101 accepted papers
Latent Diffusion Models have become a powerful tool for generating high-fidelity unrestricted adversarial examples. However, the existing methods typically perturb only the initial latent or rely on prompt engineering, which is ill-suited to the iterative nature of the diffusion process, plus optimi
Federated Learning (FL) often suffers from a trade-off between global model performance and client-level fairness due to data heterogeneity, which often leads to inconsistent performance of the globally trained models, resulting in unfair outcomes among users. Existing fair FL algorithms face a trad…
Facial expression recognition (FER) in the wild is severely hampered by label noise and annotation ambiguity. Existing methods, including sample selection, label ensembling, and consistency regularization, primarily rely on ordinary label supervision and offer limited control over non-target predict
Acquiring three-dimensional(3D) microstructural images of cement hydration reveals critical microscale features essential for understanding hydration mechanisms and advancing material development. Micro-computed tomography(µCT) is widely used to capture these images due to its non-destructive, repea
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual
Abstract— As teamed robots increasingly share public spaces with humans, the ability to co-adapt—to mutually adjust behavior in response to one another—becomes essential for safe, efficient, and socially acceptable operation. This paper introduces a socially co-adaptive framework for heterogeneous m…
In this paper, we present Ev-iCRF, a novel self-supervised pipeline for high dynamic range (HDR) image reconstruction from a single-exposure low dynamic range (LDR) image, guided by asynchronous event streams generated by a bio-inspired event camera. The highlight of Ev-iCRF lies in its formulation
Event cameras are bio-inspired sensors that capture visual information through asynchronous brightness changes, offering distinct advantages including high temporal resolution and wide dynamic range. While prior research has investigated event-based 3D reconstruction for extreme scenarios, existing
Recent advances in neural rendering have enabled the 3D reconstruction of dynamic humans from monocular videos, with applications in robotics. However, it is still challenging to reconstruct clear humans from in-the-wild video encountering motion blur, causing shape and appearance inconsistencies, e…
Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precision to even the uninformative regions. By contrast, human vision is neither uniform nor static. It is adaptive, selective, and resource-efficient. In lig
Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the equally critical problem: how to transmit and optimize messages among agents effectively? Current communication schemes …
Robust 3D semantic occupancy is essential for legged and humanoid robots, yet most Semantic Scene Completion (SSC) systems are built for wheeled platforms with forward-facing sensors. We present OneOcc, a vision-only panoramic SSC framework tailored to severe body jitter and 360deg continuity. OneOc
Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vulnerable to adversarial attacks—particularly adversarial patch attacks—which can pose serious threats in real-world scen
Recently, diffusion models have been recognized as state-of-the-art models for image generation due to their ability to produce high-quality images. However, recent studies have shown that diffusion models are susceptible to backdoor attacks, where an attacker can activate hidden biases using a spec…
To facilitate the large-scale deployment of autonomous driving in real-world scenarios, developing low-cost and high-performance 3D object detection systems has become a critical technical challenge. Although high-beam LiDARs provide denser point cloud data, their prohibitive hardware cost and high
Reflections on the water surface hinder the extraction of valuable information from water surface images. To remove reflections from water surface images, we construct a synthetic dataset and propose a multi-task network for water surface reflection detection and removal. Specifically, we first use…
Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities usually require white-box access to T2I models, and rely on in…
3D object detection is an important task that has been widely applied in autonomous driving. To perform this task, a new trend is to fuse multi-modal inputs, i.e., LiDAR and camera. Under such a trend, recent methods fuse these two modalities by unifying them in the same 3D space. However, during di
Panoramic depth estimation presents significant challenges due to the severe distortion caused by equirectangular projection (ERP) and the limited availability of panoramic RGB-D datasets. Inspired by the recent success of neural rendering, we propose a self-supervised method, named CUBE360, that le
Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm. Nonetheless, the substantial distribution shifts among clients pose a considerable challenge to the performance of current FL algorithms. To mitigate this challenge, various methods have been proposed to enhance t…
Autonomous vehicles and robots often struggle with reliable visual perception at night due to the low illumination and motion blur caused by the long exposure time of RGB cameras. Existing methods address this challenge by sequentially connecting the off-the-shelf pretrained lowlight enhancement and
Entity Segmentation (ES) aims at identifying and segmenting distinct entities within an image without the need for predefined class labels. This characteristic makes ES well-suited to open-world applications with adaptation to diverse and dynamically changing environments, where new and previously u…
Event cameras are bio-inspired sensors that output asynchronous and sparse event streams, instead of fixed frames. Benefiting from their distinct advantages, such as high dynamic range and high temporal resolution, event cameras have been applied to address 3D reconstruction, important for robotic m
Recent advances in neural rendering have enabled the 3D reconstruction of dynamic humans from monocular videos, with applications in robotics. However, it is still challenging to reconstruct clear humans from in-the-wild video encountering motion blur, causing shape and appearance inconsistencies, e
