Related papers: DISCount: Counting in Large Image Collections with…

Indiscernible marine object counting encounters numerous challenges, including limited visibility in underwater scenes, mutual occlusion and overlap among objects, and the dynamic similarity in appearance, color, and texture between the…

Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, \emph{a.k.a} few-shot and zero-shot counting. In this paper, we propose a generalized framework for both few-shot and…

Crowd counting aims to predict the number of people and generate the density map in the image. There are many challenges, including varying head scales, the diversity of crowd distribution across images and cluttered backgrounds. In this…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning…

Various works have aimed at combining the inference efficiency of recurrent models and training parallelism of multi-head attention for sequence modeling. However, most of these works focus on tasks with fixed-dimension observation spaces,…

This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than…

In this project, we build a modular, scalable system that can collect, store, and process millions of satellite images. We test the relative importance of both of the key limitations constraining the prevailing literature by applying this…

The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain that the model can train on. Classification becomes more challenging when dealing with new data from a different…

This paper addresses the problem of multi-view people occupancy map estimation. Existing solutions for this problem either operate per-view, or rely on a background subtraction pre-processing. Both approaches lessen the detection…

Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer…

Photographs convey the stories of photographers to the audience. However, this story-telling aspect of photography is easily distracted by visual clutter. Informed by a pilot study, we identified the kinds of clutter that amateurs…

We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind…

Anthropogenic activities pose threats to wildlife and marine fauna, prompting the need for efficient animal counting methods. This research study utilizes deep learning techniques to automate counting tasks. Inspired by previous studies on…

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of…

Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale…

Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global…

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or…

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…