Abstract: An endoscopy system (1) comprises an endoscope (2) with a camera (3) at its tip. The endoscope extends through an endoscope guide (4) for guiding movement of the endoscope and for measurement of its movement as it enters the body. The guide (4) comprises a generally conical body (5) having a through passage (105) through which the endoscope (2) extends. A motion sensor comprises an optical transmitter (7) and a detector (8) mounted alongside the passage (105) to measure the insertion-withdrawal linear motion and also rotation of the endoscope by the endoscopist's hand. The system (1) also comprises a flexure controller (10) having wheels operated by the endoscopist. The camera (3), the motion sensor (7/8), and the flexure controller (10) are all connected to a processor (11) which feeds a display.

Abstract: The visual analysis of humans from images is an important topic of interest due to its relevance to many computer vision applications like pedestrian detection, monitoring and surveillance, human-computer interaction, e-health or content-based image retrieval, among others.
In this dissertation we are interested in learning different visual representations of the human body that are helpful for the visual analysis of humans in images and video sequences. To that end, we analyze both RGB and depth image modalities and address the problem from three different research lines, at different levels of abstraction; from pixels to gestures: human segmentation, human pose estimation and gesture recognition.
First, we show how binary segmentation (object vs. background) of the human body in image sequences is helpful to remove all the background clutter present in the scene. The presented method, based on Graph cuts optimization, enforces spatio-temporal consistency of the produced segmentation masks among consecutive frames. Secondly, we present a framework for multi-label segmentation for obtaining much more detailed segmentation masks: instead of just obtaining a binary representation separating the human body from the background, finer segmentation masks can be obtained separating the different body parts.
At a higher level of abstraction, we aim for a simpler yet descriptive representation of the human body. Human pose estimation methods usually rely on skeletal models of the human body, formed by segments (or rectangles) that represent the body limbs, appropriately connected following the kinematic constraints of the human body. In practice, such skeletal models must fulfill some constraints in order to allow for efficient inference, while actually limiting the expressiveness of the model. In order to cope with this, we introduce a top-down approach for predicting the position of the body parts in the model, using a mid-level part representation based on Poselets.
Finally, we propose a framework for gesture recognition based on the bag of visual words framework. We leverage the benefits of RGB and depth image modalities by combining modality-specific visual vocabularies in a late fusion fashion. A new rotation-variant depth descriptor is presented, yielding better results than other state-of-the-art descriptors. Moreover, spatio-temporal pyramids are used to encode rough spatial and temporal structure. In addition, we present a probabilistic reformulation of Dynamic Time Warping for gesture segmentation in video sequences. A Gaussian-based probabilistic model of a gesture is learnt, implicitly encoding possible deformations in both spatial and time domains.

Abstract: Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism.

Abstract: Image generation is arguably one of the most attractive, compelling, and challenging tasks in computer vision. Among the methods which perform image generation, generative adversarial networks (GANs) play a key role. The most common image generation models based on GANs can be divided into two main approaches. The first one, called simply image generation takes random noise as an input and synthesizes an image which follows the same distribution as the images in the training set. The second class, which is called image-to-image translation, aims to map an image from a source domain to one that is indistinguishable from those in the target domain. Image-to-image translation methods can further be divided into paired and unpaired image-to-image translation based on whether they require paired data or not. In this thesis, we aim to address some challenges of both image generation and image-to-image generation.GANs highly rely upon having access to vast quantities of data, and fail to generate realistic images from random noise when applied to domains with few images. To address this problem, we aim to transfer knowledge from a model trained on a large dataset (source domain) to the one learned on limited data (target domain). We find that both GANs andconditional GANs can benefit from models trained on large datasets. Our experiments show that transferring the discriminator is more important than the generator. Using both the generator and discriminator results in the best performance. We found, however, that this method suffers from overfitting, since we update all parameters to adapt to the target data. We propose a novel architecture, which is tailored to address knowledge transfer to very small target domains. Our approach effectively exploreswhich part of the latent space is more related to the target domain. Additionally, the proposed method is able to transfer knowledge from multiple pretrained GANs. Although image-to-image translation has achieved outstanding performance, it still facesseveral problems. First, for translation between complex domains (such as translations between different modalities) image-to-image translation methods require paired data. We show that when only some of the pairwise translations have been seen (i.e. during training), we can infer the remaining unseen translations (where training pairs are not available). We propose a new approach where we align multiple encoders and decoders in such a way that the desired translation can be obtained by simply cascadingthe source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). Second, we address the issue of bias in image-to-image translation. Biased datasets unavoidably contain undesired changes, which are dueto the fact that the target dataset has a particular underlying visual distribution. We use carefully designed semantic constraints to reduce the effects of the bias. The semantic constraint aims to enforce the preservation of desired image properties. Finally, current approaches fail to generate diverse outputs or perform scalable image transfer in a single model. To alleviate this problem, we propose a scalable and diverse image-to-image translation. We employ random noise to control the diversity. The scalabitlity is determined by conditioning the domain label.computer vision, deep learning, imitation learning, adversarial generative networks, image generation, image-to-image translation.

