Computer Vision and Pattern Recognition papers

Pofolia’s corpus holds 99 papers from Computer Vision and Pattern Recognition (2002–2026), each with a short summary. Below, the 20 most-cited, then the most recently added.

At a glance

• Most cited: Deep Residual Learning for Image Recognition (2016, 223,583 citations).
• The 20 papers listed have 910,043 citations between them.
• 3 of the 3 with a known journal quartile appeared in a Q1 journal.
• 2 have a free full text (open access).
• Most frequent journals: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 IEEE/CVF International Conference on Computer Vision (ICCV), arXiv (Cornell University).
• Published between 2014 and 2024.

Most cited

Ranked by citation count. Because citations accumulate over time, this list naturally leans towards work published a few years ago; for where the field is now, see “recently added”. How to read the signals

• Deep Residual Learning for Image Recognition

  2016 · 223,583 citations

  A new residual learning framework enables training significantly deeper neural networks, achieving state-of-the-art image recognition performance.

  Go to source →

• ImageNet classification with deep convolutional neural networks

  Communications of the ACM · 2017 · Q1 · SJR 1.00 · FWCI 4435.36 · 75,715 citations · Open access

  A deep convolutional neural network achieved state-of-the-art ImageNet classification, reducing top-5 error rates to 17.0% in 2010 and a winning 15.3% in 2012.

  Go to source →

• Very Deep Convolutional Networks for Large-Scale Image Recognition

  arXiv (Cornell University) · 2014 · 75,542 citations · Open access

  Increasing convolutional network depth to 16-19 weight layers, using small 3x3 filters, significantly improves accuracy in large-scale image recognition over prior configurations.

  Go to source →

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · Q1 · SJR 4.00 · FWCI 1672.08 · 54,589 citations

  This paper introduces a Region Proposal Network (RPN) that integrates seamlessly with object detection networks, enabling real-time performance by generating region proposals at nearly no computational cost.

  Go to source →

• Going deeper with convolutions

  2015 · 46,948 citations

  A novel deep convolutional neural network architecture, Inception, has set a new state-of-the-art for image classification and detection on the ILSVRC14 challenge.

  Go to source →

• Densely Connected Convolutional Networks

  2017 · 44,970 citations

  DenseNets introduce a new convolutional network architecture where each layer connects to every other layer in a feed-forward manner, significantly increasing the number of direct connections compared to traditional networks.

  Go to source →

• Fully convolutional networks for semantic segmentation

  2015 · 37,045 citations

  This paper introduces fully convolutional networks (FCNs) that can perform semantic segmentation on images of any size, achieving state-of-the-art results with efficient inference.

  Go to source →

• Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  2014 · 31,870 citations

  A new algorithm, R-CNN, significantly boosts object detection accuracy by over 30% on the PASCAL VOC 2012 dataset, achieving a 53.3% mAP.

  Go to source →

• Rethinking the Inception Architecture for Computer Vision

  2016 · 31,095 citations

  A new network design, Inception, efficiently scales up convolutional networks by factorizing convolutions and using aggressive regularization, achieving state-of-the-art results on the ILSVRC 2012 classification challenge.

  Go to source →

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

  2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 30,585 citations

  The Swin Transformer introduces a hierarchical architecture with shifted windows, enabling efficient self-attention computation for general-purpose computer vision tasks.

  Go to source →

• Mask R-CNN

  2017 · 28,989 citations

  Mask R-CNN is a new framework that efficiently detects objects and generates high-quality segmentation masks for each instance in an image, extending Faster R-CNN with a mask prediction branch.

  Go to source →

• Feature Pyramid Networks for Object Detection

  2017 · 28,919 citations

  Feature Pyramid Networks (FPNs) efficiently construct a rich multi-scale feature representation from deep convolutional networks with marginal computational cost.

  Go to source →

• Squeeze-and-Excitation Networks

  2018 · 28,761 citations

  A novel 'Squeeze-and-Excitation' (SE) block adaptively recalibrates channel-wise feature responses by modeling interdependencies between channels, significantly improving deep learning model performance.

  Go to source →

• Fast R-CNN

  2015 · 28,041 citations

  Fast R-CNN is a novel object detection method that significantly improves training and testing speeds while increasing accuracy by efficiently classifying object proposals using deep convolutional networks.

  Go to source →

• Focal Loss for Dense Object Detection

  2017 · 26,050 citations

  A novel 'Focal Loss' function effectively addresses the extreme class imbalance in training dense object detectors, enabling them to surpass the accuracy of slower, two-stage detectors while maintaining speed.

  Go to source →

• MobileNetV2: Inverted Residuals and Linear Bottlenecks

  2018 · 25,715 citations

  MobileNetV2 introduces a novel mobile architecture featuring inverted residuals and linear bottlenecks, significantly improving state-of-the-art performance on mobile tasks like image classification, object detection, and semantic segmentation across various model sizes.

