paper-with-me

Papers

Dynamic Relation Transformer for Contextual Text Block Detection

2024-01-17 · Jiawei Wang, Shunchi Zhang, Kai Hu, Chixiang Ma, Zhuoyao Zhong, Lei Sun, Qiang Huo

Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes. Previous methodologies have treated CTBD as either a visual relation extraction challenge within computer vision or as a sequence modeling problem from the perspective of natural language processing. We introduce a new framework that frames CTBD as a graph generation problem. This methodology consists of two essential procedures: identifying individual text units as graph nodes and discerning the sequential reading order relationships among these units as graph edges. Leveraging the cutting-edge capabilities of DQ-DETR for node detection, our framework innovates further by integrating a novel mechanism, a Dynamic Relation Transformer (DRFormer), dedicated to edge generation. DRFormer incorporates a dual interactive transformer decoder that deftly manages a dynamic graph structure refinement process. Through this iterative process, the model systematically enhances the graph's fidelity, ultimately resulting in improved precision in detecting contextual text blocks. Comprehensive experimental evaluations conducted on both SCUT-CTW-Context and ReCTS-Context datasets substantiate that our method achieves state-of-the-art results, underscoring the effectiveness and potential of our graph generation framework in advancing the field of CTBD.

📄 PDF Abstract BibTeX arXiv:2401.09232

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderGraph GenerationRelationRelation Extraction

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Contextual Transformer Networks for Visual Recognition

2021-07-26 · Yehao Li, Ting Yao, Yingwei Pan, Tao Mei

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous compu…

Image ClassificationInstance Segmentationobject-detectionObject Detection+1

HittER: Hierarchical Transformers for Knowledge Graph Embeddings

2020-08-28 · EMNLP 2021 11 · Sanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao 외

This paper examines the challenging problem of learning representations of entities and relations in a complex multi-relational knowledge graph. We propose HittER, a Hierarchical Transformer model to jointly learn Entity…

Knowledge Graph EmbeddingsLink PredictionQuestion AnsweringRelation

Transformer ASR with Contextual Block Processing

2019-10-16 · Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transform…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

PSFormer: Point Transformer for 3D Salient Object Detection

2022-10-28 · Baian Chen, Lipeng Gu, Xin Zhuang, Yiyang Shen 외

We propose PSFormer, an effective point transformer model for 3D salient object detection. PSFormer is an encoder-decoder network that takes full advantage of transformers to model the contextual information in both mult…

DecoderObjectobject-detectionObject Detection+1

Gaussian Context Transformer

2021-06-19 · CVPR 2021 1 · Dongsheng Ruan, Daiyin Wang, Yuan Zheng, Nenggan Zheng 외

Recently, a large number of channel attention blocks are proposed to boost the representational power of deep convolutional neural networks (CNNs). These approaches commonly learn the relationship between global cont…