Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning

arXiv:2610.06234v1 Announce Type: new 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.

Related

• CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting
• SAGE-Yoga: Multi-Cue Learning for Yoga Pose Classification and Joint-Level Correction
• CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval

Source: arXiv cs.CV | 2026-10-06