The role of context in image annotation and recommendation

With the rise of smart phones, lifelogging devices (e.g. Google Glass) and popularity of image sharing websites (e.g. Flickr), users are capturing and sharing every aspect of their life online producing a wealth of visual content. Of these uploaded images, the majority are poorly annotated or exist in complete semantic isolation making the process of building retrieval systems difficult as one must firstly understand the meaning of an image in order to retrieve it. To alleviate this problem, many image sharing websites offer manual annotation tools which allow the user to “tag” their photos, however, these techniques are laborious and as a result have been poorly adopted; Sigurbjörnsson and van Zwol (2008) showed that 64% of images uploaded to Flickr are annotated with < 4 tags. Due to this, an entire body of research has focused on the automatic annotation of images (Hanbury, 2008; Smeulders et al., 2000; Zhang et al., 2012a) where one attempts to bridge the semantic gap between an image’s appearance and meaning e.g. the objects present. Despite two decades of research the semantic gap still largely exists and as a result automatic annotation models often offer unsatisfactory performance for industrial implementation. Further, these techniques can only annotate what they see, thus ignoring the “bigger picture” surrounding an image (e.g. its location, the event, the people present etc). Much work has therefore focused on building photo tag recommendation (PTR) methods which aid the user in the annotation process by suggesting tags related to those already present. These works have mainly focused on computing relationships between tags based on historical images e.g. that NY and timessquare co-exist in many images and are therefore highly correlated. However, tags are inherently noisy, sparse and ill-defined often resulting in poor PTR accuracy e.g. does NY refer to New York or New Year? This thesis proposes the exploitation of an image’s context which, unlike textual evidences, is always present, in order to alleviate this ambiguity in the tag recommendation process. Specifically we exploit the “what, who, where, when and how” of the image capture process in order to complement textual evidences in various photo tag recommendation and retrieval scenarios. In part II, we combine text, content-based (e.g. # of faces present) and contextual (e.g. day-of-the-week taken) signals for tag recommendation purposes, achieving up to a 75% improvement to precision@5 in comparison to a text-only TF-IDF baseline. We then consider external knowledge sources (i.e. Wikipedia & Twitter) as an alternative to (slower moving) Flickr in order to build recommendation models on, showing that similar accuracy could be achieved on these faster moving, yet entirely textual, datasets. In part II, we also highlight the merits of diversifying tag recommendation lists before discussing at length various problems with existing automatic image annotation and photo tag recommendation evaluation collections. In part III, we propose three new image retrieval scenarios, namely “visual event summarisation”, “image popularity prediction” and “lifelog summarisation”. In the first scenario, we attempt to produce a rank of relevant and diverse images for various news events by (i) removing irrelevant images such memes and visual duplicates (ii) before semantically clustering images based on the tweets in which they were originally posted. Using this approach, we were able to achieve over 50% precision for images in the top 5 ranks. In the second retrieval scenario, we show that by combining contextual and content-based features from images, we are able to predict if it will become “popular” (or not) with 74% accuracy, using an SVM classifier. Finally, in chapter 9 we employ blur detection and perceptual-hash clustering in order to remove noisy images from lifelogs, before combining visual and geo-temporal signals in order to capture a user’s “key moments” within their day. We believe that the results of this thesis show an important step towards building effective image retrieval models when there lacks sufficient textual content (i.e. a cold start).

The impact of event sponsorship on children’s brand image and purchase intentions: The mediator effects of product involvement and brand familiarity

Field lab in marketing: Children consumer behaviour

Image summarisation: human action description from static images

Dissertação de Mestrado, Processamento de Linguagem Natural e Indústrias da Língua, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2014

"España Verde": tourism destination image among German Facebook users

Dissertação de Mestrado, Economia do Turismo e da Economia Regional, Faculdade de Economia, Universidade do Algarve, 2016

Malséance : la mort et l'image dans le (méta)théâtre de Samuel Beckett et de Jean Genet

Both ludic and macabre, the theatrical works of Samuel Beckett and Jean Genet are a paradox to behold. Indeed, as this thesis seeks to illustrate, despite their vastly differing aesthetics, at the core of each playwright’s stage productions is a tension between the characters’ yearning for silence and invisibility, and the continual creation of an often humorous, chaotic, exaggerated or theatrical image that depicts this very longing. Seeking an impossible intersection between their image and their death, they are trapped in a double bind that guarantees aesthetic failure. In order to grasp the close, yet delicate, relationship between the image of death and the death of the image, as presented in the plays of Beckett and Genet, we will explore how the characters’ creative processes deflate the very images — both visual and auditory — that they create. More specifically, we will examine how mimesis both liberates and confines the characters; while the symbolic realm provides the only means of self-representation, it is also a source of profound alienation and powerlessness, for it never adequately conveys meaning. Thus, body, gesture, language and voice are each the site of simultaneous and ceaseless reappearance and disappearance, for which death remains the only (aporetic) cure. Struggling against theatrical form, which demands the actors’ and the audience’s physical presence, both playwrights make shrewd use of metatheatre to slowly empty the stage and thereby suggest the impending, yet impossible, erasure of their characters.

The Worldhood of the Cinematic Image

A close analysis of the specifically cinematographic procedure in Akira Kurosawa’s ‘Dream’ Crows reveals it as an articulated and insightful philosophical statement, endowed with general relevance concerning ‘natural’ perception, phenomenological Erlebnis, mechanical image and aesthetic rapture. The antagonism between the Benjaminian lineage of a mechanical irreducibility of the cinematic image to anthropocentric categories, and the Cartesian tradition of a film-philosophy still relying on the equally irreducible structure of the intentional act, be it the one of a deeply embodied and enworlded counsciousness, in accounting for the essential structure of film and spectator (and their relation), i.e., the antagonism between the decentering primacy of the image and the self-centered primacy of perception, cannot be settled through a simple Phenomenological shift from occularcentric, intentional counsciousness to its embodyment ‘in-the-world’ as yet another carrier of intentionality. Still it remains to be explained what is it in the mechanical image that is able to so deeply affect the human flesh, and conversely, to what features in the human bodily experience is its mechanical other, the fascinating image, so successfuly adressing? It should be expected from the anti-Cartesianism of both the early and the late Merleau-Ponty the textual support for an approach to the essential condition of passivity in movie watching, that would be convergent with Benjamin. The Chapter ‘Le sentir’, in Phénoménologie de la perception, will offer us the proper guide to elucidate what we are already perceiving and conceiving in Kurosawa’s film, where the ex-static phenomenological body of the aesthetical contemplator ‘enters the frame’ like the Benjaminian surgeon enters the body and like the painter - and always already like our deepest level of ‘sensing’, previously to any act of cousciousness - ‘just looses himself in the scene before him’. The Polichinello secret of cinema watching is nonetheless too evident to be seen, and that is where Phenomenological description and reduction are still required.

Cafuza, Mulata, Negra: body and memory in the discourse of brazilian beers

This article aims to undertake a discursive analysis of the label and advertising material of three beers sold in Brazil: the Cafuza beer, the Mulata beer and Devassa Negra beer. Starting from the regularity that binds and weaves the statements in question - the reference to the African-Brazilian woman - the objective is to present an analysis that considers the semiotic nature of these statements, and bring out their enunciation margins and its historical dimension. The purpose is to analyze the discursive thread that provides conditions of emergence, providing visibility to the scenario of enslavement still perdurable here as historical a priori, in a game of memories that echo through time. What we will see is the body of the black woman (also mulatto and black-indian woman) caught by a discourse that comes from the image of the female sexual slavery and reaches today its exacerbation, especially if we think of the (con)fusion established between the brand names of those beers and the women printed on their labels: products to be consumed? As a theoretical and methodological framework, this article will have as a starting point the discussions made within the French Discourse Analysis in the course of the 1980s. We will bring forward a discussion, although in general, on how emerges, in that decade, the concerns about a semiotic materiality of discourse, beyond the linguistic materiality. Anchored by this panorama, our goal is to work out new perspectives through its analytical application. It is the attempt to take the statement considering the different languages that comprise it, as well as to provide it with the historical density intrinsic to it, making it appear, in the light of the day, what was not visible immediately.

BODY AND VISUALITY OF CONCHITA IN LA FEMME ET LE PANTIN

This paper aims to discuss the construction of the image of Conchita character within the novel La femme et le Pantin, written by Pierre Louÿs in 1898, along with reference works and translations of literature, painting and film. Work genre romance unconfessable presents relational features the seduction and the making of the feminine about the subversion of the ideals of womanhood in the fin-de-sciècle, using the idiosyncrasy of the physical body and the Spanish character, before the traditional values of the time, and how about overcoming the idea of courtly love. This process meant that these elements interact continuously among themselves, establishing itself as a new perspective to the construction of the female character in his fiction. Thus, this discussion takes place on different aspects of development, from the direct reading of the authors and the novel as a basis, considering the character alive as a result of the relationship between memory, culture and time.