91 accepted papers
Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies. Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs, which can be problematic…
With the accelerated popularization of electric vehicles (EV), battery safety issues have become an important research focus. Data-driven battery fault diagnosis algorithms, built on real-world operational data, are critical methods for reducing safety risks. However, existing battery datasets have…
Existing reasoning segmentation approaches typically fine-tune multimodal large language models (MLLMs) using image-text pairs and corresponding mask labels. While recent efforts leverage reinforcement fine-tuning to further enhance reasoning ability, they often suffer from overthinking and produce …
Remote sensing change detection (CD) has achieved remarkable progress in recent years. However, little attention has been paid to generalizable change detection (GCD) methods that can effectively generalize to unseen scenarios or domains beyond the training distribution. The major challenges in GCD
Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information, leading to poor background preservation, spatial inconsistencies,
In the realm of autonomous driving, accurately detecting surrounding obstacles is crucial for effective decision-making. Traditional methods primarily rely on 3D bounding boxes to represent these obstacles, which often fail to capture the complexity of irregularly shaped, real-world objects. To over
Cold-start item recommendation is a significant challenge in recommendation systems, particularly when new items are introduced without any historical interaction data. While existing methods leverage multi-modal content to alleviate the cold-start issue, they often neglect the inherent multi-view s
White-Light Imaging (WLI) is the standard for endoscopic cancer screening, but Narrow-Band Imaging (NBI) offers superior diagnostic details. A key challenge is transferring knowledge from NBI to enhance WLI-only models, yet existing methods are critically hampered by their reliance on paired NBI-WLI
Locating vertebral landmarks on anteroposterior (AP) X-ray images is challenging due to the tissue overlap. Despite the great progress of heatmap-based methods, they often predict missing/false points, which are intolerable in the downstream applications like scoliosis assessment. In this paper, we
Mix-supervised image segmentation aims to effectively leverage heterogeneous annotations. Recent prompt-based advances utilize foundation models such as Segment Anything Model (SAM) to generate pseudo-masks by treating weak labels as spatial prompts. However, these methods rely heavily on sparse spa
Planning smooth trajectories through a sequence of waypoints under nonconvex constraints is challenging due to the coupling between coefficient optimization and time allocation. Existing gradient-based spline trajectory optimization methods tend to be susceptible to local minima and poor initializat
Current referring video segmentation methods typically operate in an offline manner, where sparse frames are first selected for image-level referring segmentation, and the resulting masks are then propagated across the video. Although video sampling captures global context, its isolated processing s
Recently, many self-supervised pre-training methods have been proposed to improve the performance of deep neural networks (DNNs) for 3D point clouds processing. However, the common mechanism underlying the effectiveness of different pre-training methods remains unclear. In this paper, we use game-th…
This paper introduces a systematic approach to identifying a physically feasible set of robot dynamics parameters. The framework consists of four steps: 1) Identification of robot dynamics parameters using least squares combined with a linear friction model. 2) Construction of a weighting matrix bas
Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assess…
This paper studies the convergence of clipped stochastic gradient descent (SGD) algorithms with decision-dependent data distribution. Our setting is motivated by privacy preserving optimization algorithms that interact with performative data where the prediction models can influence future outcomes.…
Anticipating and recognizing surgical workflows are critical for intelligent surgical assistance systems. However, existing methods rely on deterministic decision-making, struggling to generalize across the large anatomical and procedural variations inherent in real-world surgeries. In this paper, w…
Low-Rank Adaptation (LoRA) methods have demonstrated considerable success in achieving parameter-efficient fine-tuning (PEFT) for Transformer-based foundation models. These methods typically fine-tune individual Transformer layers using independent LoRA adaptations. However, directly applying existi…
Surgical phase recognition has become a crucial requirement in laparoscopic surgery, enabling various clinical applications like surgical risk forecasting. Current methods typically identify the surgical phase using individual frame-wise embeddings as the fundamental unit for time modeling. However,…
