Juan Chen

Yuxin Wen, Qing Shuai, Di Kang et al.

We present HY-Motion 1.0, a series of state-of-the-art, large-scale, motion generation models capable of generating 3D human motions from textual descriptions. HY-Motion 1.0 represents the first successful attempt to scale up Diffusion Transformer (DiT)-based flow matching models to the billion-parameter scale within the motion generation domain, delivering instruction-following capabilities that significantly outperform current open-source benchmarks. Uniquely, we introduce a comprehensive, full-stage training paradigm -- including large-scale pretraining on over 3,000 hours of motion data, high-quality fine-tuning on 400 hours of curated data, and reinforcement learning from both human feedback and reward models -- to ensure precise alignment with the text instruction and high motion quality. This framework is supported by our meticulous data processing pipeline, which performs rigorous motion cleaning and captioning. Consequently, our model achieves the most extensive coverage, spanning over 200 motion categories across 6 major classes. We release HY-Motion 1.0 to the open-source community to foster future research and accelerate the transition of 3D human motion generation models towards commercial maturity.

Xingyu Liu, Juan Chen, Quan Wen

Traditional convolutional neural networks are limited to handling Euclidean space data, overlooking the vast realm of real-life scenarios represented as graph data, including transportation networks, social networks, and reference networks. The pivotal step in transferring convolutional neural networks to graph data analysis and processing lies in the construction of graph convolutional operators and graph pooling operators. This comprehensive review article delves into the world of graph convolutional neural networks. Firstly, it elaborates on the fundamentals of graph convolutional neural networks. Subsequently, it elucidates the graph neural network models based on attention mechanisms and autoencoders, summarizing their application in node classification, graph classification, and link prediction along with the associated datasets.

Bolong Zhang, Juan Chen, Quan Wen

Image super-resolution reconstruction is an important task in the field of image processing technology, which can restore low resolution image to high quality image with high resolution. In recent years, deep learning has been applied in the field of image super-resolution reconstruction. With the continuous development of deep neural network, the quality of the reconstructed images has been greatly improved, but the model complexity has also been increased. In this paper, we propose two lightweight models named as MSwinSR and UGSwinSR based on Swin Transformer. The most important structure in MSwinSR is called Multi-size Swin Transformer Block (MSTB), which mainly contains four parallel multi-head self-attention (MSA) blocks. UGSwinSR combines U-Net and GAN with Swin Transformer. Both of them can reduce the model complexity, but MSwinSR can reach a higher objective quality, while UGSwinSR can reach a higher perceptual quality. The experimental results demonstrate that MSwinSR increases PSNR by $\mathbf{0.07dB}$ compared with the state-of-the-art model SwinIR, while the number of parameters can reduced by $\mathbf{30.68\%}$, and the calculation cost can reduced by $\mathbf{9.936\%}$. UGSwinSR can effectively reduce the amount of calculation of the network, which can reduced by $\mathbf{90.92\%}$ compared with SwinIR.

Kaiyuan Zhai, Juan Chen, Chao Wang et al.

Accurate and reliable pedestrian trajectory prediction is critical for the application of intelligent applications, yet achieving trustworthy prediction remains highly challenging due to the complexity of interactions among pedestrians. Previous methods often adopt black-box modeling of pedestrian interactions. Despite their strong performance, such opaque modeling limits the reliability of predictions in real-world deployments. To address this issue, we propose InSyn (Interaction-Synchronization Network), a novel Transformer-based model that explicitly captures diverse interaction patterns (e.g., walking in sync or conflicting) while effectively modeling direction-sensitive social behaviors. Additionally, we introduce a training strategy, termed Seq-Start of Seq (SSOS), designed to alleviate the common issue of initial-step divergence in numerical time-series prediction. Experiments on the ETH and UCY datasets demonstrate that our model not only outperforms recent black-box baselines in prediction accuracy, especially under high-density scenarios, but also provides transparent interaction modeling, as shown in the case study. Furthermore, the SSOS strategy proves to be effective in improving sequential prediction performance, reducing the initial-step prediction error by approximately 6.58%. Code is avaliable at https://github.com/rickzky1001/InSyn

