Measuring photography aesthetics with deep CNNs

Learning Photography Aesthetics with Deep CNNs

Automatic photo aesthetic assessment is a challenging arti cial intelligence task. Existing computational approaches have focused on modeling a single aesthetic score or class (good or bad photo), however these do not provide any details on why the photograph is good or bad; or which attributes contribute to the quality of the photograph. To obtain both accuracy and human-interpretability, we a...

Measuring Fire Behavior with Photography

Photography is practical for recording and measuring some aspects of forest fire behavior i f the scale and perspective can be determined. This paper describes a photogrammetric method for measuring flame height and rate of spread for fires on flat terrain. The flames are photographed at known times wi th a camera in front of the advancing fire. Scale and perspective of the photographs are dete...

Visual Perception and the Aesthetics of Photography

Object Detectors Emerge in Deep Scene CNNs

With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these...

What Do Deep CNNs Learn About Objects?

Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters. What exactly do these parameters represent? Recent work has started to analyse CNN representations, finding that, e.g., they are invariant to some 2D transformations Fischer et al. (2014), but are confused by particular types of image nois...