along with detection.
Journal ArticleDOI
Graph-Based Multimodal Sequential Embedding for Sign Language Translation
TL;DR: In this paper , a graph-based multimodal sequential embedding network (MSeqGraph) is proposed, in which multiple sequential modalities are densely correlated and a graph embedding unit (GEU) is designed to realize the intra-modal and intermodal correlations, and a hierarchical GEU stacker with a pooling-based skip connection is proposed.
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.