OOIR: Observatory of International Research

Papers

(The H4-Index of Computer Vision and Image Understanding is 25. 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 2021-04-01 to 2025-04-01.)

Article	Citations
Semantic-preserved point-based human avatar	243
Rebalanced supervised contrastive learning with prototypes for long-tailed visual recognition	216
Fake News Detection Based on BERT Multi-domain and Multi-modal Fusion Network	208
Incremental few-shot instance segmentation via feature enhancement and prototype calibration	191
A multi-modal explainability approach for human-aware robots in multi-party conversation	128
Luminance prior guided Low-Light 4C catenary image enhancement	96
Robust Teacher: Self-correcting pseudo-label-guided semi-supervised learning for object detection	83
Target-aware and spatial-spectral discriminant feature joint correlation filters for hyperspectral video object tracking	69
Seam estimation based on dense matching for parallax-tolerant image stitching	67
Dual stage semantic information based generative adversarial network for image super-resolution	66
Multi-Scale Adaptive Skeleton Transformer for action recognition	61
Exploring using jigsaw puzzles for out-of-distribution detection	59
PMGNet: Disentanglement and entanglement benefit mutually for compositional zero-shot learning	55
Spatial attention for human-centric visual understanding: An Information Bottleneck method	47
MDC-Net: Multi-domain constrained kernel estimation network for blind image super resolution	46
Deep video compression based on Long-range Temporal Context Learning	43
Static graph convolution with learned temporal and channel-wise graph topology generation for skeleton-based action recognition	41
RFCNet: Enhancing urban segmentation using regularization, fusion, and completion	32
3D scene generation for zero-shot learning using ChatGPT guided language prompts	32
An egocentric video and eye-tracking dataset for visual search in convenience stores	30
RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving	29
Local optimization cropping and boundary enhancement for end-to-end weakly-supervised segmentation network	28
UATST: Towards unpaired arbitrary text-guided style transfer with cross-space modulation	28
Trimap-guided feature mining and fusion network for natural image matting	26
Adaptive gradients and weight projection based on quantized neural networks for efficient image classification	26