联合类-时间学习用于多实例部分标签学习的视频分类

中文摘要 AI 辅助

多实例部分标签学习（MIPL）解决了实例空间和标签空间中的不精确监督问题，可应用于视频分类。然而，包级标签并未显式监督候选类别与时间证据之间的对应关系。我们提出了PIVOTMIPL，通过联合类-时间分配将标签消歧与时间证据分配相结合。占用正则化的球面匹配在关联上下文视频特征的同时，学习非均匀的时间质量分布，并抑制过度集中。在训练过程中，候选受限推理在候选标签集内重新计算分配。随后，双边际KL投影构建了一个结构化教师模型，该模型融合了动量精炼的类别信念，同时保留提议的时间占用。一个单一的计划级KL目标将全空间预测器与该教师模型对齐。我们的分析刻画了候选重新求解与掩蔽不同的条件，并表明在所提出的构造下，联合目标可分解为类边际和类条件时间监督。我们使用模型生成的候选标签从Breakfast、DoTA和FineAction构建了VCMIPL基准，并在四种特征表示上评估了该方法。大量实验结果表明，PIVOTMIPL在有效性和效率方面均优于现有的MIPL算法。

英文摘要

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.

发表机构

• Southeast University（东南大学）
• Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）

机构由 AI 辅助整理，请以论文原文为准。