Underwater object detection (UOD) is crucial for monitoring marine ecosystems, underwater robotics, environmental protection, and autonomous underwater vehicles (AUVs). Despite progress, many models struggle under real-world conditions due to poor visibility, dynamic lighting, and domain shifts. Tra
Applying pretraining-finetuning paradigm to event cameras presents significant challenges due to the scarcity of large-scale event datasets and the inherently sparse nature of event data, which increases the risk of overfitting during extensive pretraining.In this paper, we explore the transfer of p…
Small targets in infrared imagery exhibit challenging characteristics due to their minimal semantic information and the extremely imbalanced distribution between the targets and the background. In this paper, we propose a frequency band integration network to extract salient features of infrared sma…
Latent Diffusion-based Text-to-Image (T2I) is a free image editing tool that typically reverses an image into noise, reconstructs it using its original text prompt, and then generates an edited version under a new target prompt. To preserve unaltered image content, features from the reconstruction a…
Automatic video polyp segmentation plays a critical role in gastrointestinal cancer screening, but the cost of frame-by-frame annotations is prohibitively high. While sparse-frame supervised methods have reduced this burden proportionately, the cost remains overwhelming for long-duration videos and…
Document image rectification aims to eliminate geometric deformation in photographed documents to facilitate text recognition. However, existing methods often neglect the significance of foreground elements, which provide essential geometric references and layout information for document image corre…
Large language models (LLMs) hold revolutionary potential to digitize and enhance the Health & Public Services (H&PS) industry. Despite their advanced linguistic abilities, concerns about accuracy, stability, and traceability still persist, especially in high-stakes areas such as transportation syst…
Sensor simulation is pivotal for scalable validation of autonomous driving systems, yet existing Neural Radiance Fields (NeRF) based methods face applicability and efficiency challenges in industrial workflows. This paper introduces a Gaussian Splatting (GS) based system to address these challenges:
We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as intermediates or noisy and sparse correspondences from voxel-based model…
We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBo…
While recent online HD mapping methods relieve burdened offline pipelines and solve map freshness, they remain limited by perceptual inaccuracies, occlusion in dense traffic, and an inability to fuse multi-agent observations. We propose RTMap to enhance these single-traversal methods by persistently…
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space, enabling seamless cross-modal prompting and intera…
Cerebrovascular segmentation demands a comprehensive understanding of vascular topology from a global perspective on 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) images. However, existing 3D segmentation methods typically rely on patch-wise processing to manage computational costs, whe…
Movable antennas (MA) allow flexible positioning within a specified region, enhancing wireless communication performance. This paper explores leveraging MA to improve physical layer security in analog beamforming (AB) systems. Specifically, we aim to maximize the secrecy rate by jointly optimizing t…
In order to obtain a good tactile sensing, traditional dexterous hands always enable all the sensing units installed on them all the time, even if just a few sensor units are actually used, which make the tactile sensing system resource-wasting and energy consuming. In order to reduce their complexi
Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for classification and localization tasks but share the same inpu…
We introduce a Cable Grasping-Convolutional Neural Network (CG-CNN) designed to facilitate robust cable grasping in cluttered environments. Utilizing physics simulations, we generate an extensive dataset that mimics the intricacies of cable grasping, factoring in potential collisions between cables…
Tactile servoing is an effective approach to enabling robots to safely interact with unknown environments. One of the core problems in tactile servoing is to robustly converge the contact features to the desired ones via a dedicated controller. This paper proposes a Data-Driven Model Predictive Cont…
Active reconfigurable intelligent surface (RIS) is a new RIS architecture that can reflect and amplify communication signals. It can provide enhanced performance gain compared to the conventional passive RIS systems that can only reflect the signals. On the other hand, the design problem of active R…
