Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static graphs and rely on parameter averaging or distribution alignment, which implicitly assume that all features are equally transferable across clients, overlooking both the spatial and temporal heterogeneity and the presence of client-specific knowledge in real-world graphs. In this work, we identify that such assumptions create a vicious cycle of spurious representation entanglement, client-specific interference, and negative transfer, degrading generalization performance in Federated Learning over Dynamic Spatio-Temporal Graphs (FSTG). To address this issue, we propose a novel causality-inspired framework named SC-FSGL, which explicitly decouples transferable causal knowledge from client-specific noise through representation-level interventions. Specifically, we introduce a Conditional Separation Module that simulates soft interventions through client conditioned masks, enabling the disentanglement of invariant spatio-temporal causal factors from spurious signals and mitigating representation entanglement caused by client heterogeneity. In addition, we propose a Causal Codebook that clusters causal prototypes and aligns local representations via contrastive learning, promoting cross-client consistency and facilitating knowledge sharing across diverse spatio-temporal patterns. Experiments on five diverse heterogeneity Spatio-Temporal Graph (STG) datasets show that SC-FSGL outperforms state-of-the-art methods.

Due to visual ambiguities and inter-person occlusions, existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos. Even state-of-the-art large foundation models (e.g., SAM) cannot accurately distinguish human semantics in such challenging scenarios. In this work, we find that human appearance can provide a straightforward cue to address these obstacles. Based on this observation, we propose a dual-branch optimization framework to reconstruct accurate interactive motions with plausible body contacts constrained by human appearances, social proxemics, and physical laws. Specifically, we first train a diffusion model to learn the human proxemic behavior and pose prior knowledge. The trained network and two optimizable tensors are then incorporated into a dual-branch optimization framework to reconstruct human motions and appearances. Several constraints based on 3D Gaussians, 2D keypoints, and mesh penetrations are also designed to assist the optimization. With the proxemics prior and diverse constraints, our method is capable of estimating accurate interactions from in-the-wild videos captured in complex environments. We further build a dataset with pseudo ground-truth interaction annotations, which may promote future research on pose estimation and human behavior understanding. Experimental results on several benchmarks demonstrate that our method outperforms existing approaches. The code and data are available at https://www.buzhenhuang.com/works/CloseApp.html.

Group activity recognition in weakly supervised settings can be approached through either detector-based or detector-free methods. Detector-based methods typically rely on predefined graph structures to capture group relationships, which limits their ability to model the dynamic, multi-scale, and fine-grained changes in group interactions. In contrast, detector-free methods face challenges in effectively filtering irrelevant background and spectator information. In this paper, we propose a novel multi-scale hypergraph neural network framework, MHGAR, for weakly supervised group activity recognition. Unlike traditional methods with fixed graph structures, MHGAR dynamically constructs hyperedges to capture complex team formations and sub-group interactions at multiple scales. We initialize player representations by combining visual appearance and spatial positions, and iteratively refine these representations through dynamic hyperedge construction and bi-directional message passing. A cross-attentive activity classifier integrates the refined multi-scale features with ball position information to predict group activities. Our method effectively captures both fine-grained sub-group interactions and high-level team formations through its adaptive multi-scale modeling. Experimental results demonstrate state-of-the-art performance on the widely used Volleyball and NBA datasets.

Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration, but overlook the modeling of close interactions. In this work, we tackle the task of reconstructing closely interactive humans from a monocular video. The main challenge of this task comes from insufficient visual information caused by depth ambiguity and severe inter-person occlusion. In view of this, we propose to leverage knowledge from proxemic behavior and physics to compensate the lack of visual information. This is based on the observation that human interaction has specific patterns following the social proxemics. Specifically, we first design a latent representation based on Vector Quantised-Variational AutoEncoder (VQ-VAE) to model human interaction. A proxemics and physics guided diffusion model is then introduced to denoise the initial distribution. We design the diffusion model as dual branch with each branch representing one individual such that the interaction can be modeled via cross attention. With the learned priors of VQ-VAE and physical constraint as the additional information, our proposed approach is capable of estimating accurate poses that are also proxemics and physics plausible. Experimental results on Hi4D, 3DPW, and CHI3D demonstrate that our method outperforms existing approaches. The code is available at https://github.com/boycehbz/HumanInteraction.

The Data Over Cable Service Interface Specification (DOCSIS) is established as the primary cable network data communication standard inNorth America and is the first specification having reached international standard level. It is therefore appropriate to determine its performance. Previous works on performance analysis of the DOCSIS Community Antenna Television network have been carried out using computer simulations. In this paper, we propose a model for mini-slot allocation with two priority classes of traffic which supports a real-time Constant Bit Rate (CBR) service and a non-real-time data service. Real-time CBR traffic has pre-emptive high-over-line priority over non-real-time data traffic. The service discipline is First Come First Served. Two critical characteristics, average delay and throughput, are analysed. Finally, numerical results are presented. The results demonstrate that the delay requirement of real-time CBR traffic can be easily met at the expense of the delay of non-real-time data traffic.