Computer Vision and Image Understanding

Article	Citations
Deep 3D human pose estimation: A review	178
Skeleton-based action recognition via spatial and temporal transformer networks	165
Deep learning for deepfakes creation and detection: A survey	161
Pros and cons of GAN evaluation measures: New developments	150
A review of 3D human pose estimation algorithms for markerless motion capture	102
Fake face detection via adaptive manipulation traces extraction network	91
A comprehensive review of past and present image inpainting methods	78
TCLR: Temporal contrastive learning for video representation	74
CUFD: An encoder–decoder network for visible and infrared image fusion based on common and unique feature decomposition	66
High-level prior-based loss functions for medical image segmentation: A survey	53
Single-image deblurring with neural networks: A comparative survey	52
Knowledge distillation for incremental learning in semantic segmentation	51
Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion	43
Multi-focus image fusion approach based on CNP systems in NSCT domain	42
A survey on bias in visual datasets	42
Visual object tracking: A survey	42
SSMTL++: Revisiting self-supervised multi-task learning for video anomaly detection	38
Human action recognition in drone videos using a few aerial training examples	38
MFMAM: Image inpainting via multi-scale feature module with attention module	37
SSDA-YOLO: Semi-supervised domain adaptive YOLO for cross-domain object detection	36
Detection of Face Recognition Adversarial Attacks	35
Learning deep edge prior for image denoising	34
Curriculum self-paced learning for cross-domain object detection	33
The synergy of double attention: Combine sentence-level and word-level attention for image captioning	30
ICycleGAN: Single image dehazing based on iterative dehazing model and CycleGAN	28

Uncertainty-aware consistency regularization for cross-domain semantic segmentation	28
Predicting the future from first person (egocentric) vision: A survey	27
Video Deblurring via Spatiotemporal Pyramid Network and Adversarial Gradient Prior	27
MTRNet++: One-stage mask-based scene text eraser	25
Deep structural information fusion for 3D object detection on LiDAR–camera system	24
Decoupled appearance and motion learning for efficient anomaly detection in surveillance video	24
Detail preserving image denoising with patch-based structure similarity via sparse representation and SVD	24
Ghost Removal via Channel Attention in Exposure Fusion	23
Enhanced discriminative graph convolutional network with adaptive temporal modelling for skeleton-based action recognition	22
Cross-modal distillation for RGB-depth person re-identification	21
Real-time and accurate object detection in compressed video by long short-term feature aggregation	20
Animal pose estimation: A closer look at the state-of-the-art, existing gaps and opportunities	20
Multi-scale attention network for image inpainting	20
Adaptive CNN filter pruning using global importance metric	20
Person re-identification with part prediction alignment	20
Automatic detection and localization of thighbone fractures in X-ray based on improved deep learning method	19
Fully convolutional online tracking	19
Efficient dual attention SlowFast networks for video action recognition	19
A survey on RGB-D datasets	18
Multimodal attention networks for low-level vision-and-language navigation	18
SID: Incremental learning for anchor-free object detection via Selective and Inter-related Distillation	18
Sejong face database: A multi-modal disguise face database	18
Casting a BAIT for offline and online source-free domain adaptation	17
Pruning CNN filters via quantifying the importance of deep visual representations	17
Evaluate and improve the quality of neural style transfer	17
Attentive deep network for blind motion deblurring on dynamic scenes	17
MC-Calib: A generic and robust calibration toolbox for multi-camera systems	17
Task dependent deep LDA pruning of neural networks	16
A data augmentation framework by mining structured features for fake face image detection	16
PS-DeVCEM: Pathology-sensitive deep learning model for video capsule endoscopy based on weakly labeled data	16
Video action detection by learning graph-based spatio-temporal interactions	16
Encoder and decoder network with ResNet-50 and global average feature pooling for local change detection	15
Periocular biometrics and its relevance to partially masked faces: A survey	15