  Go to source →

• Learning Multiple Layers of Features from Tiny Images

  2024 · FWCI 670.28 · 25,502 citations

  Researchers developed a multi-layer generative model that learns meaningful visual features from millions of tiny web images, mimicking aspects of the human visual cortex.

  Go to source →

• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · Q1 · SJR 4.00 · FWCI 632.10 · 22,241 citations

  DeepLab introduces 'atrous convolution' to control feature resolution and enlarge filter receptive fields in deep networks, enabling better semantic image segmentation.

  Go to source →

• Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

  2017 · 22,010 citations

  This paper introduces a novel method for image-to-image translation that does not require paired training data, a common limitation in existing techniques.

  Go to source →

• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

  2017 · 21,873 citations

  Grad-CAM generates visual explanations for Convolutional Neural Network (CNN) decisions by highlighting important image regions, making complex models more transparent.

  Go to source →

Recently added

• Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection

  International Journal of Computer Vision · 2026 · Q1 · SJR 3.00 · 1 citations · Open access

  The Constellation dataset, comprising 13K images from high-altitude urban cameras, enables benchmarking object detection for privacy-preserving edge processing, revealing a 10% lower AP for small pedestrians vs. vehicles.

  Go to source →

• Performance analysis and deployment considerations of post-quantum cryptography for consumer Electronics

  Scientific Reports · 2026 · Q1 · FWCI 11.11 · 3 citations · Open access

  Lattice-based post-quantum cryptography (PQC) schemes, specifically ML-KEM and ML-DSA, offer a promising balance of execution speed and object size for gateway-class consumer electronics, outperforming RSA/ECC baselines in key encapsulation and digital signature tasks.

  Go to source →

• Causal Cohesion and Story Coherence

  2026 · 360 citations

  Children's ability to understand and remember stories hinges on the causal links between events, with more cohesive stories leading to easier comprehension and memory representation.

  Go to source →

• CP-Diffusion: Conditional Prompt-Based Diffusion Models for Video Generation

  ACM Transactions on Multimedia Computing Communications and Applications · 2026 · Q1 · FWCI 11.61 · 3 citations

  CP-Diffusion introduces a few-shot learning approach using a Multi-Head Temporal Attention (MHTA) module for motion customization in text-to-video diffusion models, significantly reducing computational needs while improving motion quality.

  Go to source →

• Abstract Functional Language Logic: A Competitive Mixture of Experts Architecture for Paradox-Free Reasoning and Adaptive Intelligence

  Zenodo (CERN European Organization for Nuclear Research) · 2025 · FWCI 44.00 · 595 citations

  This paper introduces a Competitive Mixture of Experts (CMoE) architecture based on Functional Language Logic (FLL) that replaces probabilistic LLM reasoning with mathematical functional approximators for paradox-free, efficient deduction.

  Go to source →

• Reference-Vector Removed Product Quantization for Approximate Nearest Neighbor Search

  Applied Sciences · 2025 · Q2 · FWCI 0.46 · 1 citations

  Reference-Vector Removed Product Quantization (RvRPQ) improves approximate nearest neighbor (ANN) search accuracy by subtracting encoded reference-vectors from database vectors, yielding residuals that are then quantized.

  Go to source →

• VM-UNet: Vision Mamba UNet for Medical Image Segmentation

  ACM Transactions on Multimedia Computing Communications and Applications · 2025 · Q1 · FWCI 226.04 · 541 citations

  VM-UNet, a novel U-shaped architecture for medical image segmentation, leverages State Space Models (SSMs) like Mamba to achieve linear computational complexity and effective long-range modeling, outperforming previous CNN and Transformer models.

  Go to source →

• V0.1IC

  Zenodo (CERN European Organization for Nuclear Research) · 2025 · 499 citations

  A new deep learning framework, Hamming Cube, jointly learns compact binary codes and continuous embeddings while preserving Hamming distance structure.

  Go to source →

Journals in this field

The journals that publish most of this field’s papers. Quartile (Q1–Q4), SJR and h-index are from SCImago Journal Rank; “in this field” is how many of the journal’s pooled papers belong here. What is a Q1 journal? · What is the h-index?

Every journal in Computer Vision and Pattern Recognition (Q1–Q4) →

Other subfields in Computer Science

• Computer Networks and Communications
• Computer Science Applications
• Computer Graphics and Computer-Aided Design
• Information Systems
• Hardware and Architecture
• Computational Theory and Mathematics
• Human-Computer Interaction
• Signal Processing
• Artificial Intelligence
• Software

All subfields of Computer Science →

← All fields