Related papers: Dynamic Relation Transformer for Contextual Text B…

Despite their exceptional generative abilities, large text-to-image diffusion models, much like skilled but careless artists, often struggle with accurately depicting visual relationships between objects. This issue, as we uncover through…

A comprehensive representation of an image requires understanding objects and their mutual relationship, especially in image-to-graph generation, e.g., road network extraction, blood-vessel network extraction, or scene graph generation.…

Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make the task of crack segmentation extremely challenging. In…

The DEtection TRansformer (DETR) algorithm has received considerable attention in the research community and is gradually emerging as a mainstream approach for object detection and other perception tasks. However, the current field lacks a…

Image captioning is shown to be able to achieve a better performance by using scene graphs to represent the relations of objects in the image. The current captioning encoders generally use a Graph Convolutional Net (GCN) to represent the…

Scene text image super-resolution aims to increase the resolution and readability of the text in low-resolution images. Though significant improvement has been achieved by deep convolutional neural networks (CNNs), it remains difficult to…

We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors -…

Long-term time series forecasting (LTSF) has been widely applied in finance, traffic prediction, and other domains. Recently, patch-based transformers have emerged as a promising approach, segmenting data into sub-level patches that serve…

Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image, and deep learning based copy-move forgery detection methods are in the ascendant. These deep learning based methods heavily rely on synthetic…

Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture…

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. We think the key to skeleton-based action recognition is a skeleton hanging in frames, so we focus on how the…

Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are…

Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation,…

Transfer learning paradigm has driven substantial advancements in various vision tasks. However, as state-of-the-art models continue to grow, classical full fine-tuning often becomes computationally impractical, particularly in multi-task…

Artistic text recognition is an extremely challenging task with a wide range of applications. However, current scene text recognition methods mainly focus on irregular text while have not explored artistic text specifically. The challenges…

With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP),…

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…

Named entity recognition (NER) is an important research problem in natural language processing. There are three types of NER tasks, including flat, nested and discontinuous entity recognition. Most previous sequential labeling models are…

Pattern recognition based on RGB-Event data is a newly arising research topic and previous works usually learn their features using CNN or Transformer. As we know, CNN captures the local features well and the cascaded self-attention…

Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic,…