Abstract: This project explores the feasibility of remote patient monitoring based on the analysis of 3D movements captured with smartwatches. We base our analysis on the Kinematic Theory of Rapid Human Movement. We have validated our research in a real case scenario for stroke rehabilitation at the Guttmann Institute (https://www.guttmann.com/en/) (neurorehabilitation hospital), showing promising results. Our work could have a great impact in remote healthcare applications, improving the medical efficiency and reducing the healthcare costs. Future steps include more clinical validation, developing multi-modal analysis architectures (analysing data from sensors, images, audio, etc.), and exploring the application of our technology to monitor other neurodegenerative diseases.

Abstract: Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.

Abstract: Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these models cannot flexibly adapt to varying accuracy and efficiency requirements. In this paper, we propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference depending on the desired accuracy-efficiency tradeoff. More specifically, we employ parametrized channel slimming by stepwise downward knowledge distillation during training. Motivated by the observation that the differences between segmentation results of each submodel are mainly near the semantic borders, we introduce an additional boundary guided semantic segmentation loss to further improve the performance of each submodel. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance than independent models. Extensive experiments on semantic segmentation benchmarks, Cityscapes and CamVid, demonstrate the generalization ability of our framework.

Abstract: Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.

Abstract: Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly distilling information from the crucial attention mechanism from teacher to student can significantly narrow the performance gap between both. In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model). We are also the first to apply the tiny ViT-T model on self-supervised learning. Moreover, AttnDistill is independent of self-supervised learning algorithms, it can be adapted to ViT based SSL methods to improve the performance in future research.

Abstract: 3D geometric information is essential for on-board perception in autonomous driving and driver assistance. Autonomous vehicles (AVs) are equipped with calibrated sensor suites. As part of these suites, we can find LiDARs, which are expensive active sensors in charge of providing the 3D geometric information. Depending on the operational conditions for the AV, calibrated stereo rigs may be also sufficient for obtaining 3D geometric information, being these rigs less expensive and easier to install than LiDARs. However, ensuring a proper maintenance and calibration of these types of sensors is not trivial. Accordingly, there is an increasing interest on performing monocular depth estimation (MDE) to obtain 3D geometric information on-board. MDE is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Moreover, a set of single cameras with MDE capabilities would still be a cheap solution for on-board perception, relatively easy to integrate and maintain in an AV.
Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Accordingly, the overall goal of this PhD is to study methods for improving CNN-based MDE accuracy under different training settings. More specifically, this PhD addresses different research questions that are described below. When we started to work in this PhD, state-of-theart methods for MDE were already based on CNNs. In fact, a promising line of work consisted in using image-based semantic supervision (i.e., pixel-level class labels) while training CNNs for MDE using LiDAR-based supervision (i.e., depth). It was common practice to assume that the same raw training data are complemented by both types of supervision, i.e., with depth and semantic labels. However, in practice, it was more common to find heterogeneous datasets with either only depth supervision or only semantic supervision. Therefore, our first work was to research if we could train CNNs for MDE by leveraging depth and semantic information from heterogeneous datasets. We show that this is indeed possible, and we surpassed the state-of-the-art results on MDE at the time we did this research. To achieve our results, we proposed a particular CNN architecture and a new training protocol.
After this research, it was clear that the upper-bound setting to train CNN-based MDE models consists in using LiDAR data as supervision. However, it would be cheaper and more scalable if we would be able to train such models from monocular sequences. Obviously, this is far more challenging, but worth to research. Training MDE models using monocular sequences is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. To alleviate these problems, we perform MDE by virtual-world supervision and real-world SfM self-supervision. We call our proposalMonoDEVSNet. We compensate the SfM self-supervision limitations by leveraging
virtual-world images with accurate semantic and depth supervision, as well as addressing the virtual-to-real domain gap. MonoDEVSNet outperformed previous MDE CNNs trained on monocular and even stereo sequences. We have publicly released MonoDEVSNet at <https://github.com/HMRC-AEL/MonoDEVSNet>.
Finally, since MDE is performed to produce 3D information for being used in downstream tasks related to on-board perception. We also address the question of whether the standard metrics for MDE assessment are a good indicator for future MDE-based driving-related perception tasks. By using 3D object detection on point clouds as proxy of on-board perception, we conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods which reflects relatively well the 3D object detection results we may expect.

Abstract: Despite its wide applications in criminal investigations and clinical communications with patients suffering from autism, automatic micro-expression recognition remains a challenging problem because of the lack of training data and imbalanced classes problems. In this study, we proposed a meta-learning based multi-model fusion network (Meta-MMFNet) to solve the existing problems. The proposed method is based on the metric-based meta-learning pipeline, which is specifically designed for few-shot learning and is suitable for model-level fusion. The frame difference and optical flow features were fused, deep features were extracted from the fused feature, and finally in the meta-learning-based framework, weighted sum model fusion method was applied for micro-expression classification. Meta-MMFNet achieved better results than state-of-the-art methods on four datasets. The code is available at https://github.com/wenjgong/meta-fusion-based-method.

Abstract: Multi-label image classification is about predicting a set of class labels that can be considered as orderless sequential data. Transformers process the sequential data as a whole, therefore they are inherently good at set prediction. The first vision-based transformer model, which was proposed for the object detection task introduced the concept of object queries. Object queries are learnable positional encodings that are used by attention modules in decoder layers to decode the object classes or bounding boxes using the region of interests in an image. However, inputting the same set of object queries to different decoder layers hinders the training: it results in lower performance and delays convergence. In this paper, we propose the usage of primal object queries that are only provided at the start of the transformer decoder stack. In addition, we improve the mixup technique proposed for multi-label classification. The proposed transformer model with primal object queries improves the state-of-the-art class wise F1 metric by 2.1% and 1.8%; and speeds up the convergence by 79.0% and 38.6% on MS-COCO and NUS-WIDE datasets respectively.