ShodhKosh: Journal of Visual and Performing Arts

DEEP LEARNING APPROACHES TO EMOTION RECOGNITION IN PHOTOGRAPHIC IMAGES

2026-01-02T11:21:02+00:00

Photo Emotion Recognition (PER) is supposed to learn what emotion is expressed or invoked by an image based on visual representations of color harmony, composition, object-scene semantics, human expressions in the presence when possible. In contrast to face-centric affect analysis, PER needs to analyze the emotions that frequently are a result of situational semantics and aesthetics, as opposed to explicit facial expression. This enhances ambiguity, label subjectivity, and overlapping of the classes. Additionally, the benchmarks of PER are often characterized by class imbalance and noisy annotations because of the different human perceptions. The paper is a complete analytical PER study with a proposed hybrid deep learning model (combines convolutional representations and transformer) to simultaneously identify low-level aesthetic representations and global semantic context. The proposed architecture includes CNN and transformer branches with regard to local texture color stimuli and long-range relational reasoning respectively, followed by the gated-feature fusion and using a balanced classification head. Class-balanced focal loss, label smoothing and emotion-preserving augmentation are used to construct a robust training pipeline, which prevents the distortions that are likely to alter affective meaning. The assessments of the results include macro-F1, per-class sensitivity, and the confusion behavior among the neighbouring emotions, calibration, and cross-domain strength. Numerous experiments of ablation prove that fusion and high-resistance loss decisions are always more effective on the macro-F1 and assist less in common confusions (e.g., fear vs. surprise, sadness vs. contentment/neutral). Lastly, it is a case of explainability analysis through gradient-based localization to determine whether the predictions are in agreement with the emotionally salient regions. Conclusion of the paper is deployment advice (latency, model size, and quantization) and ethical inferences of subjective affect modelling.

ASSESSING THE IMPACT OF ARTIFICIAL INTELLIGENCE ON VISUAL MARKETING MANAGEMENT

2025-12-31T13:14:16+00:00

The growing role of the visual content in the internet has made visual marketing as a highly significant strategic position in the contemporary marketing management. At the same time, the evolution of Artificial Intelligence (AI) has enabled organizations to analyze, customize, and streamline the marketing efforts in visuals on a platform and scale never before attempted or achieved. The paper discusses the AI application in visual marketing management by examining the ways that the AI capabilities have transformed strategic planning, content creation, personalization, monitoring, and optimization of visual campaigns. The research that is founded on the overall assessment of academic literature and formulated analytical theories frames AI as the empowering management attribute, but not the technology application. Consequently, based on the analysis, one can mention that the visual marketing processes are supported by the use of computer vision, predictive analytics, and generative AI in data-driven decision-making, the real-time performance measurement, and the continuous learning processes. The paper also provides the assessment of whether visual marketing can be affected by AI or not and induce the short-term performance indicators, such as engagement and conversion rates, and the long-term brand equity indicators, such as brand recall and consumer trust. In addition, the study describes the managerial and ethical issues regarding the AI adoption, including data privacy, algorithmic bias, transparency and human control. The current research contributes an analytical value to the management of AI-based visual marketing by combining strategic, operational, and governance strategies. The findings may be applicable to researchers and specialists who are interested in referring to AI as the basis of effective and responsible visual marketing in online services that are more competitive.

DEEP LEARNING FOR PHOTO EMOTION RECOGNITION

2025-12-31T13:09:35+00:00

Photographic emotion recognition has become an important field of research application in the interface of computer vision, affective computing, and deep learning, and has been applied in digital media analysis, human-computer interaction, mental health assessment, and content behavioral AI. In comparison to object or scene recognition, photo emotion recognition is the recognition of subjective affective reactions that visual stimuli trigger, which means that the task is an inherently difficult and situation-specific task. This paper introduces a deep learning-based emotion recognition model of the expressions of photographic images incorporating the psychological theories of emotions with the state-of-the-art convolutional neural network models. The framework of the proposed solution is also based on the known models of emotions, such as valence-arousal dimensions, discrete categories of emotions, which allow mapping visual patterns and affective semantics systematically. Hierarchy Visual features like color distributions, texture gradients, lighting and composition balance are represented by hierarchical feature extraction to achieve low level perceptual features of the visual image and high-level semantic features of the visual image. It uses a properly selected and annotated dataset of emotions, that are backed up by strong preprocessing and data augmentation techniques to increase generalization. The deep neural network applies convolutional learning of features and attention mechanism to highlight emotional regions of the image. Large-scale experiments are performed based on regularized training, validation, and testing conditions, and performance is measured against various baseline models in terms of accuracy, precision, recall, and F1-score measures.

