Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization

By Runpeng Cui, Hu Liu, Changshui Zhang. Computer Vision and Pattern Recognition, 2017

324 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental and Educational Psychology, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/a3c850001340266d4b2e7479f78387b5fda0815c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Developmental and Educational Psychology

In Human-Computer Interaction

Citations in the corpus

MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language (2018, methodology): “esults in this challenging, uncontrolled data set and we propose it as powerful network for sign language recognition. Method ASL100 ASL200 ASL500 ASL1000 Naive classiﬁer 4.86 2.49 1.05 0.58 VGG+LSTM [17,18] 33.42 21.21 5.86 - HCN [77] 73.98 60.29 43.83 32.50 I3D [10] 95.16 93.79 89.80 81.08 Table 4”
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training (2019, methodology): “Different from our previous work [36], we propose a distinctive segment-gloss alignment method to learn from the outputs of our sequence learning module, and we provide an explicit illustration for our iterative training scheme, by proving the training of feature extraction module to be maximizing t”
MMTM: Multimodal Transfer Module for CNN Fusion (2019, background): “Furthermore, some CNN-based models utilize recurrent architectures to capture the temporal information [72, 9, 12, 76].”
Video-based Sign Language Recognition without Temporal Segmentation (2018, methodology): “Both Deep Hand and Recurrent CNN are extensions to CNN.”
Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation (2020, background): “More recent work has tackled continuous data [42, 32, 17, 18], but the move from recognition to translation is still in its infancy [9].”
Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos (2020, background): “The best previously published state of the art [73] achieved 39.”
Improving Sign Language Translation with Monolingual Data by Sign Back-Translation (2021, background): “It inspires more research groups to study continuous SLR with large-scale vocabulary [13, 22, 34].”
Neural Sign Language Translation (2018, methodology): “Computer vision researchers adopted CTC and applied it to weakly labeled visual problems, such as lip reading [3], action recognition [30], hand shape recognition [6] and CSLR [6, 17].”