Past year
All results
- All results
- Verbatim
7 days ago · Through hierarchical encoding and prototype learning, HierCode generates unique and informative representations for each Chinese character.
Nov 24, 2023 · We present a novel approach for automatically classifying illustrations from historical Chinese local gazetteers using modern deep learning techniques.
Oct 13, 2023 · As shown in Table 2, the CCR-CLIP method exhibits higher time efficiency than decomposition-based CCR methods. 4.2. Results on Chinese Text Recognition. We ...
Missing: Categorization. | Show results with:Categorization.
Jan 11, 2024 · We propose a large-scale continual learning framework based on the convolutional prototype network (CPN), which does not save raw data for old classes.
Missing: High Categorization.
Sep 21, 2023 · This paper introduces the utilization of Long Short-Term Memory (LSTM) neural networks and TextCNN to establish a text classifier for classifying and reviewing ...
Mar 25, 2024 · This paper presents an effective approach for the offline recognition of unconstrained handwritten Chinese texts.
Missing: Categorization. | Show results with:Categorization.
May 10, 2024 · In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of ...
Missing: Categorization. | Show results with:Categorization.
Apr 18, 2024 · This survey is concerned with data augmentation methods for textual classification and aims at providing a concise and comprehensive overview for researchers ...
Apr 14, 2024 · Researchers at Tsinghua University in China have developed a revolutionary new AI chip that uses light instead of electricity to process data.
Missing: Categorization. | Show results with:Categorization.
Jul 20, 2024 · Few-shot action recognition aims to address the high cost and impracticality of manually labeling complex and variable video data in action recognition.