[
    {
        "id": "osp-15692",
        "type": "article-journal",
        "title": "Emoception: Selective Affective Layer Fine-Tuning of Video Vision Transformers for Player Arousal Change Recognition From Gameplay Footage",
        "author": [
            {
                "family": "Xia",
                "given": "Yi"
            },
            {
                "family": "Khan",
                "given": "Ibrahim"
            },
            {
                "family": "Dewantoro",
                "given": "Mury Fajar"
            },
            {
                "family": "Ouyang",
                "given": "Wenwen"
            },
            {
                "family": "Thawonmas",
                "given": "Ruck"
            }
        ],
        "URL": "https://omanscience.com/en/articles/emoception-selective-affective-layer-fine-tuning-of-video-vision-transformers-for-player-arousal-change-recognition-from-gameplay-footage",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "DOI": "10.1109/tg.2026.3691772",
        "abstract": "This article proposes Selective Affective Layer Fine-Tuning (SALFT), an efficient adaptation framework for Video Vision Transformers in player arousal recognition from gameplay. To bypass computationally expensive full fine-tuning, SALFT introduces a selection criterion based on the L2-norm change in layer parameters after brief adaptation, directly measuring representational shifts and providing a more stable basis than gradient-based alternatives. Evaluated via five-fold cross-validation on the Arousal Video Game AnnotatIoN dataset, SALFT achieves performance comparable to full fine-tuning across all games without statistically significant degradation ($p>0.05$), while updating only $\\approx$8% of parameters (over 92% reduction). Notably, in one game, SALFT consistently outperforms both full fine-tuning and the best baseline across all metrics and folds, reaching the theoretical minimum p-value (p=0.0625, exact two-sided Wilcoxon signed-rank test). In addition, we introduce an interpretability method to trace attention patterns, enhancing model transparency. These results establish SALFT as an effective and efficient approach for affective game computing."
    }
]