64 accepted papers
Subject-driven generation is a critical task in creative AI; yet current state-of-the-art methods present a stark trade-off. They either rely on computationally expensive, per-subject fine-tuning, sacrificing efficiency and zero-shot capability, or employ feed-forward architectures built on diffusio…
Despite significant advancements in general AI, its effectiveness in the medical domain is limited by the lack of specialized medical knowledge. To address this, we formulate GMAI-VL-5.5M, a multimodal medical dataset created by converting hundreds of specialized medical datasets with various annot
This paper presents the mechatronic design and implementation of a hybrid-driven disc-shaped autonomous underwater vehicle (HD-AUV). The hybrid-driven system integrates a buoyancy adjustment system and propeller thrusters, enabling the HD-AUV to achieve both high maneuverability motion and energy-ef
Spatial Transcriptomics (ST) merges the benefits of pathology images and gene expression, linking molecular profiles with tissue structure to analyze spot-level function comprehensively. Predicting gene expression from histology images is a cost-effective alternative to expensive ST technologies. Ho
Image quality is critical for accurate medical diagnosis. However, MRI, CT, and ultrasound images are often of low resolution and quality due to cost constraints, complicating the visualization of key anatomical structures and lesions. While such limitations are common in practice, traditional metho
Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is inefficient and often yields ambiguous global supervision. To addr
Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, existing DM-based VSR methods over-prioritize perceptual synthesis while neglec
Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This
Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic understanding of visual content, limiting their effectiveness in detecting context-dependent privacy risks. We propose PrivAR, which leverages vision…
Brain-assisted target speaker extraction (TSE) isolates a target speaker
Sharpness-Aware Minimization (SAM) empirically boosts generalization by seeking parameters that minimize the worst-case loss in a small neighborhood, yet existing theory explains its behavior under either strong convexity or small perturbation radius. We revisit SAM through the bilevel minimax probl…
Medical diagnosis demands models that can process multimodal medical inputs, such as medical images and patient histories, and generate diverse outputs including textual reports and visual content, such as annotations or segmentation masks. Despite this need, existing medical AI models disrupt this …
We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional fine-tuning of such controllable pipelines frequently suffers from di…
Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative transfer. While most prior work improves transfer through architectural or adaptation choices, we ask a data-centric question: *which properties of …
In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text) contrastive paradigm to learn alignment from large-scale messy web d…
Facial attractiveness prediction (FAP) has long been an important computer vision task, which could be widely applied in live videos with facial retouching. However, previous FAP datasets are either small or closed-source. Moreover, the corresponding FAP models exhibit limited generalization and ada…
Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Although past methods have achieved good performance on detecting pure machine-generated text, those detectors have poor performance on distinguishing machine-revised t…
Auditory attention detection (AAD) aims to identify the direction of the attended speaker in multi-speaker environments from brain signals, such as Electroencephalography (EEG) signals. However, existing EEG-based AAD methods overlook the spatio-temporal dependencies of EEG signals, limiting their d
The brain-assisted target speaker extraction (TSE) aims to extract the attended speech from mixed speech by utilizing the brain neural activities, for example Electroencephalography (EEG). However, existing models overlook the issue of temporal misalignment between speech and EEG modalities, which h
Vision-language pretraining (VLP) enables open-world generalization beyond predefined labels, a critical capability in surgery due to the diversity of procedures, instruments, and patient anatomies. However, applying VLP to ophthalmic surgery presents unique challenges, including limited vision-lang…
Multi-modal sarcasm detection is crucial for understanding human communications. A key aspect of multi-modal sarcasm detection is the analysis of emotion incongruity. However, the advancement of emotion analysis in video is hindered by the scarcity of labeled datasets, which are limited in both scal…
Despite the progress made by multimodal large language models (MLLMs) in computational pathology, they remain limited by a predominant focus on patch-level analysis, missing essential contextual information at the whole-slide level. The lack of large-scale instruction datasets and the gigapixel scal…
We propose a symbolic generative task description language and a corresponding inference engine that can represent arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models, which rely on large-scale training and implicit neural representations to learn cross-mod…
3D object detection (OD) is a crucial element in scene understanding. However, most existing 3D OD models have been tailored to work with light detection and ranging (LiDAR) and RGB-D point cloud data, leaving their performance on commonly available visual-inertial simultaneous localization and mapp…
In this study, we apply a graph convolutional network (GCN) in attention deficit hyperactivity disorder (ADHD) classification by using multimodal data. Here, multimodal data is integrated to construct a dual graph for leveraging the modality information. Then, a GCN learning model is performed withi…
Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions. Avoiding convergence to these critical points poses a major challenge. This work provides new theoretical insights that help demystify the intricacies of the non-conv…
Existing quality enhancement methods for compressed images focus on aligning the enhancement domain with the raw domain to yield realistic images. However these methods exhibit a pervasive enhancement bias towards the compression domain inadvertently regarding it as more realistic than the raw domai…
Whole Slide Image (WSI) classification is often formulated as a Multiple Instance Learning (MIL) problem. Recently Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However existing methods leverage coarse-grained pathogenetic descriptions for visual repre…
"Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face parsing, and landmark detection). These challenges prohibit low-cost deployment of…
"Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference image or text descriptions; and 3) time-consuming fine-tunin…
Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods primarily rely on supervised annotations, while the application in UAD is limited due…
Deep learning methods have been widely applied in Attention Deficit Hyperactivity Disorder (ADHD) classification in the past decade due to their effective learned features. However, these features are lack of neurobiological meanings and hard to be biomarkers. Here, we proposed an attention auto-enc…
