Search Results for author:
Found 16 papers, 6 papers with code
Precision Enhancement of 3D Surfaces from Multiple Compressed Depth Maps
In texture-plus-depth representation of a 3D scene, depth maps from different camera viewpoints are typically lossily compressed via the classical transform coding / coefficient quantization paradigm.
Speech Enhancement In Multiple-Noise Conditions using Deep Neural Networks
In this paper we consider the problem of speech enhancement in real-world like conditions where multiple noises can simultaneously corrupt speech.
Sound
Joint Denoising / Compression of Image Contours via Shape Prior and Context Tree
We first prove theoretically that in general a joint denoising / compression approach can outperform a separate two-stage approach that first denoises then encodes contours lossily.
Foreground Detection in Camouflaged Scenes
This paper proposes a texture guided weighted voting (TGWV) method which can efficiently detect foreground objects in camouflaged scenes.
Deep Learning Based Speech Beamforming
On the other hand, deep learning based enhancement approaches are able to learn complicated speech distributions and perform efficient inference, but they are unable to deal with variable number of input channels.
A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain
Conventional methods cannot distinguish the foreground from background due to the small differences between them and thus suffer from under-detection of the camouflaged foreground objects.
RePr: Improved Training of Convolutional Filters
We show that by temporarily pruning and then restoring a subset of the model's filters, and repeating this process cyclically, overlap in the learned features is reduced, producing improved generalization.
TAP: Text-Aware Pre-training for Text-VQA and Text-Caption
Due to this aligned representation learning, even pre-trained on the same downstream task dataset, TAP already boosts the absolute accuracy on the TextVQA dataset by +5. 4%, compared with a non-TAP baseline.
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents.
Ranked #1 on
Key Information Extraction
on SROIE
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding.
Ranked #13 on
Document Image Classification
on RVL-CDIP
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
Text recognition is a long-standing research problem for document digitalization.
Ranked #3 on
Handwritten Text Recognition
on IAM
Improving Structured Text Recognition with Regular Expression Biasing
We study the problem of recognizing structured text, i. e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing.
Understanding Long Documents with Different Position-Aware Attentions
Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input.
Diffusion-based Document Layout Generation
Our empirical analysis shows that our diffusion-based approach is comparable to or outperforming other previous methods for layout generation across various document datasets.
From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding
Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens.
XFUND: A Benchmark Dataset for Multilingual Visually Rich Form Understanding
Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities.