Text-Attributed Graphs (TAGs), which integrate text and graph structures, have recently gained traction, especially in web applications. However, as a graph structure, TAG representation learning (TAGRL) naturally inherits issues from Graph Neural Networks (GNNs), such as fairness. Moreover, previou
In warehousing systems, to enhance efficiency amid surging demand volumes, much attention has been placed on how to reasonably allocate tasks of delivery to robots. However, the labor of robots is still inevitably wasted to some extent. In this paper, we propose a pre-scheduling enhanced warehousing
The rapid advancement of artificial intelligence has significantly enhanced the intelligence of autonomous vehicles (AVs). However, owing to the complexity of AV behavior and the high dimensionality of driving environments, the objective and practical quantitative evaluation of AV intelligence remai
360 video captures the complete surrounding scenes with the ultra-large field of view of 360x180. This makes 360 scene understanding tasks, *e.g.*, segmentation and tracking, crucial for appications, such as autonomous driving, robotics. With the recent emergence of foundation models, the community…
Monocular 360° depth estimation poses significant challenges due to the inherent distortion of the equirectangular projection (ERP). This distortion separates adjacent spherical points after their projection onto the ERP plane, especially in the polar regions, resulting in insufficient spherical rel
Event cameras are bio-inspired sensors that capture intensity changes asynchronously with distinct advantages, such as high temporal resolution. Existing methods for event-based object/action recognition predominantly sample and convert event representation at every fixed temporal interval (or frequ…
Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its success, it remains an open question regarding DAMs' performance on panorama images that enjoy a large field-of-view (180x36…
Accurate polyp sizing during endoscopy is crucial for cancer risk assessment but is hindered by subjective methods and inadequate datasets lacking integrated 2D appearance, 3D structure, and real-world size information. We introduce PolypSense3D, the first multi-source benchmark dataset specifically…
Understanding the conformational landscape of proteins is essential for elucidating protein function and facilitating drug design. However, existing protein conformation benchmarks fail to capture the full energy landscape, limiting their ability to evaluate the diversity and physical plausibility o…
The Real2Sim2Real (R2S2R) paradigm is critical for advancing robotic learning. Existing methods lack a comprehensive solution to accurately reconstruct real-world objects with both spatial representations and their associated physics attributes in the Real2Sim stage. We propose a Real2Sim pipeline t
Facial expressions are a powerful medium for conveying emotions. In facial expression recognition (FER) field, the difficulty of collecting specific expressions often leads to class imbalance in mainstream datasets, significantly reducing the classification accuracy of deep neural networks. To addre…
Pneumatic actuated soft robots attract increasing interest of the researchers due to the availability and simplicity in actuation. The soft robots driven by soft pneumatic actuators (SPAs) of various active volumes demand pneumatic systems with various range of flow rate. However, the usually bulky
Video frame interpolation (VFI) that leverages the bio-inspired event cameras as guidance has recently shown better performance and memory efficiency than the frame-based methods, thanks to the event cameras' advantages, such as high temporal resolution. A hurdle for event-based VFI is how to effect…
The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and thus ignore the environmental attributes, e.g., motion blur,
"Video frames captured by rolling shutter (RS) cameras during fast camera movement frequently exhibit RS distortion and blur simultaneously. Naturally, recovering high-frame-rate global shutter (GS) sharp frames from an RS blur frame must simultaneously consider RS correction, deblur, and frame inte…
The widespread adoption of edge computing has emerged as a prominent trend for alleviating task processing delays and reducing energy consumption. However, the dynamic nature of network conditions and the varying computation capacities of edge servers (ESs) can introduce disparities between computat…
Implicit neural representation (INR) in combination with geometric rendering has recently been employed in real-time dense RGB-D SLAM. Despite active research endeavors being made there lacks a unified protocol for fair evaluation impeding the evolution of this area. In this work we establish to our…
The ability to detect objects in all lighting (i.e., normal-, over-, and under-exposed) conditions is crucial for real-world applications, such as self-driving. Traditional RGB-based detectors often fail under such varying lighting conditions. Therefore, recent works utilize novel event cameras to s…
3D semantic occupancy prediction is a pivotal task in the field of autonomous driving. Recent approaches have made great advances in 3D semantic occupancy predictions on a single modality. However, multi-modal semantic occupancy prediction approaches have encountered difficulties in dealing with the
Cooking is one of the oldest and the most common human activities in everyone’s daily life. Instructional cooking videos have also become one of the most common data sources for multimodal visual understanding researches. Compared to other domains, multimodal cooking videos: 1. not only have signifi…
"Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose , a 3D Gaussian-based novel text-to-3D scene gen…
360 depth estimation has recently received great attention for 3D reconstruction owing to its omnidirectional field of view (FoV). Recent approaches are predominantly focused on cross-projection fusion with geometry-based re-projection: they fuse 360 images with equirectangular projection (ERP) and…
Recent endeavors have been made to leverage self-supervised depth estimation as guidance in unsupervised domain adaptation (UDA) for semantic segmentation. Prior arts, however, overlook the discrepancy between semantic and depth features, as well as the reliability of feature fusion, thus leading to