This letter investigates the time-optimal trajectory generation for a six-degrees-of-freedom articulated robot moving along a given parametric path. In the generation procedure, besides the velocity, acceleration, and joint torque, the jerk is also constrained to enhance the smoothness of the robot'
Federated graph learning (FedGL) is an emerging learning paradigm to collaboratively train graph data from various clients. However, during the development and deployment of FedGL models, they are susceptible to illegal copying and model theft. Backdoor-based watermarking is a well-known method for…
In this paper, we study the joint admission control and beamforming problem within a network where one multi-antenna base station tries to serve multiple single-antenna users. Unlike most existing studies which merely identify the users that should be denied, our work further suggest better position…
Infrared small targets often exhibit small scale and weak semantic features, which makes it a great challenge to their detection. To address this situation, we propose a novel network for infrared small target detection that combines local details information and global contextual information. To pr…
Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors during their reasoning processes. Existing solutions, such as deploying task-specific verifiers or voting over multiple re…
Traditional reinforcement learning control for quadruped robots often relies on privileged information, demanding meticulous selection and precise estimation, thereby imposing constraints on the development process. This work proposes a Self-learning Latent Representation (SLR) method, which achieve…
This paper studies a risk minimization problem with decision dependent data distribution. The problem pertains to the performative prediction setting in which a trained model can affect the outcome estimated by the model. Such dependency creates a feedback loop that influences the stability of optim…
This paper studies the performative prediction problem where a learner aims to minimize the expected loss with a decision-dependent data distribution. Such setting is motivated when outcomes can be affected by the prediction model, e.g., in strategic classification. We consider a state-dependent set…
Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs) are plagued by the critical issue of hallucination. The reliable detection of such hallucinations in MLLMs has, therefore, become a vital aspect of model evaluation and the safeguarding of practical application…
Recent advanced Table Structure Recognition (TSR) models adopt image-to-text solutions to parse table structure. These methods can be formulated as image caption problem, i.e., input a single-table image and output table structure description in a specific text format, e.g., HTML. With the impressiv…
Mammogram image is important for breast cancer screening, and typically obtained in a dual-view form, i.e., cranio-caudal (CC) and mediolateral oblique (MLO), to provide complementary information for clinical decisions. However, previous methods mostly learn features from the two views independently…
Sleep stage classification based on physiological time-series is essential for sleep quality evaluation and the diagnosis of sleep disorders in clinical practice. Existing machine learning studies have achieved adequate results in sleep stage classification. However, those methods neglect the signif…
Generative Adversarial networks (GANs) have demonstrated their powerful capability of synthesizing high-resolution images, and great efforts have been made to interpret the semantics in the latent spaces of GANs. However, existing works still have the following limitations: (1) the majority of works…
Human-centric perception targets for understanding human body pose, shape and segmentation. Pre-training the model on large-scale datasets and fine-tuning it on specific tasks has become a well-established paradigm in human-centric perception. Recently, self-supervised learning methods have re-inves…
One-shot segmentation of brain tissues is typically a dual-model iterative learning: a registration model (reg-model) warps a carefully-labeled atlas onto unlabeled images to initialize their pseudo masks for training a segmentation model (seg-model); the seg-model revises the pseudo masks to enhanc…
This paper describes our topic segmentation (TS) system submitted to the ICASSP2023 Signal Processing Grand Challenge - General Meeting Understanding and Generation challenge (MUG). We make three improvements to the official baseline system of the TS track. Firstly, considering that meeting transcri…
Referring image segmentation aims to segment a referent via a natural linguistic expression. Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet…
In this paper, a deep learning network with double closed-loop structure is introduced to tackle the image deblurring problem. The first closed-loop in our model is composed of two networks which learn a pair of opposite mappings between the blurry and sharp images. By this way, the solution spaces…
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar misleading pixels, e.g., backgrounds. To address this issue,…
