Detecção de posicionamento é a tarefa de automaticamente identificar se o autor de um texto é favorável, contrário, ou nem favorável e nem contrário a uma dada proposição ou alvo. Com o amplo uso do Twitter como plataforma para expressar opiniões e posicionamentos, a análise automatizada deste conteúdo torna-se de grande valia para empresas, organizações e figuras públicas. Em geral, os trabalhos que exploram tal tarefa adotam abordagens supervisionadas ou semi-supervisionadas. O presente trabalho propõe e avalia um processo não supervisionado de detecção de posicionamento em textos de tweets que tem como entrada apenas o alvo e um conjunto de tweets a rotular e é baseado em uma abordagem híbrida composta por 2 etapas: a) rotulação automática de tweets baseada em um conjunto de heurísticas e b) classificação complementar baseada em aprendizado supervisionado de máquina. A proposta tem êxito quando aplicada a figuras públicas, superando o estado-da-arte. Além disso, são avaliadas alternativas no intuito de melhorar seu desempenho quando aplicada a outros domínios, revelando a possibilidade de se empregar estratégias tais como o uso de alvos e perfis semente dependendo das características de cada domínio. / Stance Detection is the task of automatically identifying if the author of a text is in favor of the given target, against the given target, or whether neither inference is likely. With the wide use of Twitter as a platform to express opinions and stances, the automatic analysis of this content becomes of high regard for companies, organizations and public figures. In general, works that explore such task adopt supervised or semi-supervised approaches. The present work proposes and evaluates a non-supervised process to detect stance in texts of tweets that has as entry only the target and a set of tweets to classify and is based on a hybrid approach composed by 2 stages: a) automatic labelling of tweets based on a set of heuristics and b) complementary classification based on supervised machine learning. The proposal succeeds when applied to public figures, overcoming the state-of-the-art. Beyond that, some alternatives are evaluated with the intention of increasing the performance when applied to other domains, revealing the possibility of use of strategies such as using seed targets and profiles depending on each domain characteristics.

Detecção de posicionamento é a tarefa de automaticamente identificar se o autor de um texto é favorável, contrário, ou nem favorável e nem contrário a uma dada proposição ou alvo. Com o amplo uso do Twitter como plataforma para expressar opiniões e posicionamentos, a análise automatizada deste conteúdo torna-se de grande valia para empresas, organizações e figuras públicas. Em geral, os trabalhos que exploram tal tarefa adotam abordagens supervisionadas ou semi-supervisionadas. O presente trabalho propõe e avalia um processo não supervisionado de detecção de posicionamento em textos de tweets que tem como entrada apenas o alvo e um conjunto de tweets a rotular e é baseado em uma abordagem híbrida composta por 2 etapas: a) rotulação automática de tweets baseada em um conjunto de heurísticas e b) classificação complementar baseada em aprendizado supervisionado de máquina. A proposta tem êxito quando aplicada a figuras públicas, superando o estado-da-arte. Além disso, são avaliadas alternativas no intuito de melhorar seu desempenho quando aplicada a outros domínios, revelando a possibilidade de se empregar estratégias tais como o uso de alvos e perfis semente dependendo das características de cada domínio. / Stance Detection is the task of automatically identifying if the author of a text is in favor of the given target, against the given target, or whether neither inference is likely. With the wide use of Twitter as a platform to express opinions and stances, the automatic analysis of this content becomes of high regard for companies, organizations and public figures. In general, works that explore such task adopt supervised or semi-supervised approaches. The present work proposes and evaluates a non-supervised process to detect stance in texts of tweets that has as entry only the target and a set of tweets to classify and is based on a hybrid approach composed by 2 stages: a) automatic labelling of tweets based on a set of heuristics and b) complementary classification based on supervised machine learning. The proposal succeeds when applied to public figures, overcoming the state-of-the-art. Beyond that, some alternatives are evaluated with the intention of increasing the performance when applied to other domains, revealing the possibility of use of strategies such as using seed targets and profiles depending on each domain characteristics.

