29 accepted papers
Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomi…
Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned,…
Accurate cell instance segmentation is foundational for digital pathology analysis. Existing methods based on contour detection and distance mapping still face significant challenges in processing complex and dense cellular regions. Graph coloring-based methods provide a new paradigm for this task,…
The multi-lead electrocardiogram (ECG) stands as a cornerstone of cardiac diagnosis. Recent strides in electrocardiogram self-supervised learning (eSSL) have brightened prospects for enhancing representation learning without relying on high-quality annotations. Yet earlier eSSL methods suffer a key
Anomaly detection in dynamic graphs is essential for monitoring evolving systems such as transaction networks and online platforms. Yet existing methods remain limited in realistic edge-stream settings: snapshot-based approaches discretize continuous interactions and miss fine-grained temporal signa
A positioning system that relies solely on observations based on a local frame, such as visual-inertial odometry (VIO), suffers from unobservable directions, leading to cumulative estimation errors over time. To address this issue, we propose a tightly-coupled Visual-Inertial-GNSS-Barometer odometry
Autoregressive generative models play a key role in various language tasks, especially for modeling and evaluating long text sequences. While recent methods leverage stochastic representations to better capture sequence dynamics, encoding both temporal and structural dependencies and utilizing such
How to balance between exploration and exploitation in an uncertain environment is a central challenge in reinforcement learning. In contrast, humans and animals have demonstrated superior exploration efficiency in novel environments. To understand how the brain’s neural network controls exploration…
The advent of single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) offers an innovative perspective for deciphering regulatory mechanisms by assembling a vast repository of single-cell chromatin accessibility data. While foundation models have achieved significant suc…
In this paper, we investigate the feasibility of using knowledge graphs to interpret actions and behaviors for robot manipulation control. Equipped with an uncalibrated visual servoing controller, we propose to use robot knowledge graphs to unify behavior trees and geometric constraints, conceptuali
The generalization ability of deep learning has been extensively studied in supervised settings, yet it remains less explored in unsupervised scenarios. Recently, the Unsupervised Domain Generalization (UDG) task has been proposed to enhance the generalization of models trained with prevalent unsupe…
Operating high degree of freedom robots can be difficult for users of wheelchair mounted robotic manipulators. Mode switching in Cartesian space has several drawbacks such as unintuitive control reference frames, separate translation and orientation control, and limited movement capabilities that hi
In this paper, we perform robot manipulation activities in real-world environments with language contexts by integrating a compact referring image segmentation model into the robot's perception module. First, we propose CLIPU<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www
Positron Emission Tomography (PET) is a powerful molecular imaging tool that plays a crucial role in modern medical diagnostics by visualizing radio-tracer distribution to reveal physiological processes. Accurate organ segmentation from PET images is essential for comprehensive multi-systemic analys…
3D medical image self-supervised learning (mSSL) holds great promise for medical analysis. Effectively supporting broader applications requires considering anatomical structure variations in location, scale, and morphology, which are crucial for capturing meaningful distinctions. However, previous m…
Variations in medical imaging modalities and individual anatomical differences pose challenges to cross-modality generalization in multi-modal tasks. Existing methods often concentrate exclusively on common anatomical patterns, thereby neglecting individual differences and consequently limiting thei…
Measuring the coherence of text is a vital aspect of evaluating the quality of written content. Recent advancements in neural coherence modeling have demonstrated their efficacy in capturing entity coreference and discourse relations, thereby enhancing coherence evaluation. However, many existing me…
The classical human-robot interface in uncalibrated image-based visual servoing (UIBVS) relies on either human annotations or semantic segmentation with categorical labels. Both methods fail to match natural human communication and convey rich semantics in manipulation tasks as effectively as natura…
Despite significant progress in perception tasks such as 3D scene mapping and semantic information extraction using SLAM and deep learning, applying these techniques within computationally constrained embedded systems remains a challenge. In this work, we introduce a novel end-to-end framework for e…
Image retrieval plays an important role in the Internet world. Usually, the core parts of mainstream visual retrieval systems include an online service of the embedding model and a large-scale vector database. For traditional model upgrades, the old model will not be replaced by the new one until th…
Combining Global Navigation Satellite System (GNSS) with visual and inertial sensors can give smooth pose estimation without drifting. The fusion system gradually degrades to Visual-Inertial Odometry (VIO) with the number of satellites decreasing, which guarantees robust global navigation in GNSS un
Recently, multi-expert methods have led to significant improvements in long-tail recognition (LTR). We summarize two aspects that need further enhancement to contribute to LTR boosting: (1) More diverse experts; (2) Lower model variance. However, the previous methods didn't handle them well. To this…
Single-Photon Image Super-Resolution (SPISR) aims to recover a high-resolution volumetric photon counting cube from a noisy low-resolution one by computational imaging algorithms. In real-world scenarios, pairs of training samples are often expensive or impossible to obtain. By extending Equivariant…
Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, an…
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level…
Depth information is considered valuable as it describes geometric structures, which benefits various robotic tasks. However, the depth acquired by RGB-D sensors still suffers from two deficiencies, i.e., incompletion and noises. Previous methods complete depth by exploring hand-tuned models or rais…
Visual-Inertial Odometry (VIO) is an approach to give high-accuracy pose estimation in GNSS(Global Navigation Satellite System)-denied environments. However, visual-inertial navigation slowly drifts on its four unobservable directions, namely the translations and yaw in the world frame. The visual a
Manipulation tasks in daily life, such as pouring water, unfold through human intentions. Being able to process contextual knowledge from these Activities of Daily Living (ADLs) over time can help us understand manipulation intentions, which are essential for an intelligent robot to transition smoot…
Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots…