arXiv subjects

Junbo Wang

Publications and source records attributed to Junbo Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments between vision and language. Moreover, classification-based methods rely on predefined answer sets. Treating this task as a simple classification problem may make it unable to adapt to the diversity of free-form answers and overlook the detailed semantic information of free-form answers. In order to tackle these challenges, we introduce a Cross-Mamba Interaction based Multi-Task Learning (CMI-MTL) framework that learns cross-modal feature representations from images and texts. CMI-MTL comprises three key modules: fine-grained visual-text feature alignment (FVTA), cross-modal interleaved feature representation (CIFR), and free-form answer-enhanced multi-task learning (FFAE). FVTA extracts the most relevant regions in image-text pairs through fine-grained visual-text feature alignment. CIFR captures cross-modal sequential interactions via cross-modal interleaved feature representation. FFAE leverages auxiliary knowledge from open-ended questions through free-form answer-enhanced multi-task learning, improving the model's capability for open-ended Med-VQA. Experimental results show that CMI-MTL outperforms the existing state-of-the-art methods on three Med-VQA datasets: VQA-RAD, SLAKE, and OVQA. Furthermore, we conduct more interpretability experiments to prove the effectiveness. The code is publicly available at https://github.com/BioMedIA-repo/CMI-MTL.

cs.CV↗

arXiv2025

MMED: A Multimodal Micro-Expression Dataset based on Audio-Visual Fusion

Micro-expressions (MEs) are crucial leakages of concealed emotion, yet their study has been constrained by a reliance on silent, visual-only data. To solve this issue, we introduce two principal contributions. First, MMED, to our knowledge, is the first dataset capturing the spontaneous vocal cues that co-occur with MEs in ecologically valid, high-stakes interactions. Second, the Asymmetric Multimodal Fusion Network (AMF-Net) is a novel method that effectively fuses a global visual summary with a dynamic audio sequence via an asymmetric cross-attention framework. Rigorous Leave-One-Subject-Out Cross-Validation (LOSO-CV) experiments validate our approach, providing conclusive evidence that audio offers critical, disambiguating information for ME analysis. Collectively, the MMED dataset and our AMF-Net method provide valuable resources and a validated analytical approach for micro-expression recognition.

cs.MM↗

arXiv2025

Foundation Model for Skeleton-Based Human Action Understanding

Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for human modeling, and skeleton-based action understanding has potential applications in humanoid robot control and interaction. \RED{However, existing works often lack the scalability and generalization required to handle diverse action understanding tasks. There is no skeleton foundation model that can be adapted to a wide range of action understanding tasks}. This paper presents a Unified Skeleton-based Dense Representation Learning (USDRL) framework, which serves as a foundational model for skeleton-based human action understanding. USDRL consists of a Transformer-based Dense Spatio-Temporal Encoder (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT). The DSTE module adopts two parallel streams to learn temporal dynamic and spatial structure features. The MG-FD module collaboratively performs feature decorrelation across temporal, spatial, and instance domains to reduce dimensional redundancy and enhance information extraction. The MPCT module employs both multi-view and multi-modal self-supervised consistency training. The former enhances the learning of high-level semantics and mitigates the impact of low-level discrepancies, while the latter effectively facilitates the learning of informative multimodal features. We perform extensive experiments on 25 benchmarks across across 9 skeleton-based action understanding tasks, covering coarse prediction, dense prediction, and transferred prediction. Our approach significantly outperforms the current state-of-the-art methods. We hope that this work would broaden the scope of research in skeleton-based action understanding and encourage more attention to dense prediction tasks.

cs.CV↗

arXiv2025

Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation

Semi-supervised learning (SSL) has attracted considerable attention in medical image processing. The latest SSL methods use a combination of consistency regularization and pseudo-labeling to achieve remarkable success. However, most existing SSL studies focus on segmenting large organs, neglecting the challenging scenarios where there are numerous tumors or tumors of small volume. Furthermore, the extensive capabilities of data augmentation strategies, particularly in the context of both labeled and unlabeled data, have yet to be thoroughly investigated. To tackle these challenges, we introduce a straightforward yet effective approach, termed iterative pseudo-labeling based adaptive copy-paste supervision (IPA-CP), for tumor segmentation in CT scans. IPA-CP incorporates a two-way uncertainty based adaptive augmentation mechanism, aiming to inject tumor uncertainties present in the mean teacher architecture into adaptive augmentation. Additionally, IPA-CP employs an iterative pseudo-label transition strategy to generate more robust and informative pseudo labels for the unlabeled samples. Extensive experiments on both in-house and public datasets show that our framework outperforms state-of-the-art SSL methods in medical image segmentation. Ablation study results demonstrate the effectiveness of our technical contributions.