The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency resulting from the application of the mutual nearest neighbo…
The rapid development of neural network dataset distillation in recent years has provided new ideas in many areas such as continuous learning, neural network architecture search and privacy preservation. Dataset distillation is a very effective method to distill large training datasets into small da…
In this work, we consider the problem of matrix sensing over graphs (MSoG). As a general case of matrix completion and matrix sensing problems, the MSoG problem has not been analyzed in the literature and the existing results cannot be directly applied to the MSoG problem. This work provides the fir…
User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities. Such source videos are further compressed and transcoded by media server providers before being distributed to end-users. Because of the flourishing…
Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial sentences from benign ones. However, {the core limitation of previo…
Morphological analysis is an important research issue in the field of natural language processing. In this study, we propose a context-free morphological analysis task, namely word-level prefix/suffix sense detection, which deals with the ambiguity of sense expressed by prefix/suffix. To research th…
The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhance…
In this paper, we focus on the robustness evaluation of Chinese Question Matching (QM) models. Most of the previous work on analyzing robustness issues focus on just one or a few types of artificial adversarial examples. Instead, we argue that a comprehensive evaluation should be conducted on natura…
In this paper, we present DuReader-retrieval, a large-scale Chinese dataset for passage retrieval. DuReader-retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, w…
"End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small text instance usually requires enlarging the whole image, wh…
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important. Conventional methods detect and match tentative local features across the whole images, with heuristic consistency checks to guarantee reliable matches. In this paper, we introduce a no…
Recent work has shown that current text classification models are vulnerable to small adversarial perturbation to inputs, and adversarial training that re-trains the models with the support of adversarial examples is the most popular way to alleviate the impact of the perturbation. However, current…
Underwater positioning is critical to autonomous underwater vehicles (AUVs) for navigation and geo-referencing. The rapid attenuation of the electromagnetic wave in the underwater environment prevents the use of traditional positioning methods such as the Global Positioning System, whereupon acousti
"Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a sing…
Robotic rehabilitation therapy has become an important technology to recover the motor ability of disabled individuals. Clinical studies indicate that involving the active intention of patient into rehabilitation training contributes to promoting the performance of therapies. An adaptive neural coop
Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs). Despite the promising results achieved, the rationale that interprets the behavior of KD has yet remained largely understudied. In this paper, we introduce a novel task-oriente…
Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications. Most methods attempt to develop various region of interest (RoI) operations to concatenate the detection part and the sequence recog…
Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such spurious patterns via post-hoc explanation algorithms which com…
Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter. In this paper, we introduce a novel approach, termed as Self-born Wiring (SeBoW), to learn neural…
Spiking neural network (SNN) is promising but the development has fallen far behind conventional deep neural networks (DNNs) because of difficult training. To resolve the training problem, we analyze the closed-form input-output response of spiking neurons and use the response expression to build ab…
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model. Prior methods achieve this by making the student imitate shallow behaviors, such as soft targets, features, or attention, of the teacher. In this paper, we…
Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages. Considering that most emotions usually have few causes mentioned in their conte…
Attention Deficit Hyperactivity Disorder (ADHD) is a high incidence of neurobehavioral disease in school-age children. Its neurobiological classification is meaningful for clinicians. The existing ADHD classification methods suffer from two problems, i.e., insufficient data and noise disturbance. He…
State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points. By enforcing such representation to be sparse, sparse subspace clustering is guaranteed to produce a subspace-preserving data affinity where…
We present a study of the dynamics and control of a 28-gram quadrotor during the execution of aerobatic maneuvers in the presence of propeller-aerodynamic-coefficient and torque-latency time-variations. First, through a momentum-theory-based analysis of the flow field surrounding the robot during ae…
We introduce Bee <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">+</sup> , a 95-mg four-winged microrobot with improved controllability and open-loop-response characteristics with respect to those exhibited by state-of-the-art two-winged microrobots wit
Text-to-Speech (TTS) systems have been evolving rapidly in recent years. With the great modelling power of deep neural networks, researchers have achieved end-to-end conversion from raw text to speech. It has been shown by various research projects that end-to-end TTS systems are able to generate sp…
The dynamics of quadrotors are affected by time-varying torque latency, which can greatly alter the stability robustness and performance of the closed-loop control schemes employed for flight; this issue is especially relevant during the execution of aerobatic maneuvers such as high-speed multi-flip…
Moving target detection and tracking in reverberation environment is an important yet challenging problem in many applications such as speech, sonar, radar and seismic signal processing. Extending the early work of online subspace and sparse filtering [1], this paper presents an approach based on st…
We present a new experimental method for the generation and real-time implementation of high-speed aerobatic maneuvers, including multiple flips, on a 19-gram autonomous quadrotor. A key element in the proposed approach is the design and experimental tuning of a gain scheduling control strategy in w
Compressed sensing has shown great potential in reducing data acquisition time in magnetic resonance imaging (MRI). Recently, a spread spectrum compressed sensing MRI method modulates an image with a quadratic phase. It performs better than the conventional compressed sensing MRI with variable densi…
By exploiting superimposed signals at relays, physicallayer network coding (PNC) could significantly improve the throughput of wireless communications systems. However, it is challenging to achieve perfect synchronization between superimposed signals at the relay. In this paper, we propose an approa…