the open
    research
    Contribute

    2026 edition · Top 85

    Computer vision & multimodal

    Seeing machines: recognition, detection, segmentation, self-supervised visual features and vision-language models.

    Computer vision: 41 · Multimodal & vision-language: 23 · Self-supervised learning: 21 · N = 85, scaled from 210 candidates.

    0 of 85 of this page's 85 read · saved in this browser only

    1. 1
      Computer vision2012

      ImageNet Classification with Deep Convolutional Neural Networks

      Alex Krizhevsky · 132,655 citations · Semantic Scholar

      AwardEditor's note
    2. 2
      Computer vision2015 · published 2016

      Deep Residual Learning for Image Recognition

      Kaiming He · 242,121 citations · Papers With Code

      AwardEditor's note
    3. 3
      Computer vision2015 · published 2016

      You Only Look Once: Unified, Real-Time Object Detection

      Joseph Redmon · 53,721 citations · OpenAlex

      AwardEditor's note
    4. 4
      Computer vision2009

      ImageNet: A Large-Scale Hierarchical Image Database

      Jia Deng · 78,060 citations · Semantic Scholar

      AwardEditor's note
    5. 5
      Self-supervised learning2013

      Distributed Representations of Words and Phrases and their Compositionality

      Tomas Mikolov · 35,814 citations · Papers With Code

      AwardEditor's note
    6. 6
      Computer vision2015

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

      Shaoqing Ren · 76,424 citations · Papers With Code

      Award
    7. 7
      Computer vision2013 · published 2014

      Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

      Ross Girshick · 32,680 citations · OpenAlex

      AwardEditor's note
    8. 8
      Computer vision2014 · published 2015

      Fully Convolutional Networks for Semantic Segmentation

      Jonathan Long · 43,178 citations · Papers With Code

      Award
    9. 9
      Computer vision2014 · published 2015

      Going Deeper with Convolutions

      Christian Szegedy · 48,226 citations · Papers With Code

      Award
    10. 10
      Multimodal & vision-language2021

      Learning Transferable Visual Models From Natural Language Supervision

      Alec Radford · 57,689 citations · Papers With Code

      Editor's note
    11. 11
      Computer vision2020 · published 2021

      An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

      Alexey Dosovitskiy · 71,638 citations · Papers With Code

      Editor's note
    12. 12
      Self-supervised learning2020

      A Simple Framework for Contrastive Learning of Visual Representations

      Ting Chen · 26,701 citations · Papers With Code

      Editor's note
    13. 13
      Computer vision2014

      Microsoft COCO: Common Objects in Context

      Tsung-Yi Lin · 56,284 citations · Papers With Code

      Award
    14. 14
      Multimodal & vision-language2023

      Visual Instruction Tuning

      Haotian Liu · 11,545 citations · Papers With Code

      Editor's note
    15. 15
      Computer vision2004

      Distinctive Image Features from Scale-Invariant Keypoints

      David G. Lowe · 55,667 citations · OpenAlex

      Editor's note
    16. 16
      Self-supervised learning2006

      Reducing the Dimensionality of Data with Neural Networks

      Geoffrey E. Hinton · 20,937 citations · OpenAlex

      Editor's note
    17. 17
      Self-supervised learning2021 · published 2022

      Masked Autoencoders Are Scalable Vision Learners

      Kaiming He · 13,175 citations · Papers With Code

      Editor's note
    18. 18
      Computer vision2023

      Segment Anything

      Alexander Kirillov · 16,249 citations · Papers With Code

      Editor's note
    19. 19
      Computer vision2001

      Rapid Object Detection using a Boosted Cascade of Simple Features

      Paul Viola · 18,231 citations · OpenAlex

      Award
    20. 20
      Multimodal & vision-language2022

      Flamingo: a Visual Language Model for Few-Shot Learning

      Jean-Baptiste Alayrac · 6,788 citations · Papers With Code

      Editor's note
    21. 21
      Computer vision2005

      Histograms of Oriented Gradients for Human Detection

      Navneet Dalal · 36,274 citations · Semantic Scholar

      Award
    22. 22
      Computer vision2017

      Mask R-CNN

      Kaiming He · 33,439 citations · Papers With Code

    23. 23
      Computer vision2014 · published 2015

      Very Deep Convolutional Networks for Large-Scale Image Recognition

      Karen Simonyan · 114,859 citations · Papers With Code

    24. 24
      Self-supervised learning2018

      Representation Learning with Contrastive Predictive Coding

      Aaron van den Oord · 14,862 citations · Papers With Code

      Editor's note
    25. 25
      Multimodal & vision-language2023

      BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

      Junnan Li · 9,535 citations · Papers With Code

    26. 26
      Multimodal & vision-language2015

      VQA: Visual Question Answering

      Stanislaw Antol · 6,770 citations · Papers With Code

      Editor's note
    27. 27
      Multimodal & vision-language2015

      Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

      Kelvin Xu · 10,973 citations · Papers With Code

    28. 28
      Self-supervised learning2021

      Emerging Properties in Self-Supervised Vision Transformers

      Mathilde Caron · 10,591 citations · Papers With Code

    29. 29
      Computer vision1986

      A Computational Approach to Edge Detection

      John Canny · 34,484 citations · Semantic Scholar

      Editor's noteClassic quota
    30. 30
      Self-supervised learning2019 · published 2020