"In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and…
In this paper we make the first attempt at achieving the cross-modal (i.e. image-to-events) adaptation for event-based object recognition without accessing any labeled source image data owning to privacy and commercial issues. Tackling this novel problem is non-trivial due to the novelty of event ca…
Event cameras have recently been shown beneficial for practical vision tasks such as action recognition thanks to their high temporal resolution power efficiency and reduced privacy concerns. However current research is hindered by 1) the difficulty in processing events because of their prolonged du…
Although image-dependent adversarial attacks have been studied, the more challenging image-agnostic adversarial attack for deep hashing remains an unexplored territory. In this paper, we take the first attempt on the more efficient and malicious targeted universal adversarial attack (TUAA) for deep…
This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic segmentation model i.e. student without requiring any labeled dat…
Event cameras harness advantages such as low latency, high temporal resolution, and high dynamic range (HDR), compared to standard cameras. Due to the distinct imaging paradigm shift, a dominant line of research focuses on event-to-video (E2V) reconstruction to bridge event-based and standard comput…
Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose th…
"Surgical scene perception via videos is critical for advancing robotic surgery, telesurgery, and AI-assisted surgery, particularly in ophthalmology. However, the scarcity of diverse and richly annotated video datasets has hindered the development of intelligent systems for surgical workflow analysi…
Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic re…
Convolutional neural network (CNN) is easily affected by backdoor injections, whose models perform normally on clean samples but produce specific outputs on poisoned ones. Most of the existing studies have focused on the effect of trigger feature changes of poisoned samples on model generalization…
Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the limited dynamic range and motion blur. Therefore, recent wor…
This paper addresses an interesting yet challenging problem-- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation--given only a pinhole image-trained model (i.e. source) and unlabeled panoramic images (i.e. target). Tackling this problem is nontrivial du…
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets. Moreover, semantic segmentation models trained on daytime d…
Event camera has recently received much attention for low-light image enhancement (LIE) thanks to their distinct advantages such as high dynamic range. However current research is prohibitively restricted by the lack of large-scale real-world and spatial-temporally aligned event-image datasets. To t…
The popular methods for semi-supervised semantic segmentation mostly adopt a unitary network model using convolutional neural networks (CNNs) and enforce consistency of the model’s predictions over perturbations applied to the inputs or model. However, such a learning paradigm suffers from two criti…
We present UniBind a flexible and efficient approach that learns a unified representation space for seven diverse modalities-- images text audio point cloud thermal video and event data. Existing works eg. ImageBind treat the image as the central modality and build an image-centered representation s…
In this paper we propose a new framework and new methods for the reference-free evaluation of topic segmentation systems directly in the embedding space. Specifically, we define a common framework for reference-free, embedding-based topic segmentation metrics, and show how this applies to an existin…
In this paper, we strive to answer the question 'how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation?' Accordingly, we propose an online knowledge dis…
Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent years, the diversity of adversarial examples on 3D point clouds makes them more…
The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For this reason, some works treat the ERP and pinhole images equa…
Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. However, an inadequate client sampling scheme can lead to the selection of unrepresentative subsets, resulting in significant variance in model updates and slowed convergen…
The explicit neural radiance field (NeRF) has gained considerable interest for its efficient training and fast inference capabilities, making it a promising direction such as virtual reality and gaming. In particular, PlenOctree (POT), an explicit hierarchical multi-scale octree representation, has…
Depth estimation from a monocular 360 image is a burgeoning problem owing to its holistic sensing of a scene. Recently, some methods, e.g., OmniFusion, have applied the tangent projection (TP) to represent a 360 image and predicted depth values via patch-wise regressions, which are merged to get a d…
Event cameras have the potential to overcome the limitations of classical computer vision in real-world applications. Depth estimation is a crucial step for high-level robotics tasks and has attracted much attention from the community. In this paper, we propose an event-based dense depth estimation…
Event cameras sense the intensity changes asynchronously and produce event streams with high dynamic range and low latency. This has inspired research endeavors utilizing events to guide the challenging video super-resolution (VSR) task. In this paper, we make the first at tempt to address a novel p…
Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style disparities and distortion problem of the non-uniformly distributed…
The application of deep learning to nursing procedure activity understanding has the potential to greatly enhance the quality and safety of nurse-patient interactions. By utilizing the technique, we can facilitate training and education, improve quality control, and enable operational compliance mon…
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially w…
Omnidirectional images (ODIs) have become increasingly popular, as their large field-of-view (FoV) can offer viewers the chance to freely choose the view directions in immersive environments such as virtual reality. The Mobius transformation is typically employed to further provide the opportunity f…