EVALUATING THE ROLE OF AI IN VISUAL MARKETING MANAGEMENT

2025-12-31T13:09:36+00:00

The design practices on which the visual marketing management is founded have evolved into the data-driven and analytics-based systems of decisions. The following paper is an evaluation of the way AI will be used to radically transform the management of visual marketing by automated analysis, creating, optimization and controlling of visual content in online platforms. The research is premised on the visual communication and computational intelligence theory, and the authors present how computer vision, deep learning, and generative AI models can assist visual marketing to generate and implement strategic designs more effectively. It implies a fully experimental design that involves enormous image and video files created as a result of branding and advertising campaigns and social media promotion. It is measured in multi-level measures which include visual effectiveness, brand consistency, audience engagement and ROI. Empirical results of the research demonstrates that AI based visual marketing systems are much more useful in increasing relevance of content, emotion and cross platform compatibility of brands compared with manual systems or rule based systems. The outcomes also indicate measurable increase in efficacy of the campaigns, quicker design procedures, and better consistency of the enforcement of the brand identity.

DECODING VIEWER EMOTIONS IN VISUAL MEDIA: NEUROMARKETING PERSPECTIVES ON DIGITAL ART AND ONLINE VISUAL ADVERTISING

2025-12-31T07:49:43+00:00

The emotional reaction of the viewer to visual media is one of the key issues of digital art and visual advertising online where the aesthetic impression directly determines the attention, memory, and choice. Current methods of evaluation are based on self-reports and superficial measures of engagement which provide little information on underlying affective reactions that underlie consumer behavior. This gap has been filled in this paper by considering viewer emotion decoding in the light of neuromarketing viewpoint that involves applying computational emotion analysis with visual media research. The main goal is to explore the effects of visual characteristics, narrative, and style in digital art and web-based advertisements in order to stimulate measurable emotional response and connect such a response to the results of engagement and persuasion. The paper is a synthesis of results on emotion recognition models, biometric measures, and behavioral analytics to create a hybrid framework of analytical analysis of affect-based visual comparison. The central results have shown that emotion-sensitive visual design is much more efficient in retaining attention, emotional appeal, and brand memorability, as positive affect and moderate arousal become the most prominent predictors of the viewer involvement in any platform. Moreover, the adaptive images in terms of emotions proved to be more effective than the non-adaptive ones in respect of having the artistic meaning and selling messages. The paper has a wider scope than commercial advertising in respect to digital art shows, immersive media and culturally contextual visual storytelling, with an emphasis on ethical aspects and issues on interpretability. This work provides a systematic base of the research on emotionally intelligent visual media and the potential further study of visual communication and neural markers by connecting neuromarketing and visual analytics based on AI and emotion recognition.

BLOCKCHAIN AND THE VISUAL ARTS ECOSYSTEM: DISRUPTIVE IMPACTS ON DIGITAL ART OWNERSHIP, NFTS, AND CREATIVE ECONOMIES

2025-12-31T07:26:54+00:00

One of the ways in which blockchain technology is transforming the visual arts ecosystem is by providing decentralized, transparent, and verifiable systems of ownership, distribution, and value exchange of digital art. This paper analyzes how blockchain has been disruptive to visual arts in modern times, specifically in non-fungible tokens (NFTs), creative economies, and artist-collector relationships. Historically, the digital artworks were associated with the issues with provenance, copyright protection, scarcity, and justifiable monetization. Blockchain overcomes these weaknesses by providing immutable registries, smart contracts, and tokenization to allow artists to have verifiable ownership, determine authenticity, and earn automatic royalties on transactions in the secondary market. The study takes a conceptual and analytical structure by synthesising the extant literature, platform case studies and new blockchain-based art markets to assess the worth of NFTs in redefining artistic value, authorship and market forces. The results suggest that blockchain makes global art markets more democratic by decreasing the use of intermediaries including galleries and auction houses, which are central, and thus giving power to independent and new artists. Simultaneously, it cultivates new creative economies in which digital scramble, community contribution and speculative finance overlap. Nevertheless, the paper also singles out some fundamental challenges such as environmental sustainability issues, market unpredictability, regulatory ambiguity and the issues of artistic legitimacy and cultural value. The article presents the argument that although blockchain does not substitute the traditional art institutions, it supports them by providing hybrid ecosystems through integrations of physical and digital practices. All in all, the study suggests blockchain as a revolutionary infrastructure to the visual arts, reinventing ownership, trust, and economic frameworks and proposing a sustainable, ethical, and inclusive future to enable the long-term development of digital art ecosystems.

EXPERIENTIAL AESTHETICS IN VISUAL ARTS CONSUMPTION: FANTASY, EMOTION, AND ENJOYMENT IN CONTEMPORARY ART EXPERIENCES

2025-12-31T06:46:00+00:00

Experiential aesthetics has become a key point of focus in attempting to comprehend how modern viewers approach visual arts outside of the frame of formal analysis in a way that focuses on experience, emotion, and engagement of the imagination. The paper examines the inter-relationship between fantasy, emotion, and enjoyment in determining visual art consumption as a part of contemporary art experiences. The study uses phenomenological aesthetics and cognitive-affective theories, in which the conceptualization of aesthetic engagement is an embodied process with an interpretive and emotionally situated process. Fantasy is explored as one of the most important experiential forces that allow the viewers to immerse in the story, create symbolic meaning and imaginary worlds of art, creating their own meanings and speculative worlds as they engage with works of art. The paper also examines the emotional aspects of visual art viewing, such as emotion eliciting mechanisms, empathic resonance, mood, and affective bonding, and the moderating role of cultural, social and contextual factors. Pleasure is conceptualized in the context of hedonic enjoyment and eudaimonic satisfaction and it emphasizes flow, absorption, and reflective pleasure as the keys to long-term aesthetic values and recurring interest and involvement. The paper is methodologically designed in terms of a mixed-methods approach that incorporates both qualitative interviews, observational and narrative analyses with quantitative survey instruments and psychometric modeling to produce both subjective depth and the quantifiable patterns.

