arXiv subjects

Xu Xie

Publications and source records attributed to Xu Xie.

17 recordsLinked to original sources

arXiv2026

SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild

Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object interaction datasets are predominantly captured in controlled studio settings, which limits both environmental diversity and the ability of models trained on such data to generalize to real-world scenarios. To address this challenge, we introduce a novel marker-less multi-camera system that allows for nearly unconstrained mobility in genuinely in-the-wild conditions, while still having the ability to generate precise 3D annotations of hands and objects. The capture system consists of a lightweight, back-mounted, multi-camera rig that is synchronized and calibrated with a user-worn VR headset. For 3D ground-truth annotation of hands and objects, we develop an ego-exo tracking pipeline and rigorously evaluate its quality. Finally, we present SHOW3D, the first large-scale dataset with 3D annotations that show hands interacting with objects in diverse real-world environments, including outdoor settings. Our approach significantly reduces the fundamental trade-off between environmental realism and accuracy of 3D annotations, which we validate with experiments on several downstream tasks. show3d-dataset.github.io

cs.CV↗

arXiv2025

Ego-Exo 3D Hand Tracking in the Wild with a Mobile Multi-Camera Rig

Accurate 3D tracking of hands and their interactions with the world in unconstrained settings remains a significant challenge for egocentric computer vision. With few exceptions, existing datasets are predominantly captured in controlled lab setups, limiting environmental diversity and model generalization. To address this, we introduce a novel marker-less multi-camera system designed to capture precise 3D hands and objects, which allows for nearly unconstrained mobility in genuinely in-the-wild conditions. We combine a lightweight, back-mounted capture rig with eight exocentric cameras, and a user-worn Meta Quest 3 headset, which contributes two egocentric views. We design an ego-exo tracking pipeline to generate accurate 3D hand pose ground truth from this system, and rigorously evaluate its quality. By collecting an annotated dataset featuring synchronized multi-view images and precise 3D hand poses, we demonstrate the capability of our approach to significantly reduce the trade-off between environmental realism and 3D annotation accuracy.

cs.CV↗

arXiv2025

Non-Invasive Temporal Interference Electrical Stimulation for Spinal Cord Injury Rehabilitation: A Simulation Study

Background: Spinal cord injury (SCI) rehabilitation remains a major clinical challenge, with limited treatment options for functional recovery. Temporal interference (TI) electrical stimulation has emerged as a promising non-invasive neuromodulation technique capable of delivering deep and targeted stimulation. However, the application of TI stimulation in SCI rehabilitation remains largely unexplored. Methods: This study aims to investigate the feasibility of applying non-invasive TI electrical stimulation for SCI rehabilitation. Through computational modeling, we analyzed the electric field distribution characteristics in the spinal cord under different TI stimulation configurations. Based on these findings, we propose a clinically applicable TI stimulation protocol for SCI rehabilitation. Results: The results demonstrate that TI stimulation can effectively deliver focused electric fields to targeted spinal cord segments while maintaining non-invasiveness. The electric field intensity varied depending on individual anatomical differences, highlighting the need for personalized stimulation parameters. The proposed protocol provides a practical framework for applying TI stimulation in SCI rehabilitation and offers a non-invasive alternative to traditional spinal cord stimulation techniques. Conclusions: This study establishes the feasibility of using non-invasive TI stimulation for SCI rehabilitation. The proposed stimulation protocol enables precise and targeted spinal cord modulation. However, further research is needed to refine personalized stimulation parameters and validate the clinical efficacy of this approach.

physics.med-ph↗

arXiv2024

Efficacy of Temporal Interference Electrical Stimulation for Spinal Cord Injury Rehabilitation: A Case Series

Spinal cord injury (SCI) is a debilitating condition that often results in significant motor and sensory deficits, impacting the quality of life. Current rehabilitation methods, including physical therapy and electrical stimulation, offer variable outcomes and often require invasive procedures. Temporal interference (TI) stimulation has emerged as a novel, non-invasive neuromodulation technique capable of targeting deep neural structures with precision, providing a promising alternative for SCI rehabilitation. This study explores the efficacy of TI stimulation as a non-invasive approach for improving motor and sensory function in patients with incomplete SCI. Three male patients with incomplete cervical SCI (AIS D) participated in a two-week intervention consisting of 14 sessions of TI stimulation targeting their injury sites. TI stimulation was delivered using frequencies of 1000 Hz and 1040 Hz, with assessments conducted pre- and post-intervention, including motor and sensory evaluations, functional scales, and imaging studies.All participants demonstrated significant improvements in neurological function, motor strength, sensory perception, and functional independence. Neurological levels of injury shifted upward in all cases, with one patient improving from C5 to C7. Graded Redefined Assessment of Strength, Sensibility and Prehension (GRASSP) results shows additional strength, prehension and sensory outcomes obtained for the arm and hand functions of participants. Motor scores (UEMS and LEMS) increased, sensory scores for light touch and pin prick improved, and functional assessments, such as the Berg Balance Scale (BBS) and Barthel Index (BI), showed marked gains. Pain scores also decreased in two participants, highlighting additional therapeutic benefits.