cs.CV↗

arXiv2025

ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation

In most contact-rich manipulation tasks, humans apply time-varying forces to the target object, compensating for inaccuracies in the vision-guided hand trajectory. However, current robot learning algorithms primarily focus on trajectory-based policy, with limited attention given to learning force-related skills. To address this limitation, we introduce ForceMimic, a force-centric robot learning system, providing a natural, force-aware and robot-free robotic demonstration collection system, along with a hybrid force-motion imitation learning algorithm for robust contact-rich manipulation. Using the proposed ForceCapture system, an operator can peel a zucchini in 5 minutes, while force-feedback teleoperation takes over 13 minutes and struggles with task completion. With the collected data, we propose HybridIL to train a force-centric imitation learning model, equipped with hybrid force-position control primitive to fit the predicted wrench-position parameters during robot execution. Experiments demonstrate that our approach enables the model to learn a more robust policy under the contact-rich task of vegetable peeling, increasing the success rates by 54.5% relatively compared to state-ofthe-art pure-vision-based imitation learning. Hardware, code, data and more results can be found on the project website at https://forcemimic.github.io.

cs.RO↗

arXiv2025

UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models

Previous studies on robotic manipulation are based on a limited understanding of the underlying 3D motion constraints and affordances. To address these challenges, we propose a comprehensive paradigm, termed UniAff, that integrates 3D object-centric manipulation and task understanding in a unified formulation. Specifically, we constructed a dataset labeled with manipulation-related key attributes, comprising 900 articulated objects from 19 categories and 600 tools from 12 categories. Furthermore, we leverage MLLMs to infer object-centric representations for manipulation tasks, including affordance recognition and reasoning about 3D motion constraints. Comprehensive experiments in both simulation and real-world settings indicate that UniAff significantly improves the generalization of robotic manipulation for tools and articulated objects. We hope that UniAff will serve as a general baseline for unified robotic manipulation tasks in the future. Images, videos, dataset, and code are published on the project website at:https://sites.google.com/view/uni-aff/home

cs.RO↗

arXiv2024

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation, called USDRL, which employs feature decorrelation across temporal, spatial, and instance domains in a multi-grained manner to reduce redundancy among dimensions of the representations to maximize information extraction from features. Additionally, we design a Dense Spatio-Temporal Encoder (DSTE) to capture fine-grained action representations effectively, thereby enhancing the performance of dense prediction tasks. Comprehensive experiments, conducted on the benchmarks NTU-60, NTU-120, PKU-MMD I, and PKU-MMD II, across diverse downstream tasks including action recognition, action retrieval, and action detection, conclusively demonstrate that our approach significantly outperforms the current state-of-the-art (SOTA) approaches. Our code and models are available at https://github.com/wengwanjiang/USDRL.

cs.CV↗

arXiv2024

RPMArt: Towards Robust Perception and Manipulation for Articulated Objects

Articulated objects are commonly found in daily life. It is essential that robots can exhibit robust perception and manipulation skills for articulated objects in real-world robotic applications. However, existing methods for articulated objects insufficiently address noise in point clouds and struggle to bridge the gap between simulation and reality, thus limiting the practical deployment in real-world scenarios. To tackle these challenges, we propose a framework towards Robust Perception and Manipulation for Articulated Objects (RPMArt), which learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. Our primary contribution is a Robust Articulation Network (RoArtNet) that is able to predict both joint parameters and affordable points robustly by local feature learning and point tuple voting. Moreover, we introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer. Finally, with the estimated affordable point and articulation joint constraint, the robot can generate robust actions to manipulate articulated objects. After learning only from synthetic data, RPMArt is able to transfer zero-shot to real-world articulated objects. Experimental results confirm our approach's effectiveness, with our framework achieving state-of-the-art performance in both noise-added simulation and real-world environments. Code, data and more results can be found on the project website at https://r-pmart.github.io.