ARTIFICIAL INTELLIGENCE IN CREATIVE WORKFORCE ANALYTICS: MANAGING TALENT AND PERFORMANCE IN VISUAL ARTS ORGANIZATIONS

2025-12-31T06:26:30+00:00

The visual arts organizations are moving toward a more complicated, project-driven ecosystem in which it is challenging to quantify creativity, collaboration, and performance through more traditional management strategies. The paper explores how artificial intelligence may be used as a tool to analyze the creative workforce, in this case, how talent management and performance optimization in visual arts institutions could be boosted through the use of data-driven approaches. The suggested model combines diverse information sources such as digital portfolios, project history, peer ratings, and audience engagement indicators to form multidimensional creative professional profiles. Clustering, predictive modeling, and sentiment analysis are some of the machine learning methods used to facilitate the segmentation of talent, alignment of roles, and prediction of the creative performance outcomes. AI-aided recruitment processes can improve portfolio analysis because it helps to detect hidden competencies, stylistic coherence and innovation potential that cannot be evaluated through subjective human judgment. Parallel to it, performance analytics models integrate quantitative metrics with qualitative feedback in order to determine creative productivity, collaborative and emotional reactions to critique. The evidence provided by the experiment, which is based on simulated institutional datasets, shows that the efficiency of talent utilization, the quality of project outcomes and transparency of the decision made significantly improve in comparison with the conventional workforce management techniques. The results emphasize the ability of AI to strike a balance between creative subjectivity and analytical rigor that allows to make an evidence-based decision and retain the autonomy of the creativity.

SUSTAINABLE GOVERNANCE IN DIGITAL ART AND CREATIVE FINTECH: INTEGRATING GREEN INNOVATION WITHIN VISUAL CULTURE INDUSTRIES

2025-12-31T06:26:04+00:00

Green innovation is presented as a systematic approach to the process of integrating green into models of governance that can be used to define digital art platforms, creative markets, and FinTech-based cultural economies. Based on the sustainable governance theory, eco-digital transformation frameworks, and ethical literature in the area of FinTech, the research constructs a conceptual framework connecting environmental responsibility with transparency, accountability, and cultural value creation. The paper presents a study of the digital art- FinTech ecosystem placing emphasis on platform frameworks, assetization through NFT, tokenized forms of ownership, and the environmental impact associated therewith. It follows a mixed-method research design, which involves a qualitative policy and platform analysis and quantitative evaluation of energy consumption, the carbon intensity, and efficiency measures in case studies. The evidence shows that energy-efficient blockchain protocol, green FinTech instruments, and circular practices of digital production have an enormous impact on reducing the environmental footprint and increasing trust and economic resilience in the long term. In addition, governance systems, which tie sustainability measures to platform policies, smart-contracts and economic incentives, can be used to encourage responsible innovation without limiting artistic expression.

VISUAL COMMUNICATION STRATEGIES IN DIGITAL CRISIS MANAGEMENT: AN AI-ENABLED MEDIA ANALYSIS APPROACH

2025-12-29T12:03:17+00:00

This paper examines the visual communication techniques used in crisis management regarding the digital environment with the help of an AI-enhanced media analysis system that allows evaluating the tools of clarity, credibility, and emotional appeal on the platform quickly on the high-velocity. In times of crisis, the visuals that are spread through social media, news portals, and official dashboards have a potent impact in shaping the perception of people and their actions, but the evaluation is rather divided and subjective. This study aims at coming up with a scalable system that will measure the visual effectiveness and compliance with the crisis communication objectives. The given method involves the usage of computer vision, multimodal transformers, and graph-based diffusion modelling, which would be applied to analyze the image, infographics, maps, and video frames and capture and temporal contexts. Models of elements to do with salience, color semantics, iconography, spatial hierarchy, facial affect and uncertainty cues are extracted and combined with signals that relate to engagement and propagation. The performance of strategy is determined through indicators of understanding, credibility, emotional control and risk of misinformation. Multi-crisis Multi-crisis experiments on multi-crisis datasets in the fields of public health, natural disasters and infrastructure failures indicate that the framework is better at detecting misleading visuals, and design of messages, which improve in understanding predictions by up to 18% and anxiety amplifying factors, respectively, over baseline heuristics. Heatmaps and design suggestions are offered to communicators in real-time with the help of interpretable outputs. These results allow concluding that AI-based visual analytics has the potential to positively influence the crisis-related coordination, transparency, and compliance with media members and agencies, providing them with the necessary actions to follow and assisting in the work.