      Momentum Contrast for Unsupervised Visual Representation Learning

      Kaiming He · 15,960 citations · Papers With Code

    31. 31
      Multimodal & vision-language2022

      BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

      Junnan Li · 7,483 citations · Papers With Code

    32. 32
      Computer vision2020

      NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

      Ben Mildenhall · 6,259 citations · Semantic Scholar

      Editor's note
    33. 33
      Self-supervised learning2020

      Bootstrap your own latent: A new approach to self-supervised Learning

      Jean-Bastien Grill · 9,233 citations · Papers With Code

    34. 34
      Multimodal & vision-language2014 · published 2015

      Show and Tell: A Neural Image Caption Generator

      Oriol Vinyals · 6,686 citations · Papers With Code

    35. 35
      Computer vision2020

      End-to-End Object Detection with Transformers

      Nicolas Carion · 20,420 citations · Papers With Code

    36. 36
      Computer vision2023

      3D Gaussian Splatting for Real-Time Radiance Field Rendering

      Bernhard Kerbl · 10,940 citations · Papers With Code

    37. 37
      Computer vision2015

      Fast R-CNN

      Ross Girshick · 29,250 citations · Papers With Code

      Award
    38. 38
      Self-supervised learning2014

      How transferable are features in deep neural networks?

      Jason Yosinski · 9,618 citations · Papers With Code

    39. 39
      Computer vision1999

      Object Recognition from Local Scale-Invariant Features

      David Lowe · 19,002 citations · Semantic Scholar

      Award
    40. 40
      Self-supervised learning2015 · published 2016

      Domain-Adversarial Training of Neural Networks

      Yaroslav Ganin · 12,398 citations · Papers With Code

    41. 41
      Computer vision1988

      Snakes: Active Contour Models

      Michael Kass · 17,120 citations · OpenAlex

      Award
    42. 42
      Computer vision2016 · published 2017

      Densely Connected Convolutional Networks

      Gao Huang · 48,554 citations · OpenAlex

    43. 43
      Computer vision1981

      Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography

      Martin A. Fischler · 25,887 citations · OpenAlex

      Editor's note
    44. 44
      Multimodal & vision-language2021

      Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

      Chao Jia · 6,111 citations · Papers With Code

    45. 45
      Computer vision2016 · published 2017

      PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

      Charles R. Qi · 18,771 citations · Papers With Code

    46. 46
      Computer vision2000

      Normalized Cuts and Image Segmentation

      Jianbo Shi · 18,090 citations · Semantic Scholar

      Award
    47. 47
      Computer vision2015 · published 2016

      SSD: Single Shot MultiBox Detector

      Wei Liu · 36,422 citations · Papers With Code

    48. 48
      Computer vision2016 · published 2017

      Feature Pyramid Networks for Object Detection

      Tsung-Yi Lin · 30,908 citations · OpenAlex

    49. 49
      Multimodal & vision-language2017 · published 2018

      Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

      Peter Anderson · 5,119 citations · OpenAlex

    50. 50
      Self-supervised learning2015

      FaceNet: A Unified Embedding for Face Recognition and Clustering

      Florian Schroff · 15,517 citations · Papers With Code

    51. 51
      Self-supervised learning2023 · published 2024

      DINOv2: Learning Robust Visual Features without Supervision

      Maxime Oquab · 11,351 citations · Papers With Code

    52. 52
      Multimodal & vision-language2019

      ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

      Jiasen Lu · 4,742 citations · Papers With Code

    53. 53
      Computer vision2006

      SURF: Speeded Up Robust Features

      14,958 citations · OpenAlex

      Award
    54. 54
      Computer vision1981

      An Iterative Image Registration Technique with an Application to Stereo Vision

      Bruce D. Lucas · 15,620 citations · Semantic Scholar

    55. 55
      Computer vision2019

      EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

      Mingxing Tan · 26,868 citations · Papers With Code

    56. 56
      Computer vision1981

      Determining Optical Flow

      Berthold K. P. Horn · 13,609 citations · Semantic Scholar

    57. 57
      Computer vision2021

      Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

      Ze Liu · 36,498 citations · Papers With Code

    58. 58
      Multimodal & vision-language2023

      InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

      Wenliang Dai · 4,085 citations · Papers With Code

    59. 59
      Multimodal & vision-language2014 · published 2015

      Deep Visual-Semantic Alignments for Generating Image Descriptions

      Andrej Karpathy · 6,156 citations · Papers With Code

    60. 60
      Computer vision2011

      ORB: An efficient alternative to SIFT or SURF

      11,036 citations · OpenAlex

      Award
    61. 61
      Self-supervised learning2021

      BEiT: BERT Pre-Training of Image Transformers

      Hangbo Bao · 3,960 citations · Papers With Code

    62. 62
      Multimodal