cs.RO↗

arXiv2024

Efficient Model Compression for Hierarchical Federated Learning

Federated learning (FL), as an emerging collaborative learning paradigm, has garnered significant attention due to its capacity to preserve privacy within distributed learning systems. In these systems, clients collaboratively train a unified neural network model using their local datasets and share model parameters rather than raw data, enhancing privacy. Predominantly, FL systems are designed for mobile and edge computing environments where training typically occurs over wireless networks. Consequently, as model sizes increase, the conventional FL frameworks increasingly consume substantial communication resources. To address this challenge and improve communication efficiency, this paper introduces a novel hierarchical FL framework that integrates the benefits of clustered FL and model compression. We present an adaptive clustering algorithm that identifies a core client and dynamically organizes clients into clusters. Furthermore, to enhance transmission efficiency, each core client implements a local aggregation with compression (LC aggregation) algorithm after collecting compressed models from other clients within the same cluster. Simulation results affirm that our proposed algorithms not only maintain comparable predictive accuracy but also significantly reduce energy consumption relative to existing FL mechanisms.

cs.LG↗

arXiv2024

ManiPose: A Comprehensive Benchmark for Pose-aware Object Manipulation in Robotics

Robotic manipulation in everyday scenarios, especially in unstructured environments, requires skills in pose-aware object manipulation (POM), which adapts robots' grasping and handling according to an object's 6D pose. Recognizing an object's position and orientation is crucial for effective manipulation. For example, if a mug is lying on its side, it's more effective to grasp it by the rim rather than the handle. Despite its importance, research in POM skills remains limited, because learning manipulation skills requires pose-varying simulation environments and datasets. This paper introduces ManiPose, a pioneering benchmark designed to advance the study of pose-varying manipulation tasks. ManiPose encompasses: 1) Simulation environments for POM feature tasks ranging from 6D pose-specific pick-and-place of single objects to cluttered scenes, further including interactions with articulated objects. 2) A comprehensive dataset featuring geometrically consistent and manipulation-oriented 6D pose labels for 2936 real-world scanned rigid objects and 100 articulated objects across 59 categories. 3) A baseline for POM, leveraging the inferencing abilities of LLM (e.g., ChatGPT) to analyze the relationship between 6D pose and task-specific requirements, offers enhanced pose-aware grasp prediction and motion planning capabilities. Our benchmark demonstrates notable advancements in pose estimation, pose-aware manipulation, and real-robot skill transfer, setting new standards for POM research. We will open-source the ManiPose benchmark with the final version paper, inviting the community to engage with our resources, available at our website:https://sites.google.com/view/manipose.

cs.RO↗

arXiv2024

GAMMA: Generalizable Articulation Modeling and Manipulation for Articulated Objects

Articulated objects like cabinets and doors are widespread in daily life. However, directly manipulating 3D articulated objects is challenging because they have diverse geometrical shapes, semantic categories, and kinetic constraints. Prior works mostly focused on recognizing and manipulating articulated objects with specific joint types. They can either estimate the joint parameters or distinguish suitable grasp poses to facilitate trajectory planning. Although these approaches have succeeded in certain types of articulated objects, they lack generalizability to unseen objects, which significantly impedes their application in broader scenarios. In this paper, we propose a novel framework of Generalizable Articulation Modeling and Manipulating for Articulated Objects (GAMMA), which learns both articulation modeling and grasp pose affordance from diverse articulated objects with different categories. In addition, GAMMA adopts adaptive manipulation to iteratively reduce the modeling errors and enhance manipulation performance. We train GAMMA with the PartNet-Mobility dataset and evaluate with comprehensive experiments in SAPIEN simulation and real-world Franka robot. Results show that GAMMA significantly outperforms SOTA articulation modeling and manipulation algorithms in unseen and cross-category articulated objects. We will open-source all codes and datasets in both simulation and real robots for reproduction in the final version. Images and videos are published on the project website at: http://sites.google.com/view/gamma-articulation

