In recent years there has been remarkable progress in one computer vision application
area: object detection. One of the most challenging and fundamental problems in object …

The ubiquitous and wide applications like scene understanding, video surveillance, robotics,
and self-driving systems triggered vast research in the domain of computer vision in the most …

Despite progress in perceptual tasks such as image classification, computers still perform
poorly on cognitive tasks such as image description and question answering. Cognition is …

Semantic part localization can facilitate fine-grained categorization by explicitly isolating
subtle appearance differences associated with specific object parts. Methods for pose …

Scaling up fine-grained recognition to all domains of fine-grained objects is a challenge the
computer vision community will need to face in order to realize its goal of recognizing all …

Current approaches for fine-grained recognition do the following: First, recruit experts to
annotate a dataset of images, optionally also collecting more structured data in the form of …

Part models of object categories are essential for challenging recognition tasks, where
differences in categories are subtle and only reflected in appearances of small parts of the …

Most convolutional neural networks (CNNs) lack midlevel layers that model semantic parts
of objects. This limits CNN-based methods from reaching their full potential in detecting and …

We propose a fine-grained recognition system that incorporates part localization, alignment,
and classification in one deep neural network. This is a nontrivial process, as the input to the …

Two things seem to be indisputable in the contemporary deep learning discourse: 1. The
categorical cross-entropy loss after softmax activation is the method of choice for …