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
Proceedings ArticleDOI
Unsupervised method for video action segmentation through spatio-temporal and positional-encoded embeddings
TL;DR: This work proposes a novel action segmentation method that requires no prior video analysis and no annotated data, and involves extracting spatio-temporal features from videos using a pre-trained deep network.
Proceedings ArticleDOI
Weakly-supervised Fingerspelling Recognition in British Sign Language Videos
TL;DR: In this article , a Transformer architecture was proposed to detect and recognize sequences of letters signed using fingerspelling in British Sign Language (BSL) using weak annotations from subtitles for training.
Proceedings ArticleDOI
Sign Language Video Retrieval with Free-Form Textual Queries
TL;DR: In this article , the authors propose a framework for interleaving iterative rounds of sign spotting and feature alignment to expand the scope and scale of available training data, and validate the effectiveness of SPOT-ALIGN for learning a robust sign video embedding.
Proceedings ArticleDOI
Visual-Lexical Alignment Constraint for Continuous Sign Language Recognition
TL;DR: In this paper , a Visual-Lexical Alignment Constraint (VLAC) with an improved self-distillation-based alignment supervision was proposed to enhance the generalization of the visual extractor.
Proceedings ArticleDOI
American Sign Language Fingerspelling Recognition using Attention Model
TL;DR: In this paper , a Bi-LSTM network with Connectionist Temporal Classification (CTC) was used to predict the sign and achieved an accuracy of 57% on ChicagoFSWild dataset for Fingerspelling recognition task.
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.