Detecção de posicionamento é a tarefa de automaticamente identificar se o autor de um texto é favorável, contrário, ou nem favorável e nem contrário a uma dada proposição ou alvo. Com o amplo uso do Twitter como plataforma para expressar opiniões e posicionamentos, a análise automatizada deste conteúdo torna-se de grande valia para empresas, organizações e figuras públicas. Em geral, os trabalhos que exploram tal tarefa adotam abordagens supervisionadas ou semi-supervisionadas. O presente trabalho propõe e avalia um processo não supervisionado de detecção de posicionamento em textos de tweets que tem como entrada apenas o alvo e um conjunto de tweets a rotular e é baseado em uma abordagem híbrida composta por 2 etapas: a) rotulação automática de tweets baseada em um conjunto de heurísticas e b) classificação complementar baseada em aprendizado supervisionado de máquina. A proposta tem êxito quando aplicada a figuras públicas, superando o estado-da-arte. Além disso, são avaliadas alternativas no intuito de melhorar seu desempenho quando aplicada a outros domínios, revelando a possibilidade de se empregar estratégias tais como o uso de alvos e perfis semente dependendo das características de cada domínio. / Stance Detection is the task of automatically identifying if the author of a text is in favor of the given target, against the given target, or whether neither inference is likely. With the wide use of Twitter as a platform to express opinions and stances, the automatic analysis of this content becomes of high regard for companies, organizations and public figures. In general, works that explore such task adopt supervised or semi-supervised approaches. The present work proposes and evaluates a non-supervised process to detect stance in texts of tweets that has as entry only the target and a set of tweets to classify and is based on a hybrid approach composed by 2 stages: a) automatic labelling of tweets based on a set of heuristics and b) complementary classification based on supervised machine learning. The proposal succeeds when applied to public figures, overcoming the state-of-the-art. Beyond that, some alternatives are evaluated with the intention of increasing the performance when applied to other domains, revealing the possibility of use of strategies such as using seed targets and profiles depending on each domain characteristics.

Segmenting image into multiple meaningful regions is an essential task in Computer Vision. Deep Learning has been highly successful for segmentation, benefiting from the availability of the annotated datasets and deep neural network architectures. However, depth-based hand segmentation, an important application area of semantic segmentation, has yet to benefit from rich and large datasets. In addition, while deep methods provide robust solutions, they are often not efficient enough for low-powered devices. In this thesis, we focus on these two problems. To tackle the problem of lack of rich data, we propose an automatic method for generating high-quality annotations and introduce a large scale hand segmentation dataset. By exploiting the visual cues given by an RGBD sensor and a pair of colored gloves, we automatically generate dense annotations for two-hand segmentation. Our automatic annotation method lowers the cost/complexity of creating high-quality datasets and makes it easy to expand the dataset in the future. To reduce the computational requirement and allow real-time segmentation on low power devices, we propose a new representation and architecture for deep networks that predict segmentation maps based on Voronoi Diagrams. Voronoi Diagrams split space into discrete regions based on proximity to a set of points making them a powerful representation of regions, which we can then use to represent our segmentation outcomes. Specifically, we propose to estimate the location and class for these sets of points, which are then rasterized into an image. Notably, we use a differentiable definition of the Voronoi Diagram based on the softmax operator, enabling its use as a decoder layer in an end-to-end trainable network. As rasterization can take place at any given resolution, our method especially excels at rendering high-resolution segmentation maps, given a low-resolution image. We believe that our new HandSeg dataset will open new frontiers in Hand Segmentation research, and our cost-effective automatic annotation pipeline can benefit other relevant labeling tasks. Our newly proposed segmentation network enables high-quality segmentation representations that are not practically possible on low power devices using existing approaches. / Graduate

The field of computer vision has long pursued the challenge of understanding the three-dimensional world. This endeavour is further fuelled by the increasing demand for technologies that rely on accurate perception of the 3D environment such as autonomous driving and augmented reality. However, the labelled data scarcity in the 3D domain continues to be a hindrance to extensive research and development. Semi-Supervised Learning is a valuable tool to overcome data scarcity yet most of the state-of-art methods are primarily developed and tested for two-dimensional vision problems. To address this challenge, there is a need to explore innovative approaches that can bridge the gap between 2D and 3D domains. In this work, we propose a technique that both leverages the existing abundance of two-dimensional data and makes the state-of-art semi-supervised learning methods directly applicable to 3D tasks. Multi-View Meta Pseudo Labelling (MV-MPL) combines one of the best-performing architectures in 3D shape recognition, Multi-View Convolutional Neural Networks, together with the state-of-art semi-supervised method, Meta Pseudo Labelling. To evaluate the performance of MV-MPL, comprehensive experiments are conducted on widely used shape recognition benchmarks ModelNet40, ShapeNetCore-v1, and ShapeNetCore-v2, as well as, Objaverse-LVIS. The results demonstrate that MV-MPL achieves competitive accuracy compared to fully supervised models, even when only \(10%\) of the labels are available. Furthermore, the study reveals that the object descriptors extracted from the MV-MPL model exhibit strong performance on shape retrieval tasks, indicating the effectiveness of the approach beyond classification objectives. Further analysis includes the evaluation of MV-MPL under more restrained scenarios, the enhancements to the view aggregation and pseudo-labelling processes; and the exploration of the potential of employing multi-views as augmentations for semi-supervised learning. / Forskningsområdet för datorseende har länge strävat efter utmaningen att förstå den tredimensionella världen. Denna strävan drivs ytterligare av den ökande efterfrågan på teknologier som är beroende av en korrekt uppfattning av den tredimensionella miljön, såsom autonom körning och förstärkt verklighet. Dock fortsätter bristen på märkt data inom det tredimensionella området att vara ett hinder för omfattande forskning och utveckling. Halv-vägledd lärning (semi-supervised learning) framträder som ett värdefullt verktyg för att övervinna bristen på data, ändå är de flesta av de mest avancerade semisupervised-metoderna primärt utvecklade och testade för tvådimensionella problem inom datorseende. För att möta denna utmaning krävs det att utforska innovativa tillvägagångssätt som kan överbrygga klyftan mellan 2D- och 3D-domänerna. I detta arbete föreslår vi en teknik som både utnyttjar den befintliga överflöd av tvådimensionella data och gör det möjligt att direkt tillämpa de mest avancerade semisupervised-lärandemetoderna på 3D-uppgifter. Multi-View Meta Pseudo Labelling (MV-MPL) kombinerar en av de bästa arkitekturerna för 3D-formigenkänning, Multi-View Convolutional Neural Networks, tillsammans med den mest avancerade semisupervised-metoden, Meta Pseudo Labelling. För att utvärdera prestandan hos MV-MPL genomförs omfattande experiment på väl använda uvärderingar för formigenkänning., ModelNet40, ShapeNetCore-v1 och ShapeNetCore-v2. Resultaten visar att MV-MPL uppnår konkurrenskraftig noggrannhet jämfört med helt vägledda modeller, även när endast \(10%\) av etiketterna är tillgängliga. Dessutom visar studien att objektbeskrivningarna som extraherats från MV-MPL-modellen uppvisar en stark prestanda i formåterhämtningsuppgifter, vilket indikerar effektiviteten hos tillvägagångssättet bortom klassificeringsmål. Vidare analys inkluderar utvärderingen av MV-MPL under mer begränsade scenarier, förbättringar av vyaggregerings- och pseudomärkningsprocesserna samt utforskning av potentialen att använda bilder från flera vinklar som en metod att få mer data för halv-vägledd lärande.