q-bio.NC↗

arXiv2024

AutoSimTTF: A Fully Automatic Pipeline for Electric Field Simulation and Treatment Planning of Tumor Treating Fields

Objective: Tumor Treating Fields (TTFields) is an emerging approach for cancer therapy that inhibits tumor cell proliferation by applying alternating electric fields (EF) of intermediate frequency and low intensity. The TTFields-induced electric field intensity at the tumor site is closely related to the therapeutic efficacy. Therefore, the EF simulation based on realistic head models have been utilized for the dosage analysis and treatment optimization of TTFields. However, current modeling methods require manual segmentation of tumors and rely on commercial software, which is time-consuming and labor-intensive. Approach: We introduce AutoSimTTF, a fully automatic pipeline for simulating and optimizing the EF distribution for TTFields. The main steps of AutoSimTTF utilize open-source toolkits, enabling fully automated processing of individual MRI data for TTFields. Additionally, AutoSimTTF allows for parameter optimization based on individual anatomical information, thereby achieving a more focused and higher EF distribution at the tumor site. Main results: Compared to conventional EF calculation processes, deviations in AutoSimTTF are below 20%. The optimal treatment parameters generated by AutoSimTTF produces a higher EF intensity at the tumor site (111.9%) and better focality (19.4%) compared to traditional TTFields settings. Significance: AutoSimTTF provides significant reference value and guidance for the clinical application and treatment planning of TTFields.

physics.med-ph↗

arXiv2024

Electrical Impedance Tomography Based Closed-loop Tumor Treating Fields in Dynamic Lung Tumors

Tumor Treating Fields (TTFields) is a non-invasive anticancer modality that utilizes alternating electric fields to disrupt cancer cell division and growth. While generally well-tolerated with minimal side effects, traditional TTFields therapy for lung tumors faces challenges due to the influence of respiratory motion. We design a novel closed-loop TTFields strategy for lung tumors by incorporating electrical impedance tomography (EIT) for real-time respiratory phase monitoring and dynamic parameter adjustments. Furthermore, we conduct theoretical analysis to evaluate the performance of the proposed method using the lung motion model. Compared to conventional TTFields settings, we observed that variations in the electrical conductivity of lung during different respiratory phases led to a decrease in the average electric field intensity within lung tumors, transitioning from end-expiratory (1.08 V/cm) to end-inspiratory (0.87 V/cm) phases. Utilizing our proposed closed-Loop TTFields approach at the same dose setting (2400 mA, consistent with the traditional TTFields setting), we can achieve a higher and consistent average electric field strength at the tumor site (1.30 V/cm) across different respiratory stages. Our proposed closed-loop TTFields method has the potential to improved lung tumor therapy by mitigating the impact of respiratory motion.

physics.med-ph↗

arXiv2023

FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs

Efficient detectors for edge devices are often optimized for parameters or speed count metrics, which remain in weak correlation with the energy of detectors. However, some vision applications of convolutional neural networks, such as always-on surveillance cameras, are critical for energy constraints. This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives: 1) We extensively analyze various CNNs to identify low-energy architectures, including selecting activation functions, convolutions operators, and feature fusion structures on necks. These underappreciated details in past work seriously affect the energy consumption of detectors; 2) To break through the dilemmatic energy-performance problem, we propose a balanced detector driven by energy using discovered low-energy components named \textit{FemtoDet}. In addition to the novel construction, we improve FemtoDet by considering convolutions and training strategy optimizations. Specifically, we develop a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations, and propose a recursive warm-restart (RecWR) for optimizing training strategy to escape the sub-optimization of light-weight detectors by considering the data shift produced in popular augmentations. As a result, FemtoDet with only 68.77k parameters achieves a competitive score of 46.3 AP50 on PASCAL VOC and 1.11 W $\&$ 64.47 FPS on Qualcomm Snapdragon 865 CPU platforms. Extensive experiments on COCO and TJU-DHD datasets indicate that the proposed method achieves competitive results in diverse scenes.

