OOIR: Observatory of International Research

Papers

(The TQCC of Computational Visual Media is 7. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-11-01 to 2024-11-01.)

Article	Citations
Attention mechanisms in computer vision: A survey	1033
PCT: Point cloud transformer	927
PVT v2: Improved baselines with Pyramid Vision Transformer	817
Visual attention network	229
RGB-D salient object detection: A survey	171
A survey of visual analytics techniques for machine learning	147
Transformers in computational visual media: A survey	80
High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review	44
EfficientPose: Efficient human pose estimation with neural architecture search	36
A survey on deep learning-based Monte Carlo denoising	35
Light field salient object detection: A review and benchmark	34
A survey of urban visual analytics: Advances and future directions	28
DualFace: Two-stage drawing guidance for freehand portrait sketching	28
Learning conditional photometric stereo with high-resolution features	22
Deep image synthesis from intuitive user input: A review and perspectives	20
Joint specular highlight detection and removal in single images via Unet-Transformer	18
Inversion-free geometric mapping construction: A survey	18
Improved fuzzy clustering for image segmentation based on a low-rank prior	18
An end-to-end convolutional network for joint detecting and denoising adversarial perturbations in vehicle classification	17
Foveated rendering: A state-of-the-art survey	16
Image smoothing based on global sparsity decomposition and a variable parameter	16
Low and non-uniform illumination color image enhancement using weighted guided image filtering	16
Scene text removal via cascaded text stroke detection and erasing	16
Image resizing by reconstruction from deep features	15
Progressive edge-sensing dynamic scene deblurring	14

Reference-guided structure-aware deep sketch colorization for cartoons	14
Learning to assess visual aesthetics of food images	14
Towards uniform point distribution in feature-preserving point cloud filtering	13
D2ANet: Difference-aware attention network for multi-level change detection from satellite imagery	12
Jittor-GAN: A fast-training generative adversarial network model zoo based on Jittor	12
Joint 3D facial shape reconstruction and texture completion from a single image	12
Multi-modal visual tracking: Review and experimental comparison	11
ARM3D: Attention-based relation module for indoor 3D object detection	11
Mask-aware photorealistic facial attribute manipulation	11
Facial optical flow estimation via neural non-rigid registration	11
ClusterSLAM: A SLAM backend for simultaneous rigid body clustering and motion estimation	10
Multi-scale joint feature network for micro-expression recognition	10
Unsupervised random forest for affinity estimation	10
Can attention enable MLPs to catch up with CNNs?	10
Temporally consistent video colorization with deep feature propagation and self-regularization learning	9
Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module	9
WGI-Net: A weighted group integration network for RGB-D salient object detection	9
Erroneous pixel prediction for semantic image segmentation	9
Real-time per-pixel focusing method for light field rendering	8
Point cloud completion via structured feature maps using a feedback network	8
Trajectory distributions: A new description of movement for trajectory prediction	8
Semi-supervised 3D shape segmentation with multilevel consistency and part substitution	8
Joint regression and learning from pairwise rankings for personalized image aesthetic assessment	7
NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits	7
Foundation models meet visualizations: Challenges and opportunities	7
Neighborhood co-occurrence modeling in 3D point cloud segmentation	7
Light field super-resolution using complementary-view feature attention	7
Message from the Editor-in-Chief	7
3D face recognition: A comprehensive survey in 2022	7