96 accepted papers
We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textual cues through a crossmodal prompt encoding scheme, Anomagic leverages rich contextual information to steer an inpaint
Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts.…
Collaborative perception empowers autonomous agents to share complementary information and overcome perception limitations. While early fusion offers more perceptual complementarity and is inherently robust to model heterogeneity, its high communication cost has limited its practical deployment, pro
Collaborative perception is pivotal for the large-scale deployment of autonomous driving, yet it has long grappled with the trade-off between perception accuracy and bandwidth consumption. Existing methods fail to analyze the fine-grained characteristics of Field of View (FoV), leading to inefficien…
Graphic design plays a vital role in visual communication across advertising, marketing, and multimedia entertainment. Prior work has explored automated graphic design generation using diffusion models, aiming to streamline creative workflows and democratize design capabilities. However, complex gra…
Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world d
Collaborative perception leveraging intermediate feature fusion has emerged as a leading paradigm to significantly enhance the environmental perception capabilities of autonomous driving systems. However, existing methods typically rely on discriminative supervision guided by downstream tasks. This
Current collaborative perception systems have significantly improved 3D object detection performance. However, widely used LiDAR and camera systems often suffer performance degradation under adverse weather conditions. The weather-robust 4D radar provides a promising solution to address this challen
The proliferation of multi-modal data on the internet has intensified the need for structured event understanding across textual and visual modalities. However, existing multi-modal event extraction models suffer from three major limitations: the absence of explicit event schema guidance, coarse-gra
We present Magnol.AI Copilot, an extension of the Magnol.AI digital biomarker platform that integrates multimodal large language models (LLMs) to transform digital health technology (DHT) trial dashboards into conversational systems. Copilot augments the platform with a multi-agent orchestration lay
To enhance the efficiency and safety of mobile robot path planning, this letter proposes a hybrid sampling and space-optimized RRT (HB-RRT) method. First, a hybrid sampling strategy combining Gaussian sampling with parallel sampling is employed to replace conventional random sampling. During the sam
Despite significant advancements in point cloud analysis, reducing energy consumption and improving robustness remain understudied, largely due to the inherent limitations of Convolutional Neural Networks (CNNs). To address this, we take the cue from the primary visual cortex and propose a Dendritic
With the rapid growth of visual content in open-world environments, zero-shot hashing image retrieval (ZSHIR) has emerged to tackle the challenge of recognizing novel classes using attribute-level and semantic information. However, existing methods often rely on shallow fusion of multi-source cues
Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotary Positional Encoding (ROPE). Although it can facilitate precise modeling of tok
Coded Aperture Snapshot Spectral Imaging (CASSI) has emerged as a prominent technique for efficient hyperspectral imaging. However, the tight coupling between physical encoding and computational decoding makes CASSI highly sensitive to slight hardware misalignments, which can significantly degrade r
Knowledge-based Visual Question Answering (KVQA) requires models to ground entities in images and reason over factual knowledge. Recent work has introduced its implicit-knowledge variant, IK-KVQA, where a multimodal large language model (MLLM) is the sole knowledge source and answers are produced wi
Recent advances in collaborative perception systems have led to significant improvements in 3D object detection performance. While widely deployed LiDAR and camera systems often experience performance degradation under adverse weather conditions, weather-robust 4D radar offers a promising alternativ…
In industrial point cloud analysis, detecting subtle anomalies demands high-resolution spatial data, yet prevailing benchmarks emphasize low-resolution inputs. To address this disparity, we propose a scalable pipeline for generating realistic and subtle 3D anomalies. Employing this pipeline, we deve
Reconstructing a faithful geometric surface from sparse images remains a fundamental challenge in 3D computer vision. While recent methods have achieved remarkable progress, they still struggle to recover reliable geometry due to the lack of multi-view geometric cues, particularly in non-overlapping
Aerial-terrestrial amphibious robots excel in search and rescue tasks in unstructured terrains but face challenges in autonomous navigation indoors. Traditional full-mapping methods can degrade global path planning performance, especially when semi-static obstacles shift, leading to suboptimal paths
With the massive growth of multimedia data, local devices gradually cannot meet the data processing needs, thus utilizing cloud server resources becomes better choice. To prevent privacy leakage, user data can only be stored in ciphertext. Existing cross-media retrieval schemes are only for plaintex…
Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to produce photorealistic images/videos, which is computationall…
The ability of autonomous subtask generation is important for robots to effectively cope with unforeseen situations during indoor search and rescue missions. While prior work mainly focused on improving individual low-level skills of the rescue robot, this paper proposes AutoExpand: a high-level fra
Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue to encounter challenges related to low inference speed, prima…
Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate pseudo labels for the missing instances. However, these methods…
