Call For Papers

Persuasive visual communication is becoming increasingly central to modern AI systems, ranging from recommender systems and advertising platforms to multimodal AI agents and generative assistants. These systems not only interpret visual information, but also generate multimodal content capable of influencing beliefs, decisions, emotions, and behaviors.

Despite rapid advances in multimodal foundation models, existing research primarily evaluates systems based on recognition accuracy, reasoning capability, or generation quality, while largely overlooking persuasive impact and communicative intent. In practice, visual persuasion often operates implicitly through symbolism, metaphorical structures, emotional framing, contextual cues, and cultural references that require sophisticated multimodal reasoning.

The VisPer Workshop aims to establish visual persuasion as an emerging research direction at the intersection of computer vision, multimodal AI, generative modeling, creativity, human-centered AI, and computational social science. The workshop will bring together researchers from academia and industry to discuss how AI systems can understand, generate, evaluate, personalize, and responsibly regulate persuasive visual content.

We invite submissions presenting across diverse topics, including but not limited to benchmarks, datasets, evaluation frameworks, methodologies, and theoretical perspectives related to persuasive multimodal communication and reasoning.

Topics include, but are not limited to:

• Benchmarks and evaluation metrics for persuasive effectiveness

• Multimodal reasoning and generative modeling for persuasion

• Personalized content understanding and generation

• Cross-cultural and personalized persuasion modeling

• Detection of manipulative or misleading persuasive strategies

• Affective and sensory modeling in visual communication

• Persuasive communication in recommender systems and AI agents

• Creativity, symbolism, and metaphor understanding and generation

• Visual misinformation and fake news

• Fairness, transparency, and responsible persuasive AI systems

Submission Types

We will solicit both:

• Archival submissions (8 pages)

• Non-archival submissions (4 pages)

Following the official ECCV 2026 formatting guidelines. All accepted papers will be presented as posters during the workshop.

Timeline

• July 15, 2026 - Paper Submission Deadline

• July 29, 2026 - Acceptance Notifications

• August 15, 2026 - Camera-Ready Deadline

Submission instruction

Submission Portal:   OpenReview

Dual Submissions

Dual submissions are allowed only in the non-archival track. This includes papers that are currently under review as well as papers that have already been accepted for publication in a conference proceedings or journal.