-
Article
Open AccessPublisher Correction: GOSS: towards generalized open-set semantic segmentation
-
Article
Open AccessGOSS: towards generalized open-set semantic segmentation
In this paper, we extend Open-set Semantic Segmentation (OSS) into a new image segmentation task called Generalized Open-set Semantic Segmentation (GOSS). Previously, with well-known OSS, the intelligent agent...
-
Article
Poincaré Kernels for Hyperbolic Representations
Embedding data in hyperbolic spaces has proven beneficial for many advanced machine learning applications. However, working in hyperbolic spaces is not without difficulties as a result of its curved geometry (e.g
-
Article
Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification
Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to its potential to facilitate person retrieval acros...
-
Article
A DNA image encryption based on a new hyperchaotic system
In this paper, a new four-dimensional hyperchaotic system that has better unpredictability, more complex dynamic behavior, and a larger key space is proposed. The initial chaos value is calculated by using the...
-
Article
A survey of image encryption algorithms based on chaotic system
Many researchers have devoted themselves to studying image encryption based on chaotic system and have made significant strides in research in recent decades. This paper first combs and summarizes the developm...
-
Article
A block image encryption algorithm based on a hyperchaotic system and generative adversarial networks
To address the problems of existing image encryption algorithms based on chaotic systems, such as the weak resistance to attack, the unstable performance of the chaotic system, and the small size of the key sp...
-
Chapter and Conference Paper
Learning Instance and Task-Aware Dynamic Kernels for Few-Shot Learning
Learning and generalizing to novel concepts with few samples (Few-Shot Learning) is still an essential challenge to real-world applications. A principle way of achieving few-shot learning is to realize a model...
-
Chapter and Conference Paper
Blind Image Decomposition
We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components i...
-
Chapter and Conference Paper
Channel Recurrent Attention Networks for Video Pedestrian Retrieval
Full attention, which generates an attention value per element of the input feature maps, has been successfully demonstrated to be beneficial in visual tasks. In this work, we propose a fully attentional netwo...
-
Chapter and Conference Paper
An Objects Detection Framework in UAV Videos
Unmanned aerial vehicles equipped with surveillance system have begun to play an increasingly important role in recent years, which has provided a wealth of valuable information for national security and defen...