Abstract: Self-supervised Learning has been showing upbeat performance in several computer vision tasks. The popular contrastive methods make use of a Siamese architecture with different loss functions. In this work, we go deeper into two very recent state of the art frameworks, namely, SimSiam and Barlow Twins. Inspired by them, we propose a new self-supervised learning method we call Opt-SSL that combines both image and feature contrasting. We validate the proposed method on the food recognition task, showing that our proposed framework enables the self-learning networks to learn better visual representations.

Abstract: The task of image-text matching aims to map representations from different modalities into a common joint visual-textual embedding. However, the most widely used datasets for this task, MSCOCO and Flickr30K, are actually image captioning datasets that offer a very limited set of relationships between images and sentences in their ground-truth annotations. This limited ground truth information forces us to use evaluation metrics based on binary relevance: given a sentence query we consider only one image as relevant. However, many other relevant images or captions may be present in the dataset. In this work, we propose two metrics that evaluate the degree of semantic relevance of retrieved items, independently of their annotated binary relevance. Additionally, we incorporate a novel strategy that uses an image captioning metric, CIDEr, to define a Semantic Adaptive Margin (SAM) to be optimized in a standard triplet loss. By incorporating our formulation to existing models, a large improvement is obtained in scenarios where available training data is limited. We also demonstrate that the performance on the annotated image-caption pairs is maintained while improving on other non-annotated relevant items when employing the full training set. The code for our new metric can be found at github. com/furkanbiten/ncsmetric and the model implementation at github. com/andrespmd/semanticadaptive_margin.

Abstract: We present a general framework for the garment animation problem through unsupervised deep learning inspired in physically based simulation. Existing trends in the literature already explore this possibility. Nonetheless, these approaches do not handle cloth dynamics. Here, we propose the first methodology able to learn realistic cloth dynamics unsupervisedly, and henceforth, a general formulation for neural cloth simulation. The key to achieve this is to adapt an existing optimization scheme for motion from simulation based methodologies to deep learning. Then, analyzing the nature of the problem, we devise an architecture able to automatically disentangle static and dynamic cloth subspaces by design. We will show how this improves model performance. Additionally, this opens the possibility of a novel motion augmentation technique that greatly improves generalization. Finally, we show it also allows to control the level of motion in the predictions. This is a useful, never seen before, tool for artists. We provide of detailed analysis of the problem to establish the bases of neural cloth simulation and guide future research into the specifics of this domain.
ACM Transactions on GraphicsVolume 41Issue 6December 2022 Article No.: 220pp 1–

Abstract: Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA).
In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering.

Abstract: Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase
in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models’ object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights are available online.

Abstract: Assessing the quality of movements for post-stroke patients during the rehabilitation phase is vital given that there is no standard stroke rehabilitation plan for all the patients. In fact, it depends basically on the patient’s functional independence and its progress along the rehabilitation sessions. To tackle this challenge and make neurorehabilitation more agile, we propose an automatic assessment pipeline that starts by recognising patients’ movements by means of a shallow deep learning architecture, then measuring the movement quality using jerk measure and related measures. A particularity of this work is that the dataset used is clinically relevant, since it represents movements inspired from Fugl-Meyer a well common upper-limb clinical stroke assessment scale for stroke patients. We show that it is possible to detect the contrast between healthy and patients movements in terms of smoothness, besides achieving conclusions about the patients’ progress during the rehabilitation sessions that correspond to the clinicians’ findings about each case.

Abstract: Single image super-resolution (SISR) is an important task in image processing which aims to enhance the resolution of imaging systems. Recently, SISR has witnessed great strides with the rapid development of deep learning. Recent advances in SISR are mostly devoted to designing deeper and wider networks to enhance their representation learning capacity. However, as the depth of networks increases, deep learning-based methods are faced with the challenge of computational complexity in practice. Moreover, most existing methods rarely leverage the intermediate features and also do not discriminate the computation of features by their frequencial components, thereby achieving relatively low performance. Aside from the aforementioned problems, another desired ability is to upsample images to arbitrary scales using a single model. Most current SISR methods train a dedicated model for each target resolution, losing generality and increasing memory requirements. In this thesis, we address the aforementioned issues and propose solutions to them: i) We present a novel frequency-based enhancement block which treats different frequencies in a heterogeneous way and also models inter-channel dependencies, which consequently enrich the output feature. Thus it helps the network generate more discriminative representations by explicitly recovering finer details. ii) We introduce OverNet which contains two main parts: a lightweight feature extractor that follows a novel recursive framework of skip and dense connections to reduce low-level feature degradation, and an overscaling module that generates an accurate SR image by internally constructing an overscaled intermediate representation of the output features. Then, to solve the problem of reconstruction at arbitrary scale factors, we introduce a novel multi-scale loss, that allows the simultaneous training of all scale factors using a single model. iii) We propose a directional variance attention network which leverages a novel attention mechanism to enhance features in different channels and spatial regions. Moreover, we introduce a novel procedure for using attention mechanisms together with residual blocks to facilitate the preservation of finer details. Finally, we demonstrate that our approaches achieve considerably better performance than previous state-of-the-art methods, in terms of both quantitative and visual quality.

Abstract: The transcription of sheet music into some machine-readable format can be carried out manually. However, the complexity of music notation inevitably leads to burdensome software for music score editing, which makes the whole process
very time-consuming and prone to errors. Consequently, automatic transcription
systems for musical documents represent interesting tools.
Document analysis is the subject that deals with the extraction and processing
of documents through image and pattern recognition. It is a branch of computer
vision. Taking music scores as source, the field devoted to address this task is
known as Optical Music Recognition (OMR). Typically, an OMR system takes an
image of a music score and automatically extracts its content into some symbolic
structure such as MEI or MusicXML.
In this dissertation, we have investigated different methods for recognizing a
single staff section (e.g. scores for violin, flute, etc.), much in the same way as most text recognition research focuses on recognizing words appearing in a given line image. These methods are based in two different methodologies. On the one hand, we present two methods based on Recurrent Neural Networks, in particular, the
Long Short-Term Memory Neural Network. On the other hand, a method based on Sequence to Sequence models is detailed.
Music context is needed to improve the OMR results, just like language models
and dictionaries help in handwriting recognition. For example, syntactical rules
and grammars could be easily defined to cope with the ambiguities in the rhythm.
In music theory, for example, the time signature defines the amount of beats per
bar unit. Thus, in the second part of this dissertation, different methodologies
have been investigated to improve the OMR recognition. We have explored three
different methods: (a) a graphic tree-structure representation, Dendrograms, that
joins, at each level, its primitives following a set of rules, (b) the incorporation of Language Models to model the probability of a sequence of tokens, and (c) graph neural networks to analyze the music scores to avoid meaningless relationships between music primitives.
Finally, to train all these methodologies, and given the method-specificity of
the datasets in the literature, we have created four different music datasets. Two of them are synthetic with a modern or old handwritten appearance, whereas the
other two are real handwritten scores, being one of them modern and the other
old.