Related papers: On the contrast-dependence of crowding

Visual clustering is a common perceptual task in scatterplots that supports diverse analytics tasks (e.g., cluster identification). However, even with the same scatterplot, the ways of perceiving clusters (i.e., conducting visual…

This paper investigates two fundamental descriptors of data, i.e., density distribution versus mass distribution, in the context of clustering. Density distribution has been the de facto descriptor of data distribution since the…

We study the problem of organizing a collection of objects - images, videos - into clusters, using crowdsourcing. This problem is notoriously hard for computers to do automatically, and even with crowd workers, is challenging to…

The mainstream crowd counting methods regress density map and integrate it to obtain counting results. Since the density representation to one head accords to its adjacent distribution, it embeds the same category objects with variant…

Transit surveys have to observe many stars all at once in order to compensate for the rarity of the searched events. Such surveys, especially the ones observing a deep field of view and/or broadening their stellar images, have to deal with…

Low-level "adaptive" and higher-level "sophisticated" human reasoning processes have been proposed to play opposing roles in the emergence of unpredictable collective behaviors like crowd panics, traffic jams, and market bubbles. While…

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image-plane density has no immediate physical meaning because it is…

Scatterplots are used for a variety of visual analytics tasks, including cluster identification, and the visual encodings used on a scatterplot play a deciding role on the level of visual separation of clusters. For visualization designers,…

This paper discusses how crowd and machine classifiers can be efficiently combined to screen items that satisfy a set of predicates. We show that this is a recurring problem in many domains, present machine-human (hybrid) algorithms that…

We study supervised learning problems using clustering constraints to impose structure on either features or samples, seeking to help both prediction and interpretation. The problem of clustering features arises naturally in text…

Some biological mechanisms of early vision are comparatively well understood, but they have yet to be evaluated for their ability to accurately predict and explain human judgments of image similarity. From well-studied simple connectivity…

In recent years, crowdsourcing, aka human aided computation has emerged as an effective platform for solving problems that are considered complex for machines alone. Using human is time-consuming and costly due to monetary compensations.…

Modern, state-of-the-art deep learning approaches yield human like performance in numerous object detection and classification tasks. The foundation for their success is the availability of training datasets of substantially high quantity,…

More than half of the volume of our Universe is occupied by cosmic voids. The lensing magnification effect from those under-dense regions is generally thought to give a small dimming contribution: objects on the far side of a void are…

The case grows ever stronger that the average density of matter, ordinary and dark, is less than the critical density required for a flat universe. However, most of determinations of the mass density have been dynamical, hence sensitive…

Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task lies in the…

Simplicity is held by many to be the key to general intelligence. Simpler models tend to "generalise", identifying the cause or generator of data with greater sample efficiency. The implications of the correlation between simplicity and…

Body measurements, including weight and height, are key indicators of health. Being able to visually assess body measurements reliably is a step towards increased awareness of overweight and obesity and is thus important for public health.…

We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images , we use the observation that any sub-image of a crowded scene…

This work introduces a complexity measure which addresses some conflicting issues between existing ones by using a new principle - measuring the average amount of symmetry broken by an object. It attributes low (although different)…