Related papers: ROI-based Deep Image Compression with Swin Transfo…
Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and…
PURPOSE: Deep learning methods for classifying prostate cancer (PCa) in ultrasound images typically employ convolutional networks (CNNs) to detect cancer in small regions of interest (ROI) along a needle trace region. However, this approach…
The existing Optical Character Recognition (OCR) systems are capable of recognizing images with horizontal texts. However, when the rotation of the texts increases, it becomes harder to recognizing these texts. The performance of the OCR…
This paper presents a deep learning-based framework for enhancing radar systems in the presence of interference, leveraging Reconfigurable Intelligent Surfaces (RIS). The proposed technique uses a modified MUSIC algorithm to estimate the…
Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are…
Region-of-Interest (ROI) location information in videos has many practical usages in video coding field, such as video content analysis and user experience improvement. Although ROI-based coding has been studied widely by many researchers…
To enhance on-road environmental perception for autonomous driving, accurate and real-time analytics on high-resolution video frames generated from on-board cameras be-comes crucial. In this paper, we design a lightweight object location…
Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing…
Image compression techniques typically focus on compressing rectangular images for human consumption, however, resulting in transmitting redundant content for downstream applications. To overcome this limitation, some previous works propose…
In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided. The challenges lie in how to online update the…
There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the…
ROI extraction is an active but challenging task in remote sensing because of the complicated landform, the complex boundaries and the requirement of annotations. Weakly supervised learning (WSL) aims at learning a mapping from input image…
Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…
Deep learning techniques have been applied in the context of image super-resolution (SR), achieving remarkable advances in terms of reconstruction performance. Existing techniques typically employ highly complex model structures which…
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs…
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing continuous signals independently of grid resolution. In this paper, we propose a high-fidelity neural compression framework based on a SIREN…
There is tremendous scope for improving the energy efficiency of embedded vision systems by incorporating programmable region-of-interest (ROI) readout in the image sensor design. In this work, we study how ROI programmability can be…
Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to its complex real-world challenges. To solve this problem, we…
CMOS sensors employ row-wise acquisition mechanism while imaging a scene, which can result in undesired motion artifacts known as rolling shutter (RS) distortions in the captured image. Existing single image RS rectification methods attempt…
Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…