Abstract: This thesis presents several contributions to the literature of sketch based image retrieval (SBIR). In SBIR the first challenge we face is how to map two different domains to common space for effective retrieval of images, while tackling the different levels of abstraction people use to express their notion of objects around while sketching. To this extent we first propose a cross-modal learning framework that maps both sketches and text into a joint embedding space invariant to depictive style, while preserving semantics. Then we have also investigated different query types possible to encompass people's dilema in sketching certain world objects. For this we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set.
Finally, we explore the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognises two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended. We also in this dissertation pave the path to the future direction of research in this domain.

Abstract: Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively. Particularly, comprehending text in videos holds great significance, requiring both scene text understanding and temporal reasoning. This paper focuses on exploring two recently introduced datasets, NewsVideoQA and M4-ViteVQA, which aim to address video question answering based on textual content. The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4- ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. Additionally, the study includes experimentation with BERT-QA, a text-only model, which demonstrates comparable performance to the original methods on both datasets, indicating the shortcomings in the formulation of these datasets. Furthermore, we also look into the domain adaptation aspect by examining the effectiveness of training on M4-ViteVQA and evaluating on NewsVideoQA and vice-versa, thereby shedding light on the challenges and potential benefits of out-of-domain training.

Abstract: Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream approach. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a common representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the common feature representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generalization capacity of our model on both low-scale and large-scale datasets.

Abstract: Observers are faster to detect a target among a set of distracters if the targets and distracters come from different color categories. This cross-boundary advantage seems to be limited to the right visual field, which is consistent with the dominance of the left hemisphere for language processing [Gilbert et al., Proc. Natl. Acad. Sci. USA 103, 489 (2006)]. Here we study whether a similar visual field advantage is found in the color identification task in speakers of Mandarin, a language that uses a logographic system. Forty late Mandarin-English bilinguals performed a blue-green color categorization task, in a blocked design, in their first language (L1: Mandarin) or second language (L2: English). Eleven color singletons ranging from blue to green were presented for 160 ms, randomly in the left visual field (LVF) or right visual field (RVF). Color boundary and reaction times (RTs) at the color boundary were estimated in L1 and L2, for both visual fields. We found that the color boundary did not differ between the languages; RTs at the color boundary, however, were on average more than 100 ms shorter in the English compared to the Mandarin sessions, but only when the stimuli were presented in the RVF. The finding may be explained by the script nature of the two languages: Mandarin logographic characters are analyzed visuospatially in the right hemisphere, which conceivably facilitates identification of color presented to the LVF.

Abstract: Pòster

Abstract: The Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in various dyadic interaction scenarios, with all participants competing strictly under the same conditions. The goal of the challenge is to provide the first benchmark test set for multi-modal information processing and to foster collaboration among the audio, visual, and audio-visual behaviour analysis and behaviour generation (a.k.a generative AI) communities, to compare the relative merits of the approaches to automatic appropriate facial reaction generation under different spontaneous dyadic interaction conditions. This paper presents: (i) the novelties, contributions and guidelines of the REACT2023 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2023.

Abstract: PURPOSE:
In this article, the authors studied the feasibility of estimating regional mechanical properties in cerebral aneurysms, integrating information extracted from imaging and physiological data with generic computational models of the arterial wall behavior.
METHODS:
A data assimilation framework was developed to incorporate patient-specific geometries into a given biomechanical model, whereas wall motion estimates were obtained from applying registration techniques to a pair of simulated MR images and guided the mechanical parameter estimation. A simple incompressible linear and isotropic Hookean model coupled with computational fluid-dynamics was employed as a first approximation for computational purposes. Additionally, an automatic clustering technique was developed to reduce the number of parameters to assimilate at the optimization stage and it considerably accelerated the convergence of the simulations. Several in silico experiments were designed to assess the influence of aneurysm geometrical characteristics and the accuracy of wall motion estimates on the mechanical property estimates. Hence, the proposed methodology was applied to six real cerebral aneurysms and tested against a varying number of regions with different elasticity, different mesh discretization, imaging resolution, and registration configurations.
RESULTS:
Several in silico experiments were conducted to investigate the feasibility of the proposed workflow, results found suggesting that the estimation of the mechanical properties was mainly influenced by the image spatial resolution and the chosen registration configuration. According to the in silico experiments, the minimal spatial resolution needed to extract wall pulsation measurements with enough accuracy to guide the proposed data assimilation framework was of 0.1 mm.
CONCLUSIONS:
Current routine imaging modalities do not have such a high spatial resolution and therefore the proposed data assimilation framework cannot currently be used on in vivo data to reliably estimate regional properties in cerebral aneurysms. Besides, it was observed that the incorporation of fluid-structure interaction in a biomechanical model with linear and isotropic material properties did not have a substantial influence in the final results.