[
    {
        "id": "osp-15892",
        "type": "article-journal",
        "title": "Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning",
        "author": [
            {
                "family": "Shen",
                "given": "Lingyu"
            },
            {
                "family": "Tang",
                "given": "Wei"
            },
            {
                "family": "Karray",
                "given": "Fakhri"
            },
            {
                "family": "Zhang",
                "given": "Min-Ling"
            }
        ],
        "URL": "https://omanscience.com/en/articles/joint-class-time-learning-for-video-classification-with-multi-instance-partial-label-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classification. However, bag-level labels do not explicitly supervise the correspondence between candidate classes and temporal evidence. We propose {\\ours}, which couples label disambiguation with temporal evidence allocation through a joint class--time assignment. Occupancy-regularized spherical matching associates contextualized video features while learning nonuniform temporal mass and discouraging excessive concentration. During training, candidate-restricted inference recomputes the assignment within the candidate label set. A dual-marginal KL projection then constructs a structured teacher that incorporates momentum-refined class beliefs while preserving the proposal's temporal occupancy. A single plan-level KL objective aligns the full-space predictor with this teacher. Our analysis characterizes when candidate re-solving differs from masking and shows that, under the stated construction, the joint objective decomposes into class-marginal and class-conditional temporal supervision. We construct VCMIPL benchmarks from Breakfast, DoTA, and FineAction using model-generated candidate labels and evaluate the method across four feature representations. Extensive experimental results demonstrate that PIVOTMIPL outperforms existing MIPL algorithms in both effectiveness and efficiency."
    }
]