相关论文: Quality-Aware Robust Multi-View Clustering for Het…

Certifying neural network robustness against adversarial examples is challenging, as formal guarantees often require solving non-convex problems. Hence, incomplete verifiers are widely used because they scale efficiently and substantially…

Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases. The tasks of knowledge retrieval and answer generation tasks both necessitate…

A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with the setting where…

Multimodal fake news detection aims to automatically identify real or fake news, thereby mitigating the adverse effects caused by such misinformation. Although prevailing approaches have demonstrated their effectiveness, challenges persist…

Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original…

Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient…

With the representation learning capability of the deep learning models, deep embedded multi-view clustering (MVC) achieves impressive performance in many scenarios and has become increasingly popular in recent years. Although great…

Fine Grained Visual Categorization (FGVC) remains a challenging task in computer vision due to subtle inter class differences and fragile feature representations. Existing methods struggle in fine grained scenarios, especially when labeled…

The rise of deepfake technologies has posed significant challenges to privacy, security, and information integrity, particularly in audio and multimedia content. This paper introduces a Quantum-Trained Convolutional Neural Network (QT-CNN)…

Clustering is a representative unsupervised method widely applied in multi-modal and multi-view scenarios. Multiple kernel clustering (MKC) aims to group data by integrating complementary information from base kernels. As a representative,…

Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spatiotemporal perception} and \textit{auxiliary contextual…

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

Multi-relational graph clustering has demonstrated remarkable success in uncovering underlying patterns in complex networks. Representative methods manage to align different views motivated by advances in contrastive learning. Our empirical…

Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The…

Millimeter-wave (mmWave) radar has emerged as a compact and powerful sensing modality for advanced perception tasks that leverage machine learning. It is particularly effective in scenarios where vision-based sensors fail to capture…

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge…

Multi-view clustering has been empirically shown to improve learning performance by leveraging the inherent complementary information across multiple views of data. However, in real-world scenarios, collecting strictly aligned views is…

Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem. Among the existing methods, Low-Rank…