Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Gao, Liqing"'
In sign language, the conveyance of human body trajectories predominantly relies upon the coordinated movements of hands and facial expressions across successive frames. Despite the recent advancements of sign language understanding methods, they oft
Externí odkaz:
http://arxiv.org/abs/2404.11111
The increase of web-scale weakly labelled image-text pairs have greatly facilitated the development of large-scale vision-language models (e.g., CLIP), which have shown impressive generalization performance over a series of downstream tasks. However,
Externí odkaz:
http://arxiv.org/abs/2404.08226
Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal modules to cap
Externí odkaz:
http://arxiv.org/abs/2403.12519
Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to
Externí odkaz:
http://arxiv.org/abs/2401.00268
Raw videos have been proven to own considerable feature redundancy where in many cases only a portion of frames can already meet the requirements for accurate recognition. In this paper, we are interested in whether such redundancy can be effectively
Externí odkaz:
http://arxiv.org/abs/2308.08327
Human body trajectories are a salient cue to identify actions in the video. Such body trajectories are mainly conveyed by hands and face across consecutive frames in sign language. However, current methods in continuous sign language recognition (CSL
Externí odkaz:
http://arxiv.org/abs/2303.03202
Hand and face play an important role in expressing sign language. Their features are usually especially leveraged to improve system performance. However, to effectively extract visual representations and capture trajectories for hands and face, previ
Externí odkaz:
http://arxiv.org/abs/2211.17081
Pooling methods are necessities for modern neural networks for increasing receptive fields and lowering down computational costs. However, commonly used hand-crafted pooling approaches, e.g., max pooling and average pooling, may not well preserve dis
Externí odkaz:
http://arxiv.org/abs/2207.08734
Publikováno v:
In Virtual Reality & Intelligent Hardware August 2024 6(4):323-337
Publikováno v:
In Neural Networks November 2024 179