Local–Global Transformer Neural Network for temporal action segmentation

Tian, Xin; Yao, Jin; Tang, Xianglong

doi:10.1007/s00530-022-00998-4

Cited by 12 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These experiments are conducted on the scene text image dataset TextZoom to help in comparing with state-of-arts. To evaluate BT-STISR, we conduct qualitative and quantitative experiments with the SOTA SISR and STISR methods, SRCNN [19], HAN [21], PCAN [26], TSRN [27], TBSRN [11] and TATT [15].…”

Section: Experiments Resultsmentioning

confidence: 99%

“…It plays a critical role in improving the legibility and usability of captured text [22,26]. TSRN [27] consists of incorporating both text-specific modules and a global contextual module to capture fine text details and preserve its structural consistency. It leverages a textspecific enhancement network and a text-specific fusion network to generate HR text images.…”

Section: Scene Text Image Super Resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Batch-Transformer for Scene Text Image Super Resolution

Sun,

Xie,

2024

Preprint

View full text Add to dashboard Cite

Recognizing low-resolution text images is challenging as they often lose their detailed information, leading to poor recognition accuracy. Moreover, the traditional methods, based on deep Convolutional Neural Networks (CNNs), are not effective enough for some low-resolution text images with dense characters. In this paper, a novel CNN-based Batch-Transformer network for Scene Text Image Super Resolution (BT-STISR) method is proposed to address this problem. In order to obtain the text information for text reconstruction, a pre-trained text prior module is employed to extract text information. Then a novel two pipeline batch transformer-based module is proposed, leveraging self-attention and global attention mechanisms to exert the guidance of text prior to the text reconstruction process. Experimental study on a benchmark dataset TextZoom shows that the proposed method BT-STISR achieves the best state-of-the-art performance in terms of Structural Similarity (SSIM) and Peak signal-to-noise ratio (PSNR) metrics compared to some latest methods.

show abstract