Abstract: Artificial intelligence is innovating the fashion industry by proposing new applications and solutions to the problems encountered by researchers and engineers working in the industry. In this thesis, we address three of these problems. In the first part of the thesis, we tackle the problem of multi-label image classification which is very related to fashion attribute recognition. In the second part of the thesis, we address two problems that are specific to fashion. Firstly, we address the problem of main product detection which is the task of associating correct image parts (e.g. bounding boxes) with the fashion product being sold. Secondly, we address the problem of color naming for multicolored fashion items. The task of multi-label image classification consists in assigning various concepts such as objects or attributes to images. Usually, there are dependencies that can be learned between the concepts to capture label correlations (chair and table classes are more likely to co-exist than chair and giraffe).
If we treat the multi-label image classification problem as an orderless set prediction problem, we can exploit recurrent neural networks (RNN) to capture label correlations. However, RNNs are trained to predict ordered sequences of tokens, so if the order of the predicted sequence is different than the order of the ground truth sequence, there will be penalization although the predictions are correct. Therefore, in the first part of the thesis, we propose an orderless loss function which will order the labels in the ground truth sequence dynamically in a way that the minimum loss is achieved. This results in a significant improvement of RNN models on multi-label image classification over the previous methods.
However, RNNs suffer from long term dependencies when the cardinality of set grows bigger. The decoding process might stop early if the current hidden state cannot find any object and outputs the termination token. This would cause the remaining classes not to be predicted and lower recall metric. Transformers can be used to avoid the long term dependency problem exploiting their selfattention modules that process sequential data simultaneously. Consequently, we propose a novel transformer model for multi-label image classification which surpasses the state-of-the-art results by a large margin.
In the second part of thesis, we focus on two fashion-specific problems. Main product detection is the task of associating image parts with the fashion product that is being sold, generally using associated textual metadata (product title or description). Normally, in fashion e-commerces, products are represented by multiple images where a person wears the product along with other fashion items. If all the fashion items in the images are marked with bounding boxes, we can use the textual metadata to decide which item is the main product. The initial work treated each of these images independently, discarding the fact that they all belong to the same product. In this thesis, we represent the bounding boxes from all the images as nodes in a fully connected graph. This allows the algorithm to learn relations between the nodes during training and take the entire context into account for the final decision. Our algorithm results in a significant improvement of the state-ofthe-art.
Moreover, we address the problem of color naming for multicolored fashion items, which is a challenging task due to the external factors such as illumination changes or objects that act as clutter. In the context of multi-label classification, the vaguely defined lines between the classes in the color space cause ambiguity. For example, a shade of blue which is very close to green might cause the model to incorrectly predict the color blue and green at the same time. Based on this, models trained for color naming are expected to recognize the colors and their quantities in both single colored and multicolored fashion items. Therefore, in this thesis, we propose a novel architecture with an additional head that explicitly estimates the number of colors in fashion items. This removes the ambiguity problem and results in better color naming performance.

Abstract: State of the art methods for image matching, content-based retrieval and recognition use local features. Most of these still exploit only the luminance information for detection. The color saliency boosting algorithm has provided an efficient method to exploit the saliency of color edges based on information theory. However, during the design of this algorithm, some issues were not addressed in depth: (1) The method has ignored the underlying distribution of derivatives in natural images. (2) The dependence of information content in color-boosted edges on its spatial derivatives has not been quantitatively established. (3) To evaluate luminance and color contributions to saliency of edges, a parameter gradually balancing both contributions is required.
We introduce a novel algorithm, based on the principles of independent component analysis, which models the first order derivatives of color natural images by a generalized Gaussian distribution. Furthermore, using this probability model we show that for images with a Laplacian distribution, which is a particular case of generalized Gaussian distribution, the magnitudes of color-boosted edges reflect their corresponding information content. In order to evaluate the impact of color edge saliency in real world applications, we introduce an extension of the Laplacian-of-Gaussian detector to color, and the performance for image matching is evaluated. Our experiments show that our approach provides more discriminative regions in comparison with the original detector.

Abstract: The characterization of trichromatic cameras is usually done in terms of a device-independent color space, such as the CIE 1931 XYZ space. This is indeed convenient since it allows the testing of results against colorimetric measures. We have characterized our camera to represent human cone activation by mapping the camera sensor's (RGB) responses to human (LMS) through a polynomial transformation, which can be “customized” according to the types of scenes we want to represent. Here we present a method to test the accuracy of the camera measures and a study on how the choice of training reflectances for the polynomial may alter the results.