Out-of-distribution (OOD) detection is crucial for applying machine learning systems in open-world scenarios. However, existing multimodal video OOD benchmarks typically construct in-distribution (ID) and OOD splits via sequential class partitioning, which does not explicitly account for feature-space relationships between categories. This limitation may inadvertently introduce semantic ambiguity when similar classes are assigned to opposite sides of the split. In this paper, we propose Cluster-Based Cross-Validation (CB-CV), an alternative evaluation protocol that organizes classes by feature-space similarity. In CB-CV, class prototypes are derived from a dual-stream backbone, clustered based on inter-class distances, and evaluated via leave-one-cluster-out cross-validation, where each cluster serves as the ID set and the remaining clusters form the OOD set. Across 1,701 pipeline configurations spanning three datasets, CB-CV increases the mean ID–OOD distance by 18.5% compared to sequential partitioning (p < 0.001). This distance is moderately predictive of detection performance overall (r = −0.600 with False Positive Rate at 95% True Positive Rate (FPR95)), but the strength of the relationship varies widely across methods (FPR95 correlations ranging from − 0.73 to − 0.25), indicating method-dependent sensitivity to split structure. By reporting results across multiple folds, CB-CV makes this sensitivity explicit and offers an additional characterization of robustness under structured distributional shifts. Together, these results highlight the importance of structure-aware evaluation and position CB-CV as a complementary benchmark for assessing the robustness of multimodal video OOD detection under alternative distributional structures.

This paper investigates the problem of learning mesh-based physical simulations, which is a crucial task with applications in fluid mechanics and aerodynamics. Recent works typically utilize graph neural networks (GNNs) to produce next-time states on irregular meshes by modeling interacting dynamics, and then adopt iterative rollouts for the whole trajectories. However, these methods cannot achieve satisfactory performance in long-term predictions due to the failure of capturing long-term dependency and potential error accumulations. To tackle this, we introduce a new future-to-present learning perspective, and further develop a simple yet effective approach named Foresight And Interpolation (FAIR) for long-term mesh-based simulations. The main idea of our FAIR is to first learn a graph ODE model for coarse long-term predictions and then refine short-term predictions via interpolation. Specifically, FAIR employs a continuous graph ODE model that incorporates past states into the evolution of interacting node representations, which is capable of learning coarse long-term trajectories under a multi-task learning framework. Then, we leverage a channel aggregation strategy to summarize the trajectories for refined short-term predictions, which can be illustrated using an interpolation process. Through pyramid-like alternative propagation between the foresight step and refinement step, our proposed framework FAIR can generate accurate long-term trajectories, achieving a significant error reduction compared with the best baseline on four benchmark datasets. Extensive ablation studies and visualization further validate the superiority of our proposed FAIR.

Graph classification is a fundamental machine learning problem with extensive applications in multimedia and biochemical analysis. Contemporary graph classification models usually require precise graph labels for supervision, even after self-supervised pre-training. However, in practical applications, the extensive precise annotation of graphs could be expensive or impractical. To exploit data efficiently, this work studies partial label graph learning, in which each graph is linked to a set of candidate labels but only one of them is accurate. Label ambiguity would bring difficulties in extracting graph semantics and the risk of overfitting noisy partial labels. Here, we present a novel approach called Coupled Dual Separation (CODE). To improve graph semantics mining under label ambiguity, our CODE contains a message passing branch and a graph kernel branch, which explore graph semantics implicitly and explicitly, respectively. To facilitate information exchange, we utilize one branch to separate partially labeled graphs into an informative set and an uninformative set, which provides guidance for the optimization of the other branch. Furthermore, to mitigate the risk of overfitting, parameters in coupled branches are partitioned into critical and non-critical ones for separated optimization procedures. Extensive experiments on several benchmark datasets validate the effectiveness of the proposed CODE.

This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Prototypical Graph ODE (PGODE) to address the problem. The core of PGODE is to incorporate prototype decomposition from contextual knowledge into a continuous graph ODE framework. Specifically, PGODE employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of PGODE compared to various baselines.

This paper studies the problem of rigid dynamics modeling, which has a wide range of applications in robotics, graphics, and mechanical design. The problem is partly solved by graph neural network (GNN) simulators. However, these approaches cannot effectively handle the relationship between intrinsic continuity and instantaneous changes in rigid dynamics. Moreover, they usually neglect hierarchical structures across mesh nodes and objects in systems. In this paper, we propose a novel approach named Event-attend Graph ODE (EGODE) for effective rigid dynamics modeling. In particular, we describe the rigid system using both mesh node representations and object representations. To model continuous dynamics across hierarchical structures, we use a coupled graph ODE framework for the evolution of both types of representations over a long period. In addition, to capture instantaneous changes during the collision, we introduce an event module, which can effectively estimate the occurrence of the collision and update the states of both mesh node and object representations during evolution. Extensive experiments on a range of benchmark datasets validate the superiority of the proposed EGODE compared to various state-of-the-art baselines. The source code can be found at https://github.com/yuanjypku/EGODE.

With the emergence of AI generated content, cross-modal retrieval of 2D and 3D data has obtained increasing research attention. In practical applications, massive amounts of 2D and 3D data need expensive annotation, which would make labels scarce. Even worse, complicated heterogeneous relationships between 2D and 3D data make the problem more challenging. In this research, we study the problem of semi-supervised 2D and 3D cross-modal retrieval and provide a novel method namedHierarchical Alignment with AmbiguousPseudo-labeling (HOPE) for this problem. The core of HOPE is to align two modalities in the common space from a hierarchical perspective. Specifically, HOPE not only enforces each sample to approach its respective modality-invariant anchors from an individual view, but also measures both prototypes and distribution for both modalities for discrepancy reduction from a group view. To handle label scarcity with limited error accumulation, HOPE employs two branches of perturbed networks to generate ambiguous candidates, which guides the cross-branch supervision using a margin-based ranking objective. In addition, we retrieve reliable unlabeled samples for each anchor with curriculum learning and class balance, which are added into labeled datasets to clear ambiguity. Extensive experiments on various benchmark datasets validate the superiority of the proposed HOPE.