The paper proposes a novel Economic Model Predictive Control (EMPC) scheme for Autonomous Surface Vehicles (ASVs) to simultaneously address path following accuracy and energy constraints under environmental disturbances. By formulating lateral deviations as energy-equivalent penalties in the cost fu
Diffusion models have been recognized for their ability to generate images that are not only visually appealing but also of high artistic quality. As a result, Layout-to-Image (L2I) generation has been proposed to leverage region-specific positions and descriptions to enable more precise and control…
Lung cancer is a leading cause of cancer-related deaths globally. PET-CT is crucial for imaging lung tumors, providing essential metabolic and anatomical information, while it faces challenges such as poor image quality, motion artifacts, and complex tumor morphology. Deep learning-based models are…
Time series anomaly detection plays a crucial role in a wide range of real-world applications. Given that time series data can exhibit different patterns at different sampling granularities, multi-scale modeling has proven beneficial for uncovering latent anomaly patterns that may not be apparent at…
Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality features faces domain gaps from hardware diversity and deploy…
Clustering is a common method used in machine learning to group sample points in a dataset. Gaussian Mixture Clustering (GMC) is a clustering method based on maximum likelihood estimation and expectation maximisation (EM) algorithms. Traditional GMC does not consider the fairness between different s…
The performance of traditional beamforming algorithms is influenced by the number of microphones, with performance improving as the number increases. However, in practice, the number of microphones is often limited. In this paper, we propose a novel virtual microphone estimation method that combines…
Existing deep learning-based models for remote sensing pansharpening exhibit exceptional performance on training datasets. However, due to sensor-specific characteristics and varying imaging conditions, these models suffer from substantial performance degradation when applied to unseen satellite dat…
This paper addresses the problem of face relighting under varying illumination conditions. Lighting is a fundamental element in portrait photography that shapes the mood, geometry, and overall realism of the captured characters. Most previous studies have mainly treated relighting as a 2D generation…
Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs), such as Multimodal Large Language Models (MLLMs) and Stable Diffusion Models (SDMs). Despite its effectiveness in removing undesired knowledge, GA leads to severe utility degradati…
Functional grasping is essential for humans to perform specific tasks, such as grasping scissors by the finger holes to cut materials or by the blade to safely hand them over. Enabling dexterous robot hands with functional grasping capabilities is crucial for their deployment to accomplish diverse r
Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, inc…
In the field of clustering algorithms, the Fuzzy CMeans algorithm stands out for its ability to deal with uncertainty by assigning membership degrees to data points. However, research on the fairness of Fuzzy C-Means algorithms has mainly focused on group fairness, with limited attention to individu…
Precise motion tracking control with unknown structural knowledge and noise disturbance for redundant robots remains a critical and unresolved challenge. This article proposes a novel data-driven fuzzy discrete recurrent neural network (D<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlin
Robotic tool manipulation requires understanding task-relevant semantics under visually challenging conditions, such as shape variation and occlusion. This paper presents a novel framework for Language-Embedded Semantic 6D Pose Estimation that combines natural language instructions with 3D point clo
Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly defined spatial paths.However, existing methods struggle with c…
Composed Image Retrieval (CIR) seeks to find a target image using a multi-modal query, which combines an image with modification text to pinpoint the target. While recent CIR methods have shown promise, they mainly focus on exploring relationships between the query pairs (image and text) through dat…
Repetitive motion control of redundant manipulators typically requires precise kinematic models to construct Jacobian matrices. However, model-based approaches are inherently limited when manipulator parameters are unavailable or only partially known. This paper introduces a novel data-driven discre
In contact-rich tasks such as polishing and drilling, inevitable physical interactions often lead to task deviations due to interference, typically resulting in excessive contact forces and eventual task failure. To tackle these challenges, we propose an innovative human-guided visual-impedance cont
Motion planning for continuous contact-based aerial manipulators on complex unstructured surfaces remains a substantial challenge due to the sophisticated topology of unstructured surfaces. While direct planning in the high-dimensional configuration space manifolds faces efficiency limitations, simp
The ability to robustly grasp a variety of objects is essential for dexterous robots. In this paper, we present a framework for zero-shot dynamic dexterous grasping using single-view visual inputs, designed to be resilient to various disturbances. Our approach utilizes a hand-centric object shape re…
Since its inception, impedance control has emerged as a fundamental framework for robotic interaction control. Recent advancements in geometric impedance control have demonstrated certain advantages over traditional Cartesian impedance control. However, existing geometric impedance control approache
Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, *i.e.* accurately generating entities with specified attributes and locations. Segmentation-mask-to-image (S2I) generation has emerged as a promising solution by…
Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled pinhole data to unlabeled panoramic images, but they require a…
Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hall…
The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing research into machine unlearning. However, existing unlearning app…
This paper addresses the problem of camera calibration and shape recovery using a single image of a reflectively symmetric object. Unlike existing methods requiring knowledge of 3D points or two images, this paper proposes to calibrate camera parameters using one image with known point distance rati…
Multi-channel speech enhancement extracts speech using multiple microphones that capture spatial cues. Effectively utilizing directional information is therefore key. Deep learning shows great potential on multi-channel speech enhancement and often takes short-time Fourier Transform (STFT) as inputs…
Vectorized High-Definition (HD) map construction requires predictions of the category and point coordinates of map elements (e.g. road boundary lane divider pedestrian crossing etc.). State-of-the-art methods are mainly based on point-level representation learning for regressing accurate point coord…
Social insurance benefits qualification assessment is an important task to ensure that retirees enjoy their benefits according to the regulations. It also plays a key role in curbing social security frauds. In this paper, we report the deployment of the Intelligent Benefit Certification and Analysis…
Multi-channel speech enhancement leverages multiple microphones to extract target speech signals amid background noise. Effectively utilizing directional cues is key for robust enhancement. While deep learning shows promise for multi-channel speech processing, most methods operate on short-time Four…
Driving systems often rely on high-definition (HD) maps for precise environmental information, which is crucial for planning and navigation. While current HD map constructors perform well under ideal conditions, their resilience to real-world challenges, \eg, adverse weather and sensor failures, is…
HD map construction is a fundamental and challenging task in autonomous driving to understand the surrounding environment. Recently, Camera-LiDAR BEV feature fusion methods have attracted increasing attention in HD map construction task, which can significantly boost the benchmark. However, existing…
"Online high-definition (HD) map construction is an important and challenging task in autonomous driving. Recently, there has been a growing interest in cost-effective multi-view camera-based methods without relying on other sensors like LiDAR. However, these methods suffer from a lack of explicit d…
The emergence of non-fingered soft bioinspired grippers poses a challenge for learning-based grasping control due to the lack of a model describing grasping robustness and a dataset for training. In this letter, we propose a comprehensive pipeline encompassing grasping evaluation, dataset generation
The exploration of robotic dexterous hands utilizing tools has recently attracted considerable attention. A significant challenge in this field is the precise awareness of a tool’s pose when grasped, as occlusion by the hand often degrades the quality of the estimation. Additionally, the tool’s over…
The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow…
The widespread use of cloud-based face recognition technology raises privacy concerns as unauthorized access to face images can expose personal information or be exploited for fraudulent purposes. In response privacy-preserving face recognition (PPFR) schemes have emerged to hide visual information…
This paper proposes AlphaRoute, an AlphaGo inspired algorithm for coordinating large-scale routes, built upon graph attention reinforcement learning and Monte Carlo Tree Search (MCTS). We first partition the road network into regions and model large-scale coordinated route planning as a Markov game,…
In this letter, a grasping neural network for a bio-inspired gripper (BIG-Net) trained on a synthetic dataset is proposed for the picking of novel objects. The grasp feasibility is evaluated by tracking the deformation of the soft gripping pad and three types of gripping forces during simulation. Ov
This paper addresses the problem of calibrating extrinsic parameter matrix between an RGB camera and a LiDAR. Multimodal sensing systems are essential for fully autonomous navigation platforms. A key pre-requisite for such a system is calibration between different sensors. As the two most widely equ…
Interactive image segmentation aims at obtaining a segmentation mask for an image using simple user annotations. During each round of interaction, the segmentation result from the previous round serves as feedback to guide the user's annotation and provides dense prior information for the segmentati…
This paper addresses the linear auto-calibration problem of a pan-tilt-zoom (PTZ) camera. Unlike existing methods, we take full advantage of the offset of the camera center from the rotation center, which is usually non-negligible in bullet-type PTZ cameras. Without any prior assumption, we propose…
Recent works have proposed to craft adversarial clothes for evading person detectors, while they are either only effective at limited viewing angles or very conspicuous to humans. We aim to craft adversarial texture for clothes based on 3D modeling, an idea that has been used to craft rigid adversar…
Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the o…
Learning per-point semantic features from the hierarchical feature pyramid is essential for point cloud semantic segmentation. However, most previous methods suffered from ambiguous region features or failed to refine per-point features effectively, which leads to information loss and ambiguous sema…
Shadows in images can degrade the performance of many applications. In this paper, we propose a novel multi-level feature-aware network, called TransShadow, which uses Transformer to capture both local and global context from a single image for shadow detection. Specifically, we design a multi-level…
3D single object tracking in point clouds is an essential task in robotics and autonomous driving. Many astonished trackers only adopt the voting-based region proposal network (RPN) to regress the object's location. However, they suffer from heavy outlier votes and ignore the global semantic feature