Deep learning-based single image face depth data enhancement	15
AC-VRNN: Attentive Conditional-VRNN for multi-future trajectory prediction	15
Robust real-world point cloud registration by inlier detection	15
Multi-human Fall Detection and Localization in Videos	14
BasicTAD: An astounding RGB-Only baseline for temporal action detection	14
Snow Mask Guided Adaptive Residual Network for Image Snow Removal	14
Embedding group and obstacle information in LSTM networks for human trajectory prediction in crowded scenes	14
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems	14
Context understanding in computer vision: A survey	14
Unifying frame rate and temporal dilations for improved remote pulse detection	14
Spatial location constraint prototype loss for open set recognition	14
Few-shot action recognition with implicit temporal alignment and pair similarity optimization	14
Light-weight shadow detection via GCN-based annotation strategy and knowledge distillation	14
A novel shape matching descriptor for real-time static hand gesture recognition	13
Frame-level refinement networks for skeleton-based gait recognition	13
Comprehensive comparative evaluation of background subtraction algorithms in open sea environments	13
Exploring the differences in adversarial robustness between ViT- and CNN-based models using novel metrics	13

Lightweight adaptive weighted network for single image super-resolution	12
Facial landmarks localization using cascaded neural networks	12
Multi-modal semantic image segmentation	12
A multi-view-CNN framework for deep representation learning in image classification	11
Attention-induced semantic and boundary interaction network for camouflaged object detection	11
Single image rain removal via multi-module deep grid network	11
MTCD: Cataract detection via near infrared eye images	11
Physics-based shading reconstruction for intrinsic image decomposition	11
LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR	10
HSGAN: Reducing mode collapse in GANs by the latent code distance of homogeneous samples	10
Learning to locate for fine-grained image recognition	10
Unsupervised sound localization via iterative contrastive learning	10
BacklitNet: A dataset and network for backlit image enhancement	10
Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts	10
Image retrieval with mixed initiative and multimodal feedback	10
Facial landmark points detection using knowledge distillation-based neural networks	10
α-EGAN:	10
Detecting abnormality with separated foreground and background: Mutual Generative Adversarial Networks for video abnormal event detection	10
Accurate MR image super-resolution via lightweight lateral inhibition network	10
Target-aware and spatial-spectral discriminant feature joint correlation filters for hyperspectral video object tracking	10
Self-knowledge distillation via dropout	9
Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation	9
A semantically driven self-supervised algorithm for detecting anomalies in image sets	9
MAEDAY: MAE for few- and zero-shot AnomalY-Detection	9
An efficient framework for few-shot skeleton-based temporal action segmentation	9
Rolling-Shutter-stereo-aware motion estimation and image correction	9
Monocular 3D multi-person pose estimation via predicting factorized correction factors	9
Human skeletons and change detection for efficient violence detection in surveillance videos	9
Multi-person 3D pose estimation from a single image captured by a fisheye camera	8
Low-light image enhancement by deep learning network for improved illumination map	8
Video scene parsing: An overview of deep learning methods and datasets	8
Learning representational invariances for data-efficient action recognition	8
Zero-shot sketch-based image retrieval with structure-aware asymmetric disentanglement	8
Adversarial feature distribution alignment for semi-supervised learning	8
Video frame interpolation via down–up scale generative adversarial networks	8
Multi-perspective cross-class domain adaptation for open logo detection	8
Model-image registration of a building’s facade based on dense semantic segmentation	8
Weakly supervised fine-grained image classification via two-level attention activation model	8
Learning transformer-based attention region with multiple scales for occluded person re-identification	8
When CNNs meet random RNNs: Towards multi-level analysis for RGB-D object and scene recognition	8
