Mingxin Zhang

Mingxin Zhang, Zipei Fan, Ryosuke Shibasaki et al.

In recent years, the use of WiFi fingerprints for indoor positioning has grown in popularity, largely due to the widespread availability of WiFi and the proliferation of mobile communication devices. However, many existing methods for constructing fingerprint datasets rely on labor-intensive and time-consuming processes of collecting large amounts of data. Additionally, these methods often focus on ideal laboratory environments, rather than considering the practical challenges of large multi-floor buildings. To address these issues, we present a novel WiDAGCN model that can be trained using a small number of labeled site survey data and large amounts of unlabeled crowdsensed WiFi fingerprints. By constructing heterogeneous graphs based on received signal strength indicators (RSSIs) between waypoints and WiFi access points (APs), our model is able to effectively capture the topological structure of the data. We also incorporate graph convolutional networks (GCNs) to extract graph-level embeddings, a feature that has been largely overlooked in previous WiFi indoor localization studies. To deal with the challenges of large amounts of unlabeled data and multiple data domains, we employ a semi-supervised domain adversarial training scheme to effectively utilize unlabeled data and align the data distributions across domains. Our system is evaluated using a public indoor localization dataset that includes multiple buildings, and the results show that it performs competitively in terms of localization accuracy in large buildings.

Yuchen Yang, Wei Wang, Yifei Liu et al.

Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the evaluation of state-of-the-art algorithms. To address these limitations, we introduce SGA-INTERACT, the first 3D skeleton-based benchmark for group activity understanding. It features complex activities inspired by basketball tactics, emphasizing rich spatial interactions and long-term dependencies. SGA-INTERACT introduces Temporal Group Activity Localization (TGAL) task, extending group activity understanding to untrimmed sequences, filling the gap left by GAR as a standalone task. In addition to the benchmark, we propose One2Many, a novel framework that employs a pretrained 3D skeleton backbone for unified individual feature extraction. This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks. We conduct extensive evaluations on SGA-INTERACT using two skeleton-based methods, three RGB-based methods, and a proposed baseline within the One2Many framework. The general low performance of baselines highlights the benchmark's challenges, motivating advancements in group activity understanding.

Mingxin Zhang, Xiaofeng Dai, Yu Yao et al.

In this study, we present a conditional diffusion-transformer framework for generating ensembles of three-dimensional Escherichia coli genome conformations guided by Hi-C contact maps. Instead of producing a single deterministic structure, we formulate genome reconstruction as a conditional generative modeling problem that samples heterogeneous conformations whose ensemble-averaged contacts are consistent with the input Hi-C data. A synthetic dataset is constructed using coarse-grained molecular dynamics simulations to generate chromatin ensembles and corresponding Hi-C maps under circular topology. Our models operate in a latent diffusion setting with a variational autoencoder that preserves per-bin alignment and supports replication-aware representations. Hi-C information is injected through a transformer-based encoder and cross-attention, enforcing a physically interpretable one-way constraint from Hi-C to structure. The model is trained using a flow-matching objective for stable optimization. On held-out ensembles, generated structures reproduce the input Hi-C distance-decay and structural correlation metrics while maintaining substantial conformational diversity, demonstrating the effectiveness of diffusion-based generative modeling for ensemble-level 3D genome reconstruction.

Qian Zhang, Lin Zhang, Xing Fang et al.

Visual affordance learning is crucial for robots to understand and interact effectively with the physical world. Recent advances in this field attempt to leverage pre-trained knowledge of vision-language foundation models to learn affordance properties with limited training data, providing a novel paradigm for visual affordance learning. However, these methods overlook the significance of maintaining feature alignment between visual images and language descriptions for identifying affordance areas with textual guidance, and thus may lead to suboptimal results. In this paper, we present an informative framework for text-guided affordance learning, which involves information-based constraints to achieve text-image alignment at feature level. Specifically, we design an affordance mutual information constraint that helps learn appropriate textual prompts and task-oriented visual features simultaneously by maximizing the mutual information between the features of the affordance areas in the input images and the corresponding textual prompts. In addition, we propose an object-level information constraint that maximizes the mutual information between the visual features of a given object and the text features of the category it belongs to. This enables the model to capture high-quality representations for the object, providing more reliable semantic priors for identifying affordance regions. Experimental results on the AGD20K dataset show that the proposed method outperforms existing approaches and achieves the new state-of-the-art in one-shot affordance learning.