1,721,735 research outputs found
Computer vision for the analysis of cellular activity
Full text linkIn the field of cell biology, there is an increasing use of time-lapse data to understand cellular function. Using automated microscopes, large numbers of images can be acquired, delivering videos of cell samples over time. Analysing the images manually is extremely time consuming as there are typically thousands of individual images in any given sequence. Additionally, decisions made by those analysing the images, e.g. labelling a mitotic phase (one of a set of distinct sequential stages of cell division) can be subjective, especially around transition boundaries between phases, leading to inconsistencies in the annotation. There is therefore a need for tools which facilitate automated high-throughput analysis. In this thesis we develop systems to automatically detect, track and analyse sub-cellular structures in image sequences to address biological research needs in three areas: (i) Mitotic phase labelling, (ii) Mitotic defect detection, and (iii) Cell volume estimation. We begin by presenting a system for automated segmentation and mitotic phase labelling using temporal models. This work takes the novel approach of using temporal features evaluated over the whole of the mitotic phases rather than over single frames, thereby capturing the distinctive behaviour over the phases. We compare and contrast three different temporal models: Dynamic Time Warping, Hidden Markov Models, and Semi Markov Models. A new loss function is proposed for the Semi Markov model to make it more robust to inconsistencies in data annotation near transition boundaries. We then present an approach for detecting subtle chromosome segregation errors in mitosis in embryonic stem cells, targeting two cases: misaligned chromosomes in a metaphase cell, and lagging chromosomes between anaphase cells. We additionally explore an unsupervised approach to detect unusual mitotic occurrences and test its applicability to detecting misaligned metaphase chromosomes. Finally, we describe a fully automated method, suited to high-throughput analysis, for estimating the volume of spherical mitotic cells based on a learned membrane classifier and a circular Hough transform. We also describe how it is being used further in biological research
Discriminative learned dictionaries for local image analysis
No full text1 online resource (PDF, 8 pages, includes illustrations)Mairal, Julien; Bach, Francis; Ponce, Jean; Sapiro, Guillermo; Zisserman, Andrew. (2008). Discriminative learned dictionaries for local image analysis. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/179942
Learning to lip read words by watching videos
Full text linkOur aim is to recognise the words being spoken by a talking face, given only the video but not the audio. Existing works in this area have focussed on trying to recognise a small number of utterances in controlled environments (e.g. digits and alphabets), partially due to the shortage of suitable datasets. We make three novel contributions: first, we develop a pipeline for fully automated data collection from TV broadcasts. With this we have generated a dataset with over a million word instances, spoken by over a thousand different people; second, we develop a two-stream convolutional neural network that learns a joint embedding between the sound and the mouth motions from unlabelled data. We apply this network to the tasks of audio-to-video synchronisation and active speaker detection; third, we train convolutional and recurrent networks that are able to effectively learn and recognize hundreds of words from this large-scale dataset. In lip reading and in speaker detection, we demonstrate results that exceed the current state-of-the-art on public benchmark datasets
Voxceleb: Large-scale speaker verification in the wild
No full textThe objective of this work is speaker recognition under noisy and unconstrained conditions. We make two key contributions. First, we introduce a very large-scale audio-visual dataset collected from open source media using a fully automated pipeline. Most existing datasets for speaker identification contain samples obtained under quite constrained conditions, and usually require manual annotations, hence are limited in size. We propose a pipeline based on computer vision techniques to create the dataset from open-source media. Our pipeline involves obtaining videos from YouTube; performing active speaker verification using a two-stream synchronization Convolutional Neural Network (CNN), and confirming the identity of the speaker using CNN based facial recognition. We use this pipeline to curate VoxCeleb which contains contains over a million 'real-world' utterances from over 6000 speakers. This is several times larger than any publicly available speaker recognition dataset. Second, we develop and compare different CNN architectures with various aggregation methods and training loss functions that can effectively recognise identities from voice under various conditions. The models trained on our dataset surpass the performance of previous works by a significant margin. (C) 2019 The Authors. Published by Elsevier Ltd.
You Said That?: Synthesising Talking Faces from Audio
Full text linkWe describe a method for generating a video of a talking face. The method takes still images of the target face and an audio speech segment as inputs, and generates a video of the target face lip synched with the audio. The method runs in real time and is applicable to faces and audio not seen at training time. To achieve this we develop an encoder–decoder convolutional neural network (CNN) model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on unlabelled videos using cross-modal self-supervision. We also propose methods to re-dub videos by visually blending the generated face into the source video frame using a multi-stream CNN model
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Visual recognition in art using machine learning
Full text linkThis thesis is concerned with the problem of visual recognition in art â such as finding
the objects (e.g. cars, cows and cathedrals) present in a painting, or identifying the subject
of an oil portrait. Solving this problem is extremely beneficial to art historians, who are
often interested in determining when an object first appeared in a painting or how the
portrayal of an object has evolved over time. It allows them to avoid the unenviable task
of finding paintings for study manually. However, visual recognition of art is a challenging
problem, in part due to the lack of annotation in art. A solution is to train recognition
models on natural, photographic images. These models have to overcome a domain shift
when applied to art.
Firstly, a thorough evaluation of the domain shift problem is conducted for the task of
image classification in paintings; the performance of natural image-trained and painting-
trained classifiers on a fixed set of paintings are compared for both shallow (Fisher Vec-
tors) and deep image representations (Convolutional Neural Networks â CNNs) to exam-
ine the performance gap across domains. Then, we show that this performance gap can
be ameliorated by classifying regions using detectors.
We next consider the problem of annotating gods and animals on classical Greek vases,
starting from a large dataset of images of vases with associated brief text descriptions. To
solve this, we develop a weakly supervised learning approach to solve the correspondence
problem between the descriptions and unknown image regions.
Then, we study the problem of matching photos of a person to paintings of that person,
in order to retrieve similar paintings given a query photo. We show that performance at
this task can be improved substantially by learning with a combination of photos and
paintings â either by learning a linear projection matrix common across facial identities,
or by fine-tuning a CNN.
Finally, we present several applications of this research. These include a system that
learns object classifiers on-the-fly from images crawled off the web, and uses these to find
a variety of objects in very large datasets of art. We show that this research has resulted
in the discovery of over 250,000 new object annotations across 93,000 paintings on the
public Art UK website.
</p
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
