Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on large-scale unlabeled image-tabular data, aiming to learn discriminative representations. However, existing SSL methods for image-tabular representation learning are often confined to specific data cohorts, mainly due to their rigid tabular modeling mechanisms when modeling heterogeneous tabular data. This inter-tabular barrier hinders the multi-modal SSL methods from effectively learning transferrable medical knowledge shared across diverse cohorts. In this paper, we propose a novel SSL framework, namely CITab, designed to learn powerful multi-modal feature representations in a cross-tabular manner. We design the tabular modeling mechanism from a semantic-awareness perspective by integrating column headers as semantic cues, which facilitates transferrable knowledge learning and the scalability in utilizing multiple data sources for pretraining. Additionally, we propose a prototype-guided mixture-of-linear layer (P-MoLin) module for tabular feature specialization, empowering the model to effectively handle the heterogeneity of tabular data and explore the underlying medical concepts. We conduct comprehensive evaluations on Alzheimer's disease diagnosis task across three publicly available data cohorts containing 4,461 subjects. Experimental results demonstrate that CITab outperforms state-of-the-art approaches, paving the way for effective and scalable cross-tabular multi-modal learning.

Multivariate Time-Series (MTS) analysis is crucial across various domains. Considering the spatial and temporal consistency of MTS, existing methods leverage graph structures with temporal augmentation and contrastive learning to achieve robust learning of spatial dependencies and temporal patterns. Given the inherent high-order correlations in MTS, hypergraphs present a promising approach. However, two key challenges limit their further development: 1) Feature-based perspectives capture limited spatial information, while structural perspectives encode richer spatial consistency and evolution dependency; 2) Various semantic patterns (e.g., synergy, inhibition) entangle in sensor correlations, leading to semantic ambiguity. The underlying reason is that conventional hypergraph structures cannot distinguish specific semantic roles within or across hyperedges. Thus, we propose Role Hypergraph Contrastive Learning for MTS analysis. Specifically, we introduce the concept of role to generalize hypergraphs to Role Hypergraphs, enabling precise modeling of sensor correlations by assigning each vertex-hyperedge pair with a semantic role. Building on this structure, we design a role hypergraph contrastive learning paradigm to comprehensively capture the spatial and temporal dependencies: From a structural perspective, role hypergraph structural contrasting captures spatial short-term consistency and long-term evolution; from a feature perspective, alignment of complementary role information ensures sensor-level temporal consistency. Experiments on classification and forecasting tasks demonstrate the effectiveness and interpretability of our method.

Accurate temporal prediction is the bridge between comprehensive scene understanding and embodied artificial intelligence. However, predicting multiple fine-grained states of scene at multiple temporal scales is difficult for vision-language models. We formalize the Multi‐Scale Temporal Prediction (MSTP) task in general and surgical scene by decomposing multi‐scale into two orthogonal dimensions: the temporal scale, forecasting states of human and surgery at varying look‐ahead intervals, and the state scale, modeling a hierarchy of states in general and surgical scene. For instance in general scene, states of contacting relationship are finer-grained than states of spatial relationship. For instance in surgical scene, medium‐level steps are finer‐grained than high‐level phases yet remain constrained by their encompassing phase. To support this unified task, we introduce the first MSTP Benchmark, featuring synchronized annotations across multiple state scales and temporal scales. We further propose a novel method, Incremental Generation and Multi‐agent Collaboration (IG-MC), which integrates two key innovations. Firstly, we propose an plug-and-play incremental generation to keep high-quality temporal prediction that continuously synthesizes up-to-date visual previews at expanding temporal scales to inform multiple decision-making agents, ensuring decision content and generated visuals remain synchronized and preventing performance degradation as look‐ahead intervals lengthen. Secondly, we propose a decision‐driven multi‐agent collaboration framework for multiple states prediction, comprising generation, initiation, and multi‐state assessment agents that dynamically triggers and evaluates prediction cycles to balance global coherence and local fidelity. Extensive experiments on the MSTP Benchmark in general and surgical scene show that IG‐MC is a generalizable plug-and-play method for MSTP, demonstrating the effectiveness of incremental generation and the stability of decision‐driven multi‐agent collaboration.

Image-to-image retrieval, a fundamental task, aims at matching similar images based on a query image. Existing methods with convolutional neural networks are usually sensitive to low-level visual features, and ignore high-level semantic relationship information. This makes retrieving complicated images with multiple objects and various relationships a significant challenge. Although some works introduce the scene graph to capture the global semantic features of the objects and their relations, they ignore the local visual representations. In addition, due to the fragility of individual modal representations, poisoning attacks in adversarial scenarios are easily achieved, hurting the robustness of the visual-guided foundation image retrieval model. To overcome these issues, we propose a novel hierarchical semantic-guided image-to-image retrieval method via scene graph, called Hi-SIGIR. Specifically, to begin with, our proposed method generates the scene graph of an image. Then, our model extracts and learns both the visual and semantic features of the nodes and relations within the scene graphs. Next, these features are fused to obtain local information and sent to the graph neural network to obtain global information. Using these information, the similarity between the scene graphs of several images is calculated at both the local and global levels to perform image retrieval. Finally, we introduce a surrogate that calculates relevance in a cross-modal manner to understand image content better. Experimental evaluations on several wildly-used benchmarks demonstrate the superiority of the proposed method.

Human-object relationship detection reveals the fine-grained relationship between humans and objects, helping the comprehensive understanding of videos. Previous human-object relationship detection approaches are mainly developed with object features and relation features without exploring the specific information of humans. In this paper, we propose a novel Relation-Pose Transformer (RPT) for human-object relationship detection. Inspired by the coordination of eye-head-body movements in cognitive science, we employ the head pose to find those crucial objects that humans focus on and use the body pose with skeleton information to represent multiple actions. Then, we utilize the spatial encoder to capture spatial contextualized information of the relation pair, which integrates the relation features and pose features. Next, the temporal decoder aims to model the temporal dependency of the relationship. Finally, we adopt multiple classifiers to predict different types of relationships. Extensive experiments on the benchmark Action Genome validate the effectiveness of our proposed method and show the state-of-the-art performance compared with related methods.