We consider a scenario where multiple agents are learning a common decision vector from data which can be influenced by the agents’ decisions. This leads to the problem of multi-agent performative prediction (Multi-PfD). In this paper, we formulate Multi-PfD as a decentralized optimization problem t…
Grasping of objects using multi-fingered robotic hands often fails due to small uncertainties in the hand motion control and the object's pose estimation. To tackle this problem, we propose a grasping adjustment strategy based on tactile seroving. Our technique employs feedback from a sensorized mul…
Geospatial object detection is an essential task in remote sensing community. One-stage methods based on deep learning have faster running speed but cannot reach higher detection accuracy than two-stage methods. In this paper, to achieve excellent speed/accuracy trade-off for geospatial object detec…
This paper studies the performative prediction problem which optimizes a stochastic loss function with data distribution that depends on the decision variable. We consider a setting where the agent(s) provides samples adapted to both the learner’s and agent’s previous states. The samples are then us…
Recognition of soft objects is a critical step to tailor policy for dexterous manipulation. Deformation property is one of the valuable tactile cues for inferring the identities of soft objects, especially those having similar appearance features. In this work, we implemented tactual grasping for di
Learning from a label distribution has achieved promising results on ordinal regression tasks such as facial age and head pose estimation wherein, the concept of adaptive label distribution learning (ALDL) has drawn lots of attention recently for its superiority in theory. However, compared with the…
Generative Adversarial Networks (GANs) have made a dramatic leap in high-fidelity image synthesis and stylized face generation. Recently, a layer-swapping mechanism has been developed to improve the stylization performance. However, this method is incapable of fitting arbitrary styles in a single mo…
Hyperspectral image exhibits low spatial resolution due to the limitation of imaging system. Improving it without an auxiliary high resolution (HR) image still remains a challenging problem. Recently, although many deep learning-based hyperspectral image super-resolution (SR) methods have been propo…
Optimal jamming has important applications in both military and civil communications. There have been a brunch of works investigating the optimal jamming signal design when the signal modes of the opponent are known. In this work, we focus on the less studied hidden mode jamming problem. That is, th…
Humans use their limbs to perform various movements to interact with an external environment. Thanks to limb's variable and adaptive stiffness, humans can adapt their movements to the external unstable dynamics. The underlying adaptive mechanism has been investigated, employing a simple planar devic
In this work, we focus on improving the robot’s dexterous capability by exploiting visual sensing and adaptive force control. TeachNet, a vision-based teleoperation learning framework, is exploited to map human hand postures to a multi-fingered robot hand. We augment TeachNet, which is originally ba…
In facial action unit (AU) recognition tasks, regional feature learning and AU relation modeling are two effective aspects which are worth exploring. However, the limited representation capacity of regional features makes it difficult for relation models to embed AU relationship knowledge. In this p…
In robotic teleoperation, an operator usually needs to be trained for long hours. One of the factors leading to this steep learning curve is the quality of telepresence. This letter proposes a novel and user-friendly telepresence interface for manipulation. Visual information from different views is
Online insurance is a new type of e-commerce with exponential growth. An effective recommendation model that maximizes the total revenue of insurance products listed in multiple customized sales scenarios is crucial for the success of online insurance business. Prior recommendation models are ineffe…
Benefiting from the merits of low cost and high mobility, Unmanned aerial vehicle (UAV) enabled communications have recently drawn considerable attentions. In this paper, we consider the UAV-enabled physical-layer secure communications. Specifically, we consider a UAV-ground communication systems wi…
For many Internet companies, it has been an important focus to improve user retention rate. To achieve this goal, we need to recommend proper services in order to meet the demands of users. Unlike conventional click-through rate (CTR) estimation, there are lots of noise in the collected data when m…
This paper studies the security issue of a gossip-based distributed projected gradient (DPG) algorithm, when it is applied for solving a decentralized multi-agent optimization. It is known that the gossip-based DPG algorithm is vulnerable to insider attacks because each agent locally estimates its (…
Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations to provide communication service for remote mobile users due to their high mobility and flexible deployment. However, the line-of-sight (LoS) wireless links are vulnerable to be intercepted by the eavesdropper (Eve), which prese…
This paper studies nonconvex quadratically constrained quadratic program (QCQP), which is known to be NP-hard in general. In the past decades, various approximate approaches have been developed to tackle the QCQP, including semidefinite relaxation (SDR), successive convex approximation (SCA), the va…
This paper considers multiuser massive MIMO downlink transmission, where the base station (BS) employs a massive number of transmit antennas, each equipped with a low-resolution phase shifter, to simultaneously shape desired symbols at user side, after passing through the channels and receive beamfo…
In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackle the problem of reconstructing the full 3D mesh of a human hand from a single RGB image. In contrast to existing research on 2D or 3D hand pose estimation from RGB or/and depth image data, HAMR can provide a more expressive and…
This paper considers content delivery of the cache-enabled small cell networks (C-SCNs), where users with the same request form a multicast group and are served by a cluster of small-cell base stations (SBSs) under the coordination of the central processor. The performance of such a coordination is…
Simplex-structured matrix factorization (SSMF) is a problem of recovering a basis matrix and the corresponding coefficient vectors from data, where the coefficient vectors are constrained to lie in the unit simplex. SSMF has attracted growing attention in recent years, with numerous applications suc…
In this paper, we consider how to maintain the communication quality for high-speed users in array transmission. Due to high user speed, the array transmission angle changes quickly. As a consequence, the phase shifters (beamformers) of traditional phase arrays need to be updated frequently to aim a…
The usage of articulated tools for autonomous robots is still a challenging task. One of the difficulties is to automatically estimate the tool's kinematics model. This model cannot be obtained from a single passive observation, because some information, such as a rotation axis (hinge), can only be…
This paper considers mobile computation offloading in fog-radio access networks (F-RAN), where multiple mobile users offload their computation tasks to the F-RAN through a number of fog nodes [a.k.a. enhanced remote radio heads (RRHs)]. In addition to communication capability, the fog nodes are also…
Massive multiple-input multiple-output (MIMO) has the potential to substantially improve the spectral efficiency, robustness and coverage of mobile networks. However, such potential is limited by hardware cost and power consumption associated with a large number of RF chains. Recently, one-bit quant…
In support of Cloud Robotics, Robotics and Automation as a Service (RAaaS) frameworks have the potential to reduce the complexity of software development, simplify software installation and maintenance, and facilitate data sharing for machine learning. In this proof-of-concept paper, we describe Ber…
Influence maximization is the problem of selecting $k$ nodes in a social network to maximize their influence spread. The problem has been extensively studied but most works focus on the submodular influence diffusion models. In this paper, motivated by empirical evidences, we explore influence maxim…
This paper considers a special subclass of separable semidefinite programs (SDPs), with the goal of identifying certain conditions under which the SDP has a low-rank solution. We prove that when the data matrices of the SDP satisfy certain matrix inequalities, the SDP has a low-rank solution. Moreov…
Multi-label image classification aims to predict multiple labels for a single image which contains diverse content. By utilizing label correlations, various techniques have been developed to improve classification performance. However, current existing methods either neglect image features when expl…
In this paper, parameter estimation for multi-dimensional sinusoids in additive impulsive noise is addressed. Our underlying idea is to minimize the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -norm of the residual error tensor, where 1 <;…
Consider a network that consists of one multi-antenna base station (BS) and multiple pairs of multi-antenna user equipments (UEs). In each UE pair, the communication between transmitter and receiver is established either through BS or via device-to-device (D2D) link. All the D2D transmission and the…
Consider a full-duplex two-way relay network, where two legitimate nodes simultaneously transmit and receive confidential information through a full-duplex multiantenna relay, in the presence of an eavesdropper. To secure the communications, an artificial-noise (AN)-aided amplify-and-forward (AF) st…