cs.CV↗

arXiv2022

Graph Neural Networks in Recommender Systems: A Survey

With the explosive growth of online information, recommender systems play a key role to alleviate such information overload. Due to the important application value of recommender systems, there have always been emerging works in this field. In recommender systems, the main challenge is to learn the effective user/item representations from their interactions and side information (if any). Recently, graph neural network (GNN) techniques have been widely utilized in recommender systems since most of the information in recommender systems essentially has graph structure and GNN has superiority in graph representation learning. This article aims to provide a comprehensive review of recent research efforts on GNN-based recommender systems. Specifically, we provide a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks. Moreover, we systematically analyze the challenges of applying GNN on different types of data and discuss how existing works in this field address these challenges. Furthermore, we state new perspectives pertaining to the development of this field. We collect the representative papers along with their open-source implementations in https://github.com/wusw14/GNN-in-RS.

cs.IR↗

arXiv2021

CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation

To improve user experience and profits of corporations, modern industrial recommender systems usually aim to select the items that are most likely to be interacted with (e.g., clicks and purchases). However, they overlook the fact that users may purchase the items even without recommendations. To select these effective items, it is essential to estimate the causal effect of recommendations. The real effective items are the ones which can contribute to purchase probability uplift. Nevertheless, it is difficult to obtain the real causal effect since we can only recommend or not recommend an item to a user at one time. Furthermore, previous works usually rely on the randomized controlled trial~(RCT) experiment to evaluate their performance. However, it is usually not practicable in the recommendation scenario due to its unavailable time consuming. To tackle these problems, in this paper, we propose a causal collaborative filtering~(CausCF) method inspired by the widely adopted collaborative filtering~(CF) technique. It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations. CausCF extends the classical matrix factorization to the tensor factorization with three dimensions -- user, item, and treatment. Furthermore, we also employs regression discontinuity design (RDD) to evaluate the precision of the estimated causal effects from different models. With the testable assumptions, RDD analysis can provide an unbiased causal conclusion without RCT experiments. Through dedicated experiments on both the public datasets and the industrial application, we demonstrate the effectiveness of our proposed CausCF on the causal effect estimation and ranking performance improvement.

cs.IR↗

arXiv2021

Trajectory Prediction with Latent Belief Energy-Based Model

Human trajectory prediction is critical for autonomous platforms like self-driving cars or social robots. We present a latent belief energy-based model (LB-EBM) for diverse human trajectory forecast. LB-EBM is a probabilistic model with cost function defined in the latent space to account for the movement history and social context. The low-dimensionality of the latent space and the high expressivity of the EBM make it easy for the model to capture the multimodality of pedestrian trajectory distributions. LB-EBM is learned from expert demonstrations (i.e., human trajectories) projected into the latent space. Sampling from or optimizing the learned LB-EBM yields a belief vector which is used to make a path plan, which then in turn helps to predict a long-range trajectory. The effectiveness of LB-EBM and the two-step approach are supported by strong empirical results. Our model is able to make accurate, multi-modal, and social compliant trajectory predictions and improves over prior state-of-the-arts performance on the Stanford Drone trajectory prediction benchmark by 10.9% and on the ETH-UCY benchmark by 27.6%.

cs.LG↗

arXiv2021

Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such that the reconstructed scenes provide \em{actionable} information for simulating \em{interactions} with agents. Here, we address this challenging problem by reconstructing an interactive scene using RGB-D data stream, which captures (i) the semantics and geometry of objects and layouts by a 3D volumetric panoptic mapping module, and (ii) object affordance and contextual relations by reasoning over physical common sense among objects, organized by a graph-based scene representation. Crucially, this reconstructed scene replaces the object meshes in the dense panoptic map with part-based articulated CAD models for finer-grained robot interactions. In the experiments, we demonstrate that (i) our panoptic mapping module outperforms previous state-of-the-art methods, (ii) a high-performant physical reasoning procedure that matches, aligns, and replaces objects' meshes with best-fitted CAD models, and (iii) reconstructed scenes are physically plausible and naturally afford actionable interactions; without any manual labeling, they are seamlessly imported to ROS-based simulators and virtual environments for complex robot task executions.

cs.RO↗

arXiv2021

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance

Predicting agents' future trajectories plays a crucial role in modern AI systems, yet it is challenging due to intricate interactions exhibited in multi-agent systems, especially when it comes to collision avoidance. To address this challenge, we propose to learn congestion patterns as contextual cues explicitly and devise a novel "Sense--Learn--Reason--Predict" framework by exploiting advantages of three different doctrines of thought, which yields the following desirable benefits: (i) Representing congestion as contextual cues via latent factors subsumes the concept of social force commonly used in physics-based approaches and implicitly encodes the distance as a cost, similar to the way a planning-based method models the environment. (ii) By decomposing the learning phases into two stages, a "student" can learn contextual cues from a "teacher" while generating collision-free trajectories. To make the framework computationally tractable, we formulate it as an optimization problem and derive an upper bound by leveraging the variational parametrization. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset designed for collision avoidance evaluation and remains competitive on the commonly used NGSIM US-101 highway dataset.

