Related papers: Light-weight Document Image Cleanup using Perceptu…
The number of published PDF documents has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. In this paper, we present a novel approach to document…
This paper proposes an extremely lightweight phone-based transducer model with a tiny decoding graph on edge devices. First, a phone synchronous decoding (PSD) algorithm based on blank label skipping is first used to speed up the transducer…
The advancement of imaging devices and countless images generated everyday pose an increasingly high demand on image denoising, which still remains a challenging task in terms of both effectiveness and efficiency. To improve denoising…
Convolutional Neural Network (CNN) has been widely used in unstructured datasets, one of which is image denoising. Image denoising is a noisy image reconstruction process that aims to reduce additional noise that occurs from the noisy image…
Neural Encoders are frequently used in the NLP domain to perform dense retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the…
Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…
Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important…
Text erasure from an image is helpful for various tasks such as image editing and privacy preservation. In this paper, we present TPFNet, a novel one-stage (end-toend) network for text removal from images. Our network has two parts: feature…
Text Detection and recognition is a one of the important aspect of image processing. This paper analyzes and compares the methods to handle this task. It summarizes the fundamental problems and enumerates factors that need consideration…
The Image Signal Processor (ISP) is a fundamental component in modern smartphone cameras responsible for conversion of RAW sensor image data to RGB images with a strong focus on perceptual quality. Recent work highlights the potential of…
In low-light conditions, a conventional camera imaging pipeline produces sub-optimal images that are usually dark and noisy due to a low photon count and low signal-to-noise ratio (SNR). We present a data-driven approach that learns the…
When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as…
A growing number of commercially available mobile phones come with integrated high-resolution digital cameras. That enables a new class of dedicated applications to image analysis such as mobile visual search, image cropping, object…
Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…
Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this work, we argue that these embeddings, while effective, are…
Text recognition in natural scene is a challenging problem due to the many factors affecting text appearance. In this paper, we presents a method that directly transcribes scene text images to text without needing of sophisticated character…
Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…
Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic information, it is inevitable that spatial details (e.g.,…
In this thesis, we study multiple tasks related to document layout analysis such as the detection of text lines, the splitting into acts or the detection of the writing support. Thus, we propose two deep neural models following two…
Soft context formation is a lossless image coding method for screen content. It encodes images pixel by pixel via arithmetic coding by collecting statistics for probability distribution estimation. Its main pipeline includes three stages,…