Endeavors have been recently made to leverage the vision transformer (ViT) for the challenging unsupervised domain adaptation (UDA) task. They typically adopt the cross-attention in ViT for direct domain alignment. However, as the performance of cross-attention highly relies on the quality of pseudo…
Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by…
Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world scenarios requires prohibitive computational costs and faces the c…
Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography. However, existing methods generally fail to accurately learn arbitrary textures, which may result in the failure to synthesize solid textures with high fide…
Generalizing a deep learning model to new domains is crucial for computer-aided medical diagnosis systems. Most existing unsupervised domain adaptation methods have made significant progress in reducing the domain distribution gap through adversarial training. However, these methods may still produc…
"Providing omnidirectional depth along with RGB information is important for numerous applications. However, as omnidirectional RGB-D data is not always available, synthesizing RGB-D panorama data from limited information of a scene can be useful. Therefore, some prior works tried to synthesize RGB…
Facial expression recognition (FER) has recently attracted attention in computer vision. However, existing methods mostly focus on the explicit performance and overlook their computational resources and memory consumption. Hence, achieving promising performance while maintaining the efficiency of mo…
Conditional density estimation (CDE) is the task of estimating the probability of an event conditioned on some inputs. A neural network (NN) can also be used to compute the output distribution for continuous-domain, which can be viewed as an extension of regression task. Nevertheless, it is difficul…
"Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current…
"Motion deblurring is a highly ill-posed problem due to the loss of motion information in the blur degradation process. Since event cameras can capture apparent motion with a high temporal resolution, several attempts have explored the potential of events for guiding deblurring. These methods genera…
Person re-identification (ReID) aims at retrieving images of the same person across non-overlapping camera views. The prior works focus on either fully supervised or unsupervised ReID settings, and achieve remarkable performances. In real scenarios, however, the major annotation cost comes from matc…
The 360deg imaging has recently gained much attention; however, its angular resolution is relatively lower than that of a narrow field-of-view (FOV) perspective image as it is captured using a fisheye lens with the same sensor size. Therefore, it is beneficial to super-resolve a 360deg image. Severa…
"Class Subdivision (CCS) is important for many practical applications, where the training set originally annotated for a coarse class (e.g. bird) needs to further support its sub-classes recognition (e.g. swan, crow) with only very few fine-grained labeled samples. From the perspective of causal rep…
Nuclear instance segmentation is a challenging task due to a large number of touching and overlapping nuclei in pathological images. Existing methods cannot effectively recognize the accurate boundary owing to neglecting the relationship between pixels (e.g., direction information). In this paper, w…
Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur. It has been shown that events alone can be used for end-task learning, e.g., semantic segmentation, based on encoder-decoder-like networks…
Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over the conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks…
Deep neural networks (DNNs) have achieved impressive performance on handling computer vision problems. However, it has been found that DNNs are vulnerable to adversarial examples. For such reason, adversarial perturbations have been recently studied in several respects. However, most previous works
Event cameras sense intensity changes and have many advantages over conventional cameras. To take advantage of event cameras, some methods have been proposed to reconstruct intensity images from event streams. However, the outputs are still in low resolution (LR), noisy, and unrealistic. The low-qua…
In this paper, a new sparse array structure, which further improves the degrees of freedom (DOFs) and enhanced the DOA estimation performance, for the fourth-order cumulant based direction of arrival (DOA) estimation is proposed. The new-formed array is hole-free and can achieve a large consecutive…
We present an audio-visual dataset recorded outdoors from a quadcopter and discuss baseline results for multiple applications. The dataset includes a scenario for source localization and sound enhancement with up to two static sources, and a scenario for source localization and tracking with a movin…
Event cameras have a lot of advantages over traditional cameras, such as low latency, high temporal resolution, and high dynamic range. However, since the outputs of event cameras are the sequences of asynchronous events over time rather than actual intensity images, existing algorithms could not be…
Smartphone-based identification of the mode of transportation of the user is important for context-aware services. We investigate the feasibility of recognizing the 8 most common modes of locomotion and transportation from the sound recorded by a smartphone carried by the user. We propose a convolut…
Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks th…
We propose a method to track from a multi-rotor drone a moving source, such as a human speaker or an emergency whistle, whose sound is mixed with the strong ego-noise generated by rotating motors and propellers. The proposed method is independent of the specific drone and does not need pre-training…
We address the problem of sound source localization with a microphone array mounted on a micro aerial vehicle (MAV). Due to the noise generated by motors and propellers, this scenario is characterized by extremely low signal-to-noise ratios (SNR). Based on the observation that the energy of MAV soun…