Camouflaged object detection via context-aware cross-level fusion
Camouflaged object detection (COD) aims to identify the objects that conceal themselves in
natural scenes. Accurate COD suffers from a number of challenges associated with low …
natural scenes. Accurate COD suffers from a number of challenges associated with low …
Spatiotemporal decouple-and-squeeze contrastive learning for semisupervised skeleton-based action recognition
Contrastive learning has been successfully leveraged to learn action representations for
addressing the problem of semisupervised skeleton-based action recognition. However …
addressing the problem of semisupervised skeleton-based action recognition. However …
Transition is a process: Pair-to-video change detection networks for very high resolution remote sensing images
As an important yet challenging task in Earth observation, change detection (CD) is
undergoing a technological revolution, given the broadening application of deep learning …
undergoing a technological revolution, given the broadening application of deep learning …
On the use of deep learning for video classification
The video classification task has gained significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …
the topic has gained more attention after the emergence of deep learning models as a …
Temporal decoupling graph convolutional network for skeleton-based gesture recognition
Skeleton-based gesture recognition methods have achieved high success using Graph
Convolutional Network (GCN), which commonly uses an adjacency matrix to model the …
Convolutional Network (GCN), which commonly uses an adjacency matrix to model the …
Multiscale low-light image enhancement network with illumination constraint
Images captured under low-light environments typically have poor visibility, affecting many
advanced computer vision tasks. In recent years, there have been some low-light image …
advanced computer vision tasks. In recent years, there have been some low-light image …
Spatio-temporal adaptive convolution and bidirectional motion difference fusion for video action recognition
Motion and spatio-temporal features are crucial and complementary in action recognition.
Many traditional methods focus on forward motion features but neglect the bidirectional …
Many traditional methods focus on forward motion features but neglect the bidirectional …
HRTransNet: HRFormer-driven two-modality salient object detection
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation
and share global receptive fields. It is friendly towards salient object detection (SOD) in …
and share global receptive fields. It is friendly towards salient object detection (SOD) in …
Optimized dual fire attention network and medium-scale fire classification benchmark
Vision-based fire detection systems have been significantly improved by deep models;
however, higher numbers of false alarms and a slow inference speed still hinder their …
however, higher numbers of false alarms and a slow inference speed still hinder their …
Fractional Fourier image transformer for multimodal remote sensing data classification
With the recent development of the joint classification of hyperspectral image (HSI) and light
detection and ranging (LiDAR) data, deep learning methods have achieved promising …
detection and ranging (LiDAR) data, deep learning methods have achieved promising …