Non-autoregressive transformer (NAT) based speech recognition models have gained more and more attention since they perform faster inference speed compared with autoregressive counterparts, especially when the single-step decoding is applied. However, the single-step decoding process with length pre…
In this paper, we study the loss-metric mismatch problem of supervised single-channel speech enhancement system. Most of the existing speech enhancement systems achieve unsatisfying performance since their empirically selected loss functions have semantic gaps with the non-differentiable evaluation…
Scientific literature serves as a high-quality corpus, supporting a lot of Natural Language Processing (NLP) research. However, existing datasets are centered around the English language, which restricts the development of Chinese scientific NLP. In this work, we present CSL, a large-scale Chinese S…
"This paper addresses the problem of camera auto-calibration from the fundamental matrix under general motion. The fundamental matrix can be decomposed into a symmetric part (a Steiner conic) and a skew-symmetric part (a fixed point), which we find useful for fully calibrating camera parameters. We…
PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command-line interface and a simple code structure. This paper describes the design philosophy and core architecture of PaddleS…
Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several sub-tasks and utilize multiple surrogates (e.g. boxes and masks, cen…
Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervise…
This paper presents a new variable stiffness actuator based on a second-order lever mechanism which has wide stiffness regulation range. By employing a novel symmetric structure design and improving the load capacity of the stiffness regulation module, the proposed actuator also shows well performan…
3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and challenging topic due to the irregular and sparse nature of…
In this work, we devote to address the challenging problem of scene parsing. Previous methods, though capture context to exploit global clues, handle scene parsing as a pixel-independent task. However, it is well known that pixels in an image are highly correlated with each other, especially those f…
Sequence-to-sequence attention-based models for grapheme-to-phoneme (G2P) conversion have gained significant interests. The attention-based encoder-decoder framework learns the mapping of input to output tokens by selectively focusing on relevant information, and has been shown well performance. How…
Deep learning based methods, especially convolutional neural networks (CNNs) have been successfully applied in the field of single image super-resolution (SISR). To obtain better fidelity and visual quality, most of existing networks are of heavy design with massive computation. However, the computa…
Ordinal loss is widely used in solving regression problems with deep learning technologies. Its basic idea is to convert regression to classification while preserving the natural order. However, the order constraint is enforced only by ordinal label implicitly, leading to the real output values not…
The deep learning methods in addressing semantic segmentation typically demand vast amount of pixel-wise annotated training samples. In this work, we present zero-shot semantic segmentation, which aims to identify not only the seen classes contained in training but also the novel classes that have n…
Scene text recognition (STR) is challenging due to the diversity of text instances and the complexity of scenes. However, no STR methods can adapt backbones to different diversities and complexities. In this work, inspired by the success of neural architecture search (NAS), we propose automated STR…
Speech enhancement aims to separate a target speech from background noise. Recently, speech enhancement has been formulated as a supervised learning problem, in which a learning machine is trained to estimate the target spectrum denoted as mapping-based method or a time-frequency mask denoted as mas…
Scale recovery is one of the essential problems for monocular visual odometry. The camera height is usually used as an absolute reference to recover the scale. In this case, the precision of scale recovery depends on the accuracy of the road region detection and road geometrical model calculation. I…
Supervised speech separation methods train learning machine to cast the noisy speech to the target clean speech. Most of them use mean-square error (MSE) as loss function. However, MSE is not the perfect choice because it doesn't match the human auditory perception. Short-time objective intelligibil…
Pitch is an important characteristic of speech and is useful for many applications. However, pitch determination in noisy conditions is difficult. In this paper, we propose a supervised learning algorithm to estimate pitch using a convolutional neural network (CNN). Specifically, we use a CNN for pi…
We propose a method to recover the shape of a 3D room from a full-view indoor panorama. Our algorithm can automatically infer a 3D shape from a collection of partially oriented superpixel facets and line segments. The core part of the algorithm is a constraint graph, which includes lines and superpi…
How to avoid ambiguity is a challenging problem for conic-based homography estimation. In this paper, we address the problem of homography estimation from two separate ellipses. We find that any two ellipses have a unique common self-polar triangle, which can provide three line correspondences. Furt…
Pitch information is an important cue for speech separation. However, pitch estimation in noisy condition is also a task as challenging as speech separation. In this paper, we propose a supervised learning architecture which combines these two problems concisely. The proposed algorithm is based on d…
In projective geometry, the common self-polar triangle has often been used to discuss the position relationship of two planar conics. However, there are few researches on the properties of the common self-polar triangle, especially when the two planar conics are special conics. In this paper, we exp…