cs.RO↗

arXiv2021

Contrastive Learning for Sequential Recommendation

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions. Despite their success, we argue that these approaches usually rely on the sequential prediction task to optimize the huge amounts of parameters. They usually suffer from the data sparsity problem, which makes it difficult for them to learn high-quality user representations. To tackle that, inspired by recent advances of contrastive learning techniques in the computer version, we propose a novel multi-task model called \textbf{C}ontrastive \textbf{L}earning for \textbf{S}equential \textbf{Rec}ommendation~(\textbf{CL4SRec}). CL4SRec not only takes advantage of the traditional next item prediction task but also utilizes the contrastive learning framework to derive self-supervision signals from the original user behavior sequences. Therefore, it can extract more meaningful user patterns and further encode the user representation effectively. In addition, we propose three data augmentation approaches to construct self-supervision signals. Extensive experiments on four public datasets demonstrate that CL4SRec achieves state-of-the-art performance over existing baselines by inferring better user representations.

cs.IR↗

arXiv2021

Explore User Neighborhood for Real-time E-commerce Recommendation

Recommender systems play a vital role in modern online services, such as Amazon and Taobao. Traditional personalized methods, which focus on user-item (UI) relations, have been widely applied in industrial settings, owing to their efficiency and effectiveness. Despite their success, we argue that these approaches ignore local information hidden in similar users. To tackle this problem, user-based methods exploit similar user relations to make recommendations in a local perspective. Nevertheless, traditional user-based methods, like userKNN and matrix factorization, are intractable to be deployed in the real-time applications since such transductive models have to be recomputed or retrained with any new interaction. To overcome this challenge, we propose a framework called self-complementary collaborative filtering~(SCCF) which can make recommendations with both global and local information in real time. On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information. On the other hand, it can identify similar users for each user in real time by inferring user representations on the fly with an inductive model. The proposed framework can be seamlessly incorporated into existing inductive UI approach and benefit from user neighborhood with little additional computation. It is also the first attempt to apply user-based methods in real-time settings. The effectiveness and efficiency of SCCF are demonstrated through extensive offline experiments on four public datasets, as well as a large scale online A/B test in Taobao.

cs.IR↗

arXiv2019

VRGym: A Virtual Testbed for Physical and Interactive AI

We propose VRGym, a virtual reality testbed for realistic human-robot interaction. Different from existing toolkits and virtual reality environments, the VRGym emphasizes on building and training both physical and interactive agents for robotics, machine learning, and cognitive science. VRGym leverages mechanisms that can generate diverse 3D scenes with high realism through physics-based simulation. We demonstrate that VRGym is able to (i) collect human interactions and fine manipulations, (ii) accommodate various robots with a ROS bridge, (iii) support experiments for human-robot interaction, and (iv) provide toolkits for training the state-of-the-art machine learning algorithms. We hope VRGym can help to advance general-purpose robotics and machine learning agents, as well as assisting human studies in the field of cognitive science.

cs.HC↗

arXiv2019

VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning

One of the main challenges of advancing task-oriented learning such as visual task planning and reinforcement learning is the lack of realistic and standardized environments for training and testing AI agents. Previously, researchers often relied on ad-hoc lab environments. There have been recent advances in virtual systems built with 3D physics engines and photo-realistic rendering for indoor and outdoor environments, but the embodied agents in those systems can only conduct simple interactions with the world (e.g., walking around, moving objects, etc.). Most of the existing systems also do not allow human participation in their simulated environments. In this work, we design and implement a virtual reality (VR) system, VRKitchen, with integrated functions which i) enable embodied agents powered by modern AI methods (e.g., planning, reinforcement learning, etc.) to perform complex tasks involving a wide range of fine-grained object manipulations in a realistic environment, and ii) allow human teachers to perform demonstrations to train agents (i.e., learning from demonstration). We also provide standardized evaluation benchmarks and data collection tools to facilitate a broad use in research on task-oriented learning and beyond.

cs.HC↗

arXiv2010

Theoretical and Experimental Studies of Schottky Diodes That Use Aligned Arrays of Single Walled Carbon Nanotubes

We present theoretical and experimental studies of Schottky diodes that use aligned arrays of single walled carbon nanotubes. A simple physical model, taking into account the basic physics of current rectification, can adequately describe the single-tube and array devices. We show that for as grown array diodes, the rectification ratio, defined by the maximum-to-minimum-current-ratio, is low due to the presence of m-SWNT shunts. These tubes can be eliminated in a single voltage sweep resulting in a high rectification array device. Further analysis also shows that the channel resistance, and not the intrinsic nanotube diode properties, limits the rectification in devices with channel length up to ten micrometer.

cond-mat.mes-hall↗