Special Issue on Social, Emotional, and Cognitive Visual Intelligence Call for Papers

International Journal of Computer Vision

Special Issue on Social, Emotional, and Cognitive Visual Intelligence

Recent advances in computer vision have produced major progress in
recognizing objects, actions, scenes, and events. However, a
significant gap remains between conventional visual recognition and
human perceptual intelligence: the ability to recognize,
contextualize, and interpret emotions, intentions, beliefs, social
interactions, and subjective experiences from visual observations.

This special issue focuses on social, emotional, and cognitive visual
intelligence, an emerging direction that extends computer vision from
recognizing observable entities to modeling human-centered
meaning. These problems involve latent states, ambiguity, context
dependence, cultural and individual variation, and multiple plausible
interpretations. Recent progress in multimodal foundation models,
vision-language learning, video understanding, and human-centered AI
makes this a timely and important direction for the computer vision
community.

We invite original research contributions that advance the theory,
methods, datasets, evaluation protocols, and applications of social,
emotional, and cognitive computer vision. Topics of interest include,
but are not limited to:

    Visual modeling of affective, cognitive, behavioral, and
    subjective attributes or states;

    Understanding social interaction, gesture, gaze, body language,
    group behavior, and human-agent interaction;

    Movement-in-context modeling, including approaches that treat
    emotion and social meaning as relational and contextually
    situated;

    Context-aware and subjective visual understanding, including
    ambiguity, uncertainty, cultural context, and individual
    differences;

    Multimodal and foundation models for social perception, including
    vision-language, audio-visual, physiological, and cross-modal
    learning;

    Synthesis, simulation, and generation of emotional and socially
    meaningful human behavior;

    New learning paradigms for socially grounded vision, including
    self-supervised, weakly supervised, causal, generative, and
    transfer learning approaches;

    Datasets, benchmarks, annotation methods, and evaluation metrics
    for subjective and socially situated visual understanding;

    Robustness, fairness, privacy, and responsible deployment of
    vision systems that model human attributes;

    Human-centered applications in healthcare, education, assistive
    technologies, robotics, human-computer interaction, and socially
    aware AI.

Important Dates
 Submission deadline: 15 December 2026
 First-round notification: 1 April 2027
 Revised manuscript deadline: 1 June 2027
 Final decision notification: 15 July 2027
 Expected publication: August/September 2027

Full Call for Papers: https://wang.ist.psu.edu/docs/docs/IJCV-CFP.pdf