Robust detection of dehazed images via dual-stream CNNs with adaptive feature fusion	8
Anti-jamming heart rate estimation using a spatial–temporal fusion network	8
Self-attentive 3D human pose and shape estimation from videos	8
MECCANO: A multimodal egocentric dataset for humans behavior understanding in the industrial-like domain	8
Diff attention: A novel attention scheme for person re-identification	8
Weakly supervised instance segmentation using multi-prior fusion	8
Video captioning: A comparative review of where we are and which could be the route	7
Action Capsules: Human skeleton action recognition	7
Reliable shot identification for complex event detection via visual-semantic embedding	7
E-ProSRNet: An enhanced progressive single image super-resolution approach	7
Dissected 3D CNNs: Temporal skip connections for efficient online video processing	7
SCA-Net: Spatial and channel attention-based network for 3D point clouds	7
Learning to teach and learn for semi-supervised few-shot image classification	7
Balanced softmax cross-entropy for incremental learning with and without memory	7
TMF: Temporal Motion and Fusion for action recognition	7
Graph Convolutional Networks based on manifold learning for semi-supervised image classification	7
Open cross-domain visual search	7
Infrared and visible image fusion via mutual information maximization	7
Anchor pruning for object detection	7
3D semantic segmentation based on spatial-aware convolution and shape completion for augmented reality applications	7
A comparison of methods for 3D scene shape retrieval	7
STURE: Spatial–Temporal Mutual Representation Learning for robust data association in online multi-object tracking	7
Infrared and visible image fusion using a guiding network to leverage perceptual similarity	7
FIFNET: A convolutional neural network for motion-based multiframe super-resolution using fusion of interpolated frames	7
Adaptive Capsule Network	7
DSDNet: Toward single image deraining with self-paced curricular dual stimulations	7
Deducing health cues from biometric data	7
FRIDA — Generative feature replay for incremental domain adaptation	6
Pointly-supervised scene parsing with uncertainty mixture	6
Exploiting multimodal synthetic data for egocentric human-object interaction detection in an industrial scenario	6
Pick-Object-Attack: Type-specific adversarial attack for object detection	6
SAPS: Self-Attentive Pathway Search for weakly-supervised action localization with background-action augmentation	6
Plug-and-Play video super-resolution using edge-preserving filtering	6
Fine-grained facial landmark detection exploiting intermediate feature representations	6
Feature preserving 3D mesh denoising with a Dense Local Graph Neural Network	6
Single image super-resolution via hybrid resolution NSST prediction	6
MetaVD: A Meta Video Dataset for enhancing human action recognition datasets	6
Unsupervised video anomaly detection based on multi-timescale trajectory prediction	6
Camouflaged object detection via Neighbor Connection and Hierarchical Information Transfer	6
On the exact recovery conditions of 3D human motion from 2D landmark motion with sparse articulated motion	6

Are 3D convolutional networks inherently biased towards appearance?	6
An asymmetrical-structure auto-encoder for unsupervised representation learning of skeleton sequences	6
Dynamic mode decomposition via convolutional autoencoders for dynamics modeling in videos	6
M2FINet: Modality-specific and Modality-shared Features Interaction Network for RGB-IR Person Re-Identification	6
Stacked Capsule Graph Autoencoders for geometry-aware 3D head pose estimation	6
Semantic segmentation from remote sensor data and the exploitation of latent learning for classification of auxiliary tasks	6
DenseNet-CTC: An end-to-end RNN-free architecture for context-free string recognition	6
SIFNet: Free-form image inpainting using color split-inpaint-fuse approach	6
Unsupervised face frontalization using disentangled representation-learning CycleGAN	6
One-class anomaly detection via novelty normalization	6
SnapshotNet: Self-supervised feature learning for point cloud data segmentation using minimal labeled data	6
AWDMC-Net: Classification of Adversarial Weather Degraded Multiclass scenes using a Convolution Neural Network	6
Adaptive feature denoising based deep convolutional network for single image super-resolution	6
The MSR-Video to Text dataset with clean annotations	6
Prediction and Description of Near-Future Activities in Video	6