Dongwei Gan, Ming Chang, Juan Chen

Medical image segmentation (MIS) aims to finely segment various organs. It requires grasping global information from both parts and the entire image for better segmenting, and clinically there are often certain requirements for segmentation efficiency. Convolutional neural networks (CNNs) have made considerable achievements in MIS. However, they are difficult to fully collect global context information and their pooling layer may cause information loss. Capsule networks, which combine the benefits of CNNs while taking into account additional information such as relative location that CNNs do not, have lately demonstrated some advantages in MIS. Vision Transformer (ViT) employs transformers in visual tasks. Transformer based on attention mechanism has excellent global inductive modeling capabilities and is expected to capture longrange information. Moreover, there have been resent studies on making ViT more lightweight to minimize model complexity and increase efficiency. In this paper, we propose a U-shaped 3D encoder-decoder network named 3D-EffiViTCaps, which combines 3D capsule blocks with 3D EfficientViT blocks for MIS. Our encoder uses capsule blocks and EfficientViT blocks to jointly capture local and global semantic information more effectively and efficiently with less information loss, while the decoder employs CNN blocks and EfficientViT blocks to catch ffner details for segmentation. We conduct experiments on various datasets, including iSeg-2017, Hippocampus and Cardiac to verify the performance and efficiency of 3D-EffiViTCaps, which performs better than previous 3D CNN-based, 3D Capsule-based and 3D Transformer-based models. We further implement a series of ablation experiments on the main blocks. Our code is available at: https://github.com/HidNeuron/3D-EffiViTCaps.

Yakun Chen, Kaize Shi, Zhangkai Wu et al.

Spatiotemporal data analysis is pivotal across various domains, such as transportation, meteorology, and healthcare. The data collected in real-world scenarios are often incomplete due to device malfunctions and network errors. Spatiotemporal imputation aims to predict missing values by exploiting the spatial and temporal dependencies in the observed data. Traditional imputation approaches based on statistical and machine learning techniques require the data to conform to their distributional assumptions, while graph and recurrent neural networks are prone to error accumulation problems due to their recurrent structures. Generative models, especially diffusion models, can potentially circumvent the reliance on inaccurate, previously imputed values for future predictions; However, diffusion models still face challenges in generating stable results. We propose to address these challenges by designing conditional information to guide the generative process and expedite the training process. We introduce a conditional diffusion framework called C$^2$TSD, which incorporates disentangled temporal (trend and seasonality) representations as conditional information and employs contrastive learning to improve generalizability. Our extensive experiments on three real-world datasets demonstrate the superior performance of our approach compared to a number of state-of-the-art baselines.

Wei Zhang, Juan Chen, Yanbo J. Wang et al.

Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete data. Traditional methods that attempt to reconstruct missing information often suffer from over-coupling and imprecise generation processes, leading to suboptimal outcomes. To address these issues, we introduce an Attention-based Diffusion model for Missing Modalities feature Completion (ADMC). Our framework independently trains feature extraction networks for each modality, preserving their unique characteristics and avoiding over-coupling. The Attention-based Diffusion Network (ADN) generates missing modality features that closely align with authentic multimodal distribution, enhancing performance across all missing-modality scenarios. Moreover, ADN's cross-modal generation offers improved recognition even in full-modality contexts. Our approach achieves state-of-the-art results on the IEMOCAP and MIntRec benchmarks, demonstrating its effectiveness in both missing and complete modality scenarios.

Wei Zhang, Juan Chen, En Zhu et al.

Automated depression diagnosis aims to analyze multimodal information from interview videos to predict participants' depression scores. Previous studies often lack clear explanations of how these scores were determined, limiting their adoption in clinical practice. While the advent of LLMs provides a possible pathway for explainable depression diagnosis, current LLMs capable of processing multimodal data lack training on interview data, resulting in poor diagnostic performance when used directly. In this paper, we propose a novel multimodal large language model (MLlm-DR) that can understand multimodal information inputs and supports explainable depression diagnosis. MLlm-DR integrates a smaller LLMs and a lightweight query module (LQ-former). Specifically, the smaller LLMs is designed to generate depression scores and corresponding evaluation rationales. To enhance its logical reasoning for domain-specific tasks while maintaining practicality, we constructed a robust training dataset to fine-tune it. Meanwhile, the LQ-former captures depression-related features from speech and visual data, aiding the model's ability to process multimodal information, to achieve comprehensive depression diagnosis. Our approach achieves state-of-the-art results on two interview-based benchmark datasets, CMDC and E-DAIC-WOZ, demonstrating its effectiveness and superiority.

Juan Chen, Baolong Bi, Wei Zhang et al.

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating their parametric knowledge with external retrieved content. However, knowledge conflicts caused by internal inconsistencies or noisy retrieved content can severely undermine the generation reliability of RAG systems.In this work, we argue that LLMs should rethink all evidence, including both retrieved content and internal knowledge, before generating responses.We propose CARE-RAG (Conflict-Aware and Reliable Evidence for RAG), a novel framework that improves trustworthiness through Conflict-Driven Summarization of all available evidence.CARE-RAG first derives parameter-aware evidence by comparing parameter records to identify diverse internal perspectives. It then refines retrieved evidences to produce context-aware evidence, removing irrelevant or misleading content. To detect and summarize conflicts, we distill a 3B LLaMA3.2 model to perform conflict-driven summarization, enabling reliable synthesis across multiple sources.To further ensure evaluation integrity, we introduce a QA Repair step to correct outdated or ambiguous benchmark answers.Experiments on revised QA datasets with retrieval data show that CARE-RAG consistently outperforms strong RAG baselines, especially in scenarios with noisy or conflicting evidence.

Zhiwen Xiao, Xin Xu, Huanlai Xing et al.

Time series analysis plays a vital role in various applications, for instance, healthcare, weather prediction, disaster forecast, etc. However, to obtain sufficient shapelets by a feature network is still challenging. To this end, we propose a novel robust temporal feature network (RTFN) that contains temporal feature networks and attentional LSTM networks. The temporal feature networks are built to extract basic features from input data while the attentional LSTM networks are devised to capture complicated shapelets and relationships to enrich features. In experiments, we embed RTFN into supervised structure as a feature extraction network and into unsupervised clustering as an encoder, respectively. The results show that the RTFN-based supervised structure is a winner of 40 out of 85 datasets and the RTFN-based unsupervised clustering performs the best on 4 out of 11 datasets in the UCR2018 archive.

Juan Chen, Zhiwen Xiao, Huanlai Xing et al.

Dynamic routing in software-defined networking (SDN) can be viewed as a centralized decision-making problem. Most of the existing deep reinforcement learning (DRL) agents can address it, thanks to the deep neural network (DNN)incorporated. However, fully-connected feed-forward neural network (FFNN) is usually adopted, where spatial correlation and temporal variation of traffic flows are ignored. This drawback usually leads to significantly high computational complexity due to large number of training parameters. To overcome this problem, we propose a novel model-free framework for dynamic routing in SDN, which is referred to as spatio-temporal deterministic policy gradient (STDPG) agent. Both the actor and critic networks are based on identical DNN structure, where a combination of convolutional neural network (CNN) and long short-term memory network (LSTM) with temporal attention mechanism, CNN-LSTM-TAM, is devised. By efficiently exploiting spatial and temporal features, CNNLSTM-TAM helps the STDPG agent learn better from the experience transitions. Furthermore, we employ the prioritized experience replay (PER) method to accelerate the convergence of model training. The experimental results show that STDPG can automatically adapt for current network environment and achieve robust convergence. Compared with a number state-ofthe-art DRL agents, STDPG achieves better routing solutions in terms of the average end-to-end delay.