cs.RO↗

arXiv2023

Spatial-Temporal Hypergraph Neural Network for Traffic Forecasting

Traffic forecasting, which benefits from mobile Internet development and position technologies, plays a critical role in Intelligent Transportation Systems. It helps to implement rich and varied transportation applications and bring convenient transportation services to people based on collected traffic data. Most existing methods usually leverage graph-based deep learning networks to model the complex road network for traffic forecasting shallowly. Despite their effectiveness, these methods are generally limited in fully capturing high-order spatial dependencies caused by road network topology and high-order temporal dependencies caused by traffic dynamics. To tackle the above issues, we focus on the essence of traffic system and propose STHODE: Spatio-Temporal Hypergraph Neural Ordinary Differential Equation Network, which combines road network topology and traffic dynamics to capture high-order spatio-temporal dependencies in traffic data. Technically, STHODE consists of a spatial module and a temporal module. On the one hand, we construct a spatial hypergraph and leverage an adaptive MixHop hypergraph ODE network to capture high-order spatial dependencies. On the other hand, we utilize a temporal hypergraph and employ a hyperedge evolving ODE network to capture high-order temporal dependencies. Finally, we aggregate the outputs of stacked STHODE layers to mutually enhance the prediction performance. Extensive experiments conducted on four real-world traffic datasets demonstrate the superior performance of our proposed model compared to various baselines.

cs.LG↗

arXiv2023

RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot

A key challenge in robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent research in one-shot imitation learning has shown promise in transferring trained policies to new tasks based on demonstrations. This feature is attractive for enabling robots to acquire new skills and improving task and motion planning. However, due to limitations in the training dataset, the current focus of the community has mainly been on simple cases, such as push or pick-place tasks, relying solely on visual guidance. In reality, there are many complex skills, some of which may even require both visual and tactile perception to solve. This paper aims to unlock the potential for an agent to generalize to hundreds of real-world skills with multi-modal perception. To achieve this, we have collected a dataset comprising over 110,000 contact-rich robot manipulation sequences across diverse skills, contexts, robots, and camera viewpoints, all collected in the real world. Each sequence in the dataset includes visual, force, audio, and action information. Moreover, we also provide a corresponding human demonstration video and a language description for each robot sequence. We have invested significant efforts in calibrating all the sensors and ensuring a high-quality dataset. The dataset is made publicly available at rh20t.github.io

cs.RO↗

arXiv2021

The impact of data volume on performance of deep learning based building rooftop extraction using very high spatial resolution aerial images

Building rooftop data are of importance in several urban applications and in natural disaster management. In contrast to traditional surveying and mapping, by using high spatial resolution aerial images, deep learning-based building rooftops extraction methods are efficient and accurate. Although more training data is preferred in deep learning-based tasks, the effect of data volume on building extraction models is underexplored. Therefore, the paper explores the impact of data volume on the performance of building rooftop extraction from very-high-spatial-resolution (VHSR) images using deep learning-based methods. To do so, we manually labelled 0.12m spatial resolution aerial images and perform a comparative analysis of models trained on datasets of different sizes using popular deep learning architectures for segmentation tasks, including Fully Convolutional Networks (FCN)-8s, U-Net and DeepLabv3+. The experiments showed that with more training data, algorithms converged faster and achieved higher accuracy, while better algorithms were able to better mitigate the lack of training data.

cs.CV↗

arXiv2019

Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search

Text-based person search aims to retrieve the corresponding person images in an image database by virtue of a describing sentence about the person, which poses great potential for various applications such as video surveillance. Extracting visual contents corresponding to the human description is the key to this cross-modal matching problem. Moreover, correlated images and descriptions involve different granularities of semantic relevance, which is usually ignored in previous methods. To exploit the multilevel corresponding visual contents, we propose a pose-guided multi-granularity attention network (PMA). Firstly, we propose a coarse alignment network (CA) to select the related image regions to the global description by a similarity-based attention. To further capture the phrase-related visual body part, a fine-grained alignment network (FA) is proposed, which employs pose information to learn latent semantic alignment between visual body part and textual noun phrase. To verify the effectiveness of our model, we perform extensive experiments on the CUHK Person Description Dataset (CUHK-PEDES) which is currently the only available dataset for text-based person search. Experimental results show that our approach outperforms the state-of-the-art methods by 15 \% in terms of the top-1 metric.

