Related papers: Frequency-Spatial Entanglement Learning for Camouf…
Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without…
The self-attention mechanism, which equips with a strong capability of modeling long-range dependencies, is one of the extensively used techniques in the sequential recommendation field. However, many recent studies represent that current…
The scene text removal (STR) task aims to remove text regions and recover the background smoothly in images for private information protection. Most existing STR methods adopt encoder-decoder-based CNNs, with direct copies of the features…
Quantum measurements are inherently noisy, hindering reliable entanglement detection and limiting the scalability of quantum technologies. While error mitigation and correction strategies exist, they often impose prohibitive resource…
Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation…
Environment shifts and conflicts present significant challenges for learning-based sound event localization and detection (SELD) methods. SELD systems, when trained in particular acoustic settings, often show restricted generalization…
The rapid evolution of deep generative models poses a critical challenge to deepfake detection, as detectors trained on forgery-specific artifacts often suffer significant performance degradation when encountering unseen forgeries. While…
Federated edge learning (FEEL) is envisioned as a promising paradigm to achieve privacy-preserving distributed learning. However, it consumes excessive learning time due to the existence of straggler devices. In this paper, a novel…
Hyperentanglement, defined as the simultaneous entanglement in several independent degrees of freedom (DOFs) of a quantum system, is a fascinating resource in quantum information processing with its outstanding merits. Here we propose…
EEG-based Emotion recognition holds significant promise for applications in human-computer interaction, medicine, and neuroscience. While deep learning has shown potential in this field, current approaches usually rely on large-scale…
Advances in deepfake research have led to the creation of almost perfect manipulations undetectable by human eyes and some deepfakes detection tools. Recently, several techniques have been proposed to differentiate deepfakes from realistic…
Federated Continual Learning (FCL) has emerged as a robust solution for collaborative model training in dynamic environments, where data samples are continuously generated and distributed across multiple devices. This survey provides a…
This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval.…
Semantic segmentation of electron microscopy (EM) images of biological samples remains a challenge in the life sciences. EM data captures details of biological structures, sometimes with such complexity that even human observers can find it…
Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a…
Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing…
Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance.…
We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…
Deep learning solutions of the salient object detection problem have achieved great results in recent years. The majority of these models are based on encoders and decoders, with a different multi-feature combination. In this paper, we show…
Color image steganography based on deep learning is the art of hiding information in the color image. Among them, image hiding steganography(hiding image with image) has attracted much attention in recent years because of its great…