38 accepted papers
Large language models (LLMs) frequently generate fluent yet factually inaccurate content, a phenomenon known as hallucination. Recent inference-time approaches aim to improve truthfulness by steering model activations toward semantically meaningful directions. While effective to some extent, these m
Electroencephalogram (EEG) signals have unique individual characteristics and have broad application prospects in identity authentication. At present, person identification (PI) based on EEG using the temporal-spatial-spectral feature extraction framework has achieved remarkable success. However, th…
Existing video-based automatic depression assessment (ADA) approaches frequently achieve video-level depression assessment by aggregating features or predictions of individual frames or equal-length segments within the given video. While their performances have been largely enhanced by recent advanc
Low-light image super-resolution (LLSR) is a challenging task due to the coupled degradation of low resolution and poor illumination. To address this, we propose the Guided Texture and Feature Modulation Network (GTFMN), a novel framework that decouples the LLSR task into two sub-problems: illuminat…
Functional brain network analysis plays an important role in understanding and diagnosing psychiatric disorders. However, current methods struggle with subject variations, impairing the model’s generalization ability to the test set. To address this issue, we propose the Subject Invariance-aware Inv…
Domain shift (the difference between source and target domains) poses a significant challenge in clinical applications, e.g., Diabetic Retinopathy (DR) grading. Despite considering certain clinical requirements, like source data privacy, conventional transfer methods are predominantly model-centered…
Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech dur…
Facial reactions convey crucial emotional information and coordinating interpersonal relationships in human dyadic interactions. While existing Multiple Appropriate Facial Reaction Generation (MAFRG) methods focus on generating multiple reasonable facial reactions, none of these approaches combines…
Equipped with Large Language Models (LLMs), human-centered robots are now capable of performing a wide range of tasks that were previously deemed challenging or unattainable. However, merely completing tasks is insufficient for cognitive robots, who should learn and apply human preferences to future
Despite the impressive text-to-image (T2I) synthesis capabilities of diffusion models, they often struggle to understand compositional relationships between objects and attributes, especially in complex settings. Existing approaches through building compositional architectures or generating difficul…
As an essential vision task, infrared small target detection (IRSTD) has seen significant advancements through deep learning. However, critical limitations in current evaluation protocols impede further progress. First, existing methods rely on fragmented pixel- and target-level specific met…
Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according to a binary Gaussian mixture model (GMM) and a certain fracti…
Predictive modeling of unannotated spatiotemporal data presents inherent challenges, primarily due to the highly entangled visual dynamics in real-world scenes. To tackle these complexities, we introduce a novel insight through Disentangling Deterministic and Probabilistic (DDP) modeling. We note a
Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance. While existing methods address training-inference modality gaps via specialized per-combination models, they introduce high deployment costs by requiring exhaustive mode…
The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, it relies on strong supervision from a considerable amount of labeled training da…
Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance.…
Multimodal representation learning using visual movements from cine magnetic resonance imaging (MRI) and their acoustics has shown great potential to learn shared representation and to predict one modality from another. Here, we propose a new synthesis framework to translate from cine MRI sequences…
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both p(x|y) and p(y). Since the label is inaccessible in the target domain, the conventional adversarial UDA assumes…
In this paper, we focus on the problem of citing sentence generation, which entails generating a short text to capture the salient information in a cited paper and the connection between the citing and cited paper. We present BACO, a BAckground knowledge- and COntent-based framework for citing sente…
AI Safety is a major concern in many deep learning applications such as autonomous driving. Given a trained deep learning model, an important natural problem is how to reliably verify the model's prediction. In this paper, we propose a novel framework --- deep verifier networks (DVN) to detect unrel…
In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training. Considering the inherent conditional and label shifts, we would expect the alignment of p(x|y) and p(y). However, the…
The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk of misclassification which is usually measured by the distance between the prediction and label in a semantic hierarchica…
Reinforcement Learning (RL) has made remarkable achievements, but it still suffers from inadequate exploration strategies, sparse reward signals, and deceptive reward functions. To alleviate these problems, a Population-guided Novelty Search (PNS) parallel learning method is proposed in this paper.…
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discrete labels. However, in many tasks (e.g., medical diagnosis), the labels are discrete and successively distributed. The U…
Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-gr…
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to disentangle the unsupervisely learned relative-pose/rotation and im…
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…
The RNN-Transducer (RNNT) outperforms classic Automatic Speech Recognition (ASR) systems when a large amount of supervised training data is available. For low-resource languages, the RNNT models overfit, and can not directly take advantage of additional large text corpora as in classic ASR systems.W…
Semantic segmentation is a class of methods to classify each pixel in an image into semantic classes, which is critical for autonomous vehicles and surgery systems. Cross-entropy (CE) loss-based deep neural networks (DNN) achieved great success w.r.t. the accuracy-based metrics, e.g., mean Intersect…
Common spatial pattern (CSP) is widely used in motor imagery classification tasks. Classical CSP depends only on spatial filters. To improve its performance, a novel and efficient spatio-temporal filtering strategy is proposed in this paper to extract discriminative features. Common temporal filters…
Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since ps…
This paper targets the task with discrete and periodic class labels (e.g., pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or regression loss is not well matched to this problem as they ignore the periodic nature of the labels and the class similarity, o…
Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization remains an open issue. We systematically summarize the detrimental factors as task-relevant/irrelevant sem…
We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images. We use feature restructuring to exploit the correlations of both inner&inter-set images. Specifically, the residual self-attention can effectively restructure the fe…
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents. To this end, we propose a learning-based approach to generate visually coherent completion given a high-resolution image with missing components. In order to overcome the dif…
This paper targets the problem of image set-based face verification and identification. Unlike traditional single media (an image or video) setting, we encounter a set of heterogeneous contents containing orderless images and videos. The importance of each image is usually considered either equal or…
In this paper, we propose a novel sparse common spatial pattern (CSP) algorithm to optimally select channels of EEG signals. Compared to the traditional CSP, which maximizes the variance of signals in one class and minimizes the variance of signals in the other class, the classification accuracy is…
Internet videos provide a virtually boundless source of audio with a conspicuous lack of localized annotations, presenting an ideal setting for unsupervised methods. With this motivation, we perform an unprecedented exploration into the large-scale discovery of recurring audio events in a diverse co…