cs.CV↗

arXiv2019

Eshelby tensors and overall properties of nano-composites considering both interface stretching and bending effects

In this study, the fundamental framework of analytical micromechanics is generalized to consider nano-composites with both interface stretching and bending effects. The interior and exterior Eshelby tensors for a spherical nano-inclusion, with an interface defined by the Steigmann-Ogden model, subjected to an arbitrary uniform eigenstrain are derived for the first time. Correspondingly, the stress/strain concentration tensors for a spherical nano-inhomogeneity subjected to arbitrary uniform far-field stress/strain loadings are also derived. Using the obtained concentration tensors, the effective bulk and shear moduli are derived by employing the dilute approximation and the Mori-Tanaka method, respectively, which can be used for both nano-composites and nano-porous materials. An equivalent interface curvature parameter reflecting the influence of the interface bending resistance is found, which can significantly simplify the complex expressions of the effective properties. In addition to size-dependency, the closed form expressions show that the effective bulk modulus is invariant to interface bending resistance parameters, in contrast to the effective shear modulus. We also put forward for the first time a characteristic interface curvature parameter, near which the effective shear modulus is affected significantly. Numerical results show that the effective shear moduli of nano-composites and nano-porous materials can be greatly improved by an appropriate surface modification. Finally, the derived effective modulus with the Steigmann-Ogden interface model is provided in the supplemental MATLAB code, which can be easily executed, and used as a benchmark for semi-analytical solutions and numerical solutions in future studies.

physics.comp-ph↗

arXiv2019

Spherical nano-inhomogeneity with the Steigmann-Ogden interface model under general uniform far-field stress loading

An explicit solution, considering the interface bending resistance as described by the Steigmann-Ogden interface model, is derived for the problem of a spherical nano-inhomogeneity (nanoscale void/inclusion) embedded in an infinite linear-elastic matrix under a general uniform far-field-stress (including tensile and shear stresses). The Papkovich-Neuber (P-N) general solutions, which are expressed in terms of spherical harmonics, are used to derive the analytical solution. A superposition technique is used to overcome the mathematical complexity brought on by the assumed interfacial residual stress in the Steigmann-Ogden interface model. Numerical examples show that the stress field, considering the interface bending resistance as with the Steigmann-Ogden interface model, differs significantly from that considering only the interface stretching resistance as with the Gurtin-Murdoch interface model. In addition to the size-dependency, another interesting phenomenon is observed: some stress components are invariant to interface bending stiffness parameters along a certain circle in the inclusion/matrix. Moreover, a characteristic line for the interface bending stiffness parameters is presented, near which the stress concentration becomes quite severe. Finally, the derived analytical solution with the Steigmann-Ogden interface model is provided in the supplemental MATLAB code, which can be easily executed, and used as a benchmark for semi-analytical solutions and numerical solutions in future studies.

physics.class-ph↗

arXiv2016

Multimodal Memory Modelling for Video Captioning

Video captioning which automatically translates video clips into natural language sentences is a very important task in computer vision. By virtue of recent deep learning technologies, e.g., convolutional neural networks (CNNs) and recurrent neural networks (RNNs), video captioning has made great progress. However, learning an effective mapping from visual sequence space to language space is still a challenging problem. In this paper, we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide global visual attention on described targets. Specifically, the proposed M3 attaches an external memory to store and retrieve both visual and textual contents by interacting with video and sentence with multiple read and write operations. First, text representation in the Long Short-Term Memory (LSTM) based text decoder is written into the memory, and the memory contents will be read out to guide an attention to select related visual targets. Then, the selected visual information is written into the memory, which will be further read out to the text decoder. To evaluate the proposed model, we perform experiments on two publicly benchmark datasets: MSVD and MSR-VTT. The experimental results demonstrate that our method outperforms the state-of-theart methods in terms of BLEU and METEOR.

cs.CV↗