Abstract: In the current work, we identify several problems of current tracking systems. The lack of large-scale labeled datasets hampers the usage of deep learning, especially end-to-end training, for tracking in TIR images. Therefore, many methods for tracking on TIR data are still based on hand-crafted features. This situation also happens in multi-modal tracking, e.g. RGB-T tracking. Another reason, which hampers the development of RGB-T tracking, is that there exists little research on the fusion mechanisms for combining information from RGB and TIR modalities. One of the crucial components of most trackers is the update module. For the currently existing end-to-end tracking architecture, e.g, Siamese trackers, the online model update is still not taken into consideration at the training stage. They use no-update or a linear update strategy during the inference stage. While such a hand-crafted approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update.
To address the data-scarcity for TIR and RGB-T tracking, we use image-to-image translation to generate a large-scale synthetic TIR dataset. This dataset allows us to perform end-to-end training for TIR tracking. Furthermore, we investigate several fusion mechanisms for RGB-T tracking. The multi-modal trackers are also trained in an end-to-end manner on the synthetic data. To improve the standard online update, we pose the updating step as an optimization problem which can be solved by training a neural network. Our approach thereby reduces the hand-crafted components in the tracking pipeline and sets a further step in the direction of a complete end-to-end trained tracking network which also considers updating during optimization.

Abstract: Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural networks using methods from topological data analysis. For this purpose, we compute homological persistence diagrams of weighted graphs constructed from neuron activation correlations after a training phase, aiming to capture patterns that are linked to the generalization capacity of the network. We compare the usefulness of different numerical summaries from persistence diagrams and show that a combination of some of them can accurately predict and partially explain the generalization gap without the need of a test set. Evaluation on two computer vision recognition tasks (CIFAR10 and SVHN) shows competitive generalization gap prediction when compared against state-of-the-art methods.

Abstract: In this chapter we present tools that can be used to build intelligent systems for colonoscopy.
The idea is, by using methods based on computer vision and artificial intelligence, add significant value to the colonoscopy procedure. Intelligent systems are being used to assist in other medical interventions

Abstract: In video compression the luma channel can be useful for predicting chroma channels (Cb, Cr), as has been demonstrated with the Cross-Component Linear Model (CCLM) used in Versatile Video Coding (VVC) standard. More recently, it has been shown that neural networks can even better capture the relationship among different channels. In this paper, a new attention-based neural network is proposed for cross-component intra prediction. With the goal to simplify neural network design, the new framework consists of four branches: boundary branch and luma branch for extracting features from reference samples, attention branch for fusing the first two branches, and prediction branch for computing the predicted chroma samples. The proposed scheme is integrated into VVC test model together with one additional binary block-level syntax flag which indicates whether a given block makes use of the proposed method. Experimental results demonstrate 0.31%/2.36%/2.00% BD-rate reductions on Y/Cb/Cr components, respectively, on top of the VVC Test Model (VTM) 7.0 which uses CCLM.

Abstract: We propose a method to acquire multispectral data with handheld devices with front-mounted RGB cameras. We propose to use the display of the device as an illuminant while the camera captures images illuminated by the red, green and
blue primaries of the display. Three illuminants and three response functions of the camera lead to nine response values which are used for reflectance estimation. Results are promising and show that the accuracy of the spectral reconstruction improves in the range from 30-40% over the spectral
reconstruction based on a single illuminant. Furthermore, we propose to compute sensor-illuminant aware linear basis by discarding the part of the reflectances that falls in the sensorilluminant null-space. We show experimentally that optimizing reflectance estimation on these new basis functions decreases
the RMSE significantly over basis functions that are independent to sensor-illuminant. We conclude that, multispectral data acquisition is potentially possible with consumer hand-held devices such as tablets, mobiles, and laptops, opening up applications which are currently considered to be unrealistic.

Abstract: PURPOSE:
Lack of objective measurement of tracheal obstruction degree has a negative impact on the chosen treatment prone to lead to unnecessary repeated explorations and other scanners. Accurate computation of tracheal stenosis in videobronchoscopy would constitute a breakthrough for this noninvasive technique and a reduction in operation cost for the public health service.
METHODS:
Stenosis calculation is based on the comparison of the region delimited by the lumen in an obstructed frame and the region delimited by the first visible ring in a healthy frame. We propose a parametric strategy for the extraction of lumen and tracheal ring regions based on models of their geometry and appearance that guide a deformable model. To ensure a systematic applicability, we present a statistical framework to choose optimal parametric values and a strategy to choose the frames that minimize the impact of scope optical distortion.
RESULTS:
Our method has been tested in 40 cases covering different stenosed tracheas. Experiments report a non- clinically relevant [Formula: see text] of discrepancy in the calculated stenotic area and a computational time allowing online implementation in the operating room.
CONCLUSIONS:
Our methodology allows reliable measurements of airway narrowing in the operating room. To fully assess its clinical impact, a prospective clinical trial should be done.

Abstract: Images and videos are pervasive in our life and communication. With advances in smart and portable devices, high capacity communication networks and high definition cinema, image and video compression are more relevant than ever. Traditional block-based linear transform codecs such as JPEG, H.264/AVC or the recent H.266/VVC are carefully designed to meet not only the rate-distortion criteria, but also the practical requirements of applications.
Recently, a new paradigm based on deep neural networks (i.e., neural image/video compression) has become increasingly popular due to its ability to learn powerful nonlinear transforms and other coding tools directly from data instead of being crafted by humans, as was usual in previous coding formats. While achieving excellent rate-distortion performance, these approaches are still limited mostly to research environments due to heavy models and other practical limitations, such as being limited to function on a particular rate and due to high memory and computational cost. In this thesis, we study these practical limitations, and designing more practical neural image compression approaches.
After analyzing the differences between traditional and neural image compression, our first contribution is the modulated autoencoder (MAE), a framework that includes a mechanism to provide multiple rate-distortion options within a single model with comparable performance to independent models. In a second contribution, we propose the slimmable compressive autoencoder (SlimCAE), which in addition to variable rate, can optimize the complexity of the model and thus reduce significantly the memory and computational burden.
Modern generative models can learn custom image transformation directly from suitable datasets following encoder-decoder architectures, task known as image-to-image (I2I) translation. Building on our previous work, we study the problem of distributed I2I translation, where the latent representation is transmitted through a binary channel and decoded in a remote receiving side. We also propose a variant that can perform both translation and the usual autoencoding functionality.
Finally, we also consider neural video compression, where the autoencoder is typically augmented with temporal prediction via motion compensation. One of the main bottlenecks of that framework is the optical flow module that estimates the displacement to predict the next frame. Focusing on this module, we propose a method that improves the accuracy of the optical flow estimation and a simplified variant that reduces the computational cost.
Key words: neural image compression, neural video compression, optical flow, practical neural image compression, compressive autoencoders, image-to-image translation, deep learning.