Search results

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

This paper is aimed at examining and critically analyzing systematical literature on wine and cross-modality between the five senses. In particular, the researchers want to highlight the role of multisensory analysis on wine marketing and consumer behavior studies.

This paper is based on a systematic review of literature conducted on peer-reviewed journals.

Results highlight how multisensory analysis of wine is a growing topic insomuch that research on this kind of topic is exploded in the last years. Nevertheless, wine and cross-modality is more analyzed on food science journals than in marketing ones.

The paper examines a field of research moderately explored in order to shed light to the current status of scientific studies and to propose new research questions to develop.

Explores the interval nature of semantic scale adjectives across three languages: English, Putonghua Chinese, and Japanese. Reports on a pilot study conducted among native speakers of each language using the techniques of magnitude scaling. Respondents rated an assortment of common adjectives by comparing the magnitude of the word to a given modulus. The results indicate that the traditional translation/back‐translation technique may not provide response intervals that are comparable cross‐culturally. Further, between languages the results indicate that the meaning attached to the adjectives by native speakers varies substantially. Discusses implications for market research, as well as future areas of research.

A considerable body of literature has shown how the perception of flavor is the result of a multi-sensory combination. Starting with this premise, this paper aims to verify how music impacts on wine flavor.

An experiment was organized as follows: it focuses on the influence of music on the taste of red and white wine, in particular, two kinds of music were transmitted, namely, classical and pop. Participants had to listen to music through headphones tasting, in the meanwhile, 40 mL of wine (an merlot and a chardonnay). After this experience, they had to give an evaluation about some attributes of the wine. The attributes to be evaluated were: sparkling, refreshing, delicate, refined, sweet, sour, alcoholic and pleasant. Data were finally analyzed by using the ANOVA model.

They highlight that a chardonnay is perceived to be more delicate and sweeter if accompanied by a classical music background; in the case of Merlot, on the other hand, it is perceived as less alcohol when high-volume pop music is transmitted. Implications are finally discussed.

The influence of hearing on taste is underestimated in the literature. The originality of this manuscript consists of comparing two different music genders and their impact on wine consumers in an Italian context. Moreover, the analysis of marketing implications represents a novelty for these kind of studies.

This paper aimed to inform research or collection development on the topic of Claude Debussy, with particular attention paid to English-language resources that highlight the cross-modal nature of his work.

This objective was achieved by examining primary and secondary sources relating to the works and correspondences of Debussy and those of painter James Abbott McNeill Whistler, and the works of poet Charles Baudelaire, whose work influenced Debussy.

Holistically studying Debussy and his contemporary influences enables the researcher to develop a richer understanding of Debussy's work.

This paper may have implications for research on James Abbott McNeill Whistler, Charles Baudelaire, Impressionism, and Symbolism.

The purpose of this paper is to develop a comprehensive conceptual framework of visual-tactile interplay and consumer responses in brand, product and servicescape contexts.

This paper performs a literature review of visual-tactile interplay by reviewing prior research in marketing and psychology.

The review reveals that visual-tactile interplay provokes various consumer responses depending on whether brands, products or servicescapes are used. The paper develops a comprehensive conceptual framework mapping out visual-tactile interplay and the relationship with consumers’ cognition, emotions and behaviors.

A conceptual model was developed with a novel view on how visual and tactile cues can together influence consumer responses.

This paper shows how visual-tactile interplay is successful in brand, product and servicescape contexts and provides practical insight for firms into how to provoke consumers’ cognitive, emotional and behavioral responses.

This paper contributes to existing literature by developing a conceptual framework and model of visual-tactile interplay and consumer responses by drawing on research in marketing and psychology.

Research on cross-modal sensory interactions has shown that visual aspects of food can influence consumer's expectation and perception of taste, mouthfeel and liking. This paper aims to investigate the effects of a rounded (“bouba”) and a squared (“kiki”) shape on expected and perceived sweetness, bitterness, creaminess and liking of chocolates.

Brazilian consumers (N = 230) divided into two groups of 115 individuals each evaluated five chocolates containing 30, 40, 50, 60 and 70% of cocoa. One of the groups evaluated all formulations in the rounded shape and the other in the squared shape. Results were analysed with mixed multivariate analysis of variance (mixed-MANOVA) between shapes, repeated-measures MANOVA between pre- and post-tasting and Pearson's correlation analysis was performed between liking ratings and sweetness, bitterness and creaminess confirmation/disconfirmation.

The study found significant effects (p < 0.05) of shape on expected and perceived creaminess but not on other attributes; of cocoa percentage (30, 40, 50, 60 and 70%) on all four attributes; and time (pre- and post-tasting) on sweetness, bitterness and liking but not creaminess. Finally, it found significant negative correlations between the creaminess difference indices and the liking ratings for the 30, 50 and 60% chocolates.

This study reports that consumers may expect and perceive chocolates as creamier in a rounded shape than in an angular shape and that if the expectation of creaminess is not confirmed by sensory perception, acceptability may be negatively affected.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

This paper aims to extend current understanding concerning the cross-modal correspondences between sounds and tastes by introducing new research tools and experimental data to study associations and their reflections between music and taste.

The experiment design addresses the multidisciplinary approach by using cultural, chemical and statistical analysis methods.

The paper provides further evidence that exposure to the “sweet” or “sour” musical pieces influences people’s food-related thinking processes and behaviors. It also demonstrates that sweet or sour elements in the music may reflect to actual sweetness (as measured by sugar content) and sourness (as measured by organic acid content) of foods developed in association with music carrying similar taste characteristics.

The findings should be replicated and expanded using larger consumer samples and wider repertoires of “taste music” and dependent variables. Also, the level of experimental control should be improved; e.g., the “sweet” and “sour” music were produced using different instruments, which may have an influence to the results.

Ambient “taste music” that is congruent with the basic flavors of the dishes can be played in restaurants to highlight guests’ sensory experience.

By carefully considering the symbolic meanings of the music used in different social situations, it is possible to create multimodal experiences and even subconscious expectations in people’ minds.

Cross-modal associations are made between the tastes and music. This can influence on perception of food and provide new ways to build multimodal gastronomic experiences.

This study aims to understand social media users’ responses to the influencer-endorsed wine short videos on the most popular platform – Douyin, relying on message interpretation process (MIP) framework and identify segmentation differences from gender and the generational cohorts (Gen Z and Gen Y).

Topic modeling, content analysis and quantitative analysis were used to decipher the user-generated content (UGC) data retrieved from 81 wine videos posted by the top 30 social media influencers (SMI) who focused on wine products and consumption experience messages.

The results demonstrate social media users are most inclined to respond to product-related topics, followed by the influencer, emotional, alcohol drinking intent, behavioral and skepticism. Meanwhile, the findings also revealed that the female group was more likely to engage in influencer topics, whereas the male group contributed more to product subjects. Gen Z cohort involved more themes about alcohol drinking intent, whereas Gen Y contributed more to skepticism.

The findings provide hospitality and wine practitioners, SMI and brand sponsors valuable information to use this advanced tactic among various social networking services.

This study is the first to grasp the Douyin users’ perceptions of this newly emerged influencer marketing strategy via UGC data. Originality is established by investigating gender and generational cohorts’ differences underlined by MIP.

顾客在 TikTok（抖音）对网红葡萄酒营销短视频有何见解？探索性别和代际差异

本研究旨在了解社交媒体用户对最受欢迎的平台 - 抖音- 的网红认可的葡萄酒短视频的反应, 依靠消息解释过程 (MIP) 框架, 并识别性别和世代群组的细分差异（Z世代和 Y 世代）。

利用主题建模、内容分析和定量分析来破译从30 名社交媒体网红发布的 81 个葡萄酒视频中关注葡萄酒产品和消费体验信息检索到的 UGC 数据。

结果表明, 社交媒体用户最倾向于回应产品相关话题, 其次是影响者、情绪、饮酒意图、行为和怀疑态度。同时, 调查结果还显示, 女性群体更可能参与有社交媒体网红主题的话题, 而男性群体对产品主题的贡献更大。 Z 世代队列涉及更多关于饮酒意图的主题, 而 Y 世代则表现更多怀疑。

研究结果为酒店和葡萄酒从业者、社交媒体影响者和品牌赞助商提供了宝贵的信息, 以在各种社交网络服务中使用这种先进的策略。

这项研究首次通过 UGC 数据掌握了抖音用户对这种新兴的网红营销策略的看法。通过 MIP 体现性别和代际群体的差异从而体现本研究的原创价值。