Camouflaged object detection via context-aware cross-level fusion

G Chen, SJ Liu, YJ Sun, GP Ji, YF Wu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
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 …

Spatiotemporal decouple-and-squeeze contrastive learning for semisupervised skeleton-based action recognition

B Xu, X Shu, J Zhang, G Dai… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Contrastive learning has been successfully leveraged to learn action representations for
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

M Lin, G Yang, H Zhang - IEEE Transactions on Image …, 2022‏ - ieeexplore.ieee.org
As an important yet challenging task in Earth observation, change detection (CD) is
undergoing a technological revolution, given the broadening application of deep learning …

On the use of deep learning for video classification

A Ur Rehman, SB Belhaouari, MA Kabir, A Khan - Applied Sciences, 2023‏ - mdpi.com
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 …

Temporal decoupling graph convolutional network for skeleton-based gesture recognition

J Liu, X Wang, C Wang, Y Gao… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Skeleton-based gesture recognition methods have achieved high success using Graph
Convolutional Network (GCN), which commonly uses an adjacency matrix to model the …

Multiscale low-light image enhancement network with illumination constraint

GD Fan, B Fan, M Gan, GY Chen… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
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 …

Spatio-temporal adaptive convolution and bidirectional motion difference fusion for video action recognition

L Li, M Tang, Z Yang, J Hu, M Zhao - Expert Systems with Applications, 2024‏ - Elsevier
Motion and spatio-temporal features are crucial and complementary in action recognition.
Many traditional methods focus on forward motion features but neglect the bidirectional …

HRTransNet: HRFormer-driven two-modality salient object detection

B Tang, Z Liu, Y Tan, Q He - … on Circuits and Systems for Video …, 2022‏ - ieeexplore.ieee.org
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation
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

H Yar, T Hussain, M Agarwal, ZA Khan… - … on Image Processing, 2022‏ - ieeexplore.ieee.org
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 …

Fractional Fourier image transformer for multimodal remote sensing data classification

X Zhao, M Zhang, R Tao, W Li, W Liao… - … on Neural Networks …, 2022‏ - ieeexplore.ieee.org
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 …