Leonardo Gomes Capozzi

Abstract
Every year, the VISion Understanding and Machine intelligence (VISUM) summer school runs a competition where participants can learn and share knowledge about Computer Vision and Machine Learning in a vibrant environment. 2021 VISUM's focused on applying those methodologies in fashion. Recently, there has been an increase of interest within the scientific community in applying computer vision methodologies to the fashion domain. That is highly motivated by fashion being one of the world's largest industries presenting a rapid development in e-commerce mainly since the COVID-19 pandemic. Computer Vision for Fashion enables a wide range of innovations, from personalized recommendations to outfit matching. The competition enabled students to apply the knowledge acquired in the summer school to a real-world problem. The ambition was to foster research and development in fashion outfit complementary product retrieval by leveraging vast visual and textual data with domain knowledge. For this, a new fashion outfit dataset (acquired and curated by FARFETCH) for research and benchmark purposes is introduced. Additionally, a competitive baseline with an original negative sampling process for triplet mining was implemented and served as a starting point for participants. The top 3 performing methods are described in this paper since they constitute the reference state-of-the-art for this particular problem. To our knowledge, this is the first challenge in fashion outfit complementary product retrieval. Moreover, this joint project between academia and industry brings several relevant contributions to disseminating science and technology, promoting economic and social development, and helping to connect early-career researchers to real-world industry challenges.

Abstract
With the advent of self-driving cars, and big companies such as Waymo or Bosch pushing forward into fully driverless transportation services, the in-vehicle behaviour of passengers must be monitored to ensure safety and comfort. The use of audio-visual information is attractive by its spatio-temporal richness as well as non-invasive nature, but faces tile likely constraints posed by available hardware and energy consumption. Hence new strategies are required to improve the usage of these scarce resources. We propose the processing of audio and visual data in a cascade pipeline for in-vehicle action recognition. The data is processed by modality-specific sub-modules. with subsequent ones being used when a confident classification is not reached. Experiments show an interesting accuracy-acceleration trade-off when compared with a parallel pipeline with late fusion, presenting potential for industrial applications on embedded devices.

Abstract
With the advent of self-driving cars and the push by large companies into fully driverless transportation services, monitoring passenger behaviour in vehicles is becoming increasingly important for several reasons, such as ensuring safety and comfort. Although several human action recognition (HAR) methods have been proposed, developing a true HAR system remains a very challenging task. If the dataset used to train a model contains a small number of actors, the model can become biased towards these actors and their unique characteristics. This can cause the model to generalise poorly when confronted with new actors performing the same actions. This limitation is particularly acute when developing models to characterise the activities of vehicle occupants, for which data sets are short and scarce. In this study, we describe and evaluate three different methods that aim to address this actor bias and assess their performance in detecting in-vehicle violence. These methods work by removing specific information about the actor from the model's features during training or by using data that is independent of the actor, such as information about body posture. The experimental results show improvements over the baseline model when evaluated with real data. On the Hanau03 Vito dataset, the accuracy improved from 65.33% to 69.41%. On the Sunnyvale dataset, the accuracy improved from 82.81% to 86.62%.

Abstract
The task of person re-identification has important applications in security and surveillance systems. It is a challenging problem since there can be a lot of differences between pictures belonging to the same person, such as lighting, camera position, variation in poses and occlusions. The use of Deep Learning has contributed greatly towards more effective and accurate systems. Many works use attention mechanisms to force the models to focus on less distinctive areas, in order to improve performance in situations where important information may be missing. This paper proposes a new, more flexible method for calculating these masks, using a U-Net which receives a picture and outputs a mask representing the most distinctive areas of the picture. Results show that the method achieves an accuracy comparable or superior to those in state-of-the-art methods.

Abstract
The traditional task of locating suspects using forensic sketches posted on public spaces, news, and social media can be a difficult task. Recent methods that use computer vision to improve this process present limitations, as they either do not use end-to-end networks for sketch recognition in police databases (which generally improve performance) or/and do not offer a photo-realistic representation of the sketch that could be used as alternative if the automatic matching process fails. This paper proposes a method that combines these two properties, using a conditional generative adversarial network (cGAN) and a pre-trained face recognition network that are jointly optimised as an end-to-end model. While the model can identify a short list of potential suspects in a given database, the cGAN offers an intermediate realistic face representation to support an alternative manual matching process. Evaluation on sketch-photo pairs from the CUFS, CUFSF and CelebA databases reveal the proposed method outperforms the state-of-the-art in most tasks, and that forcing an intermediate photo-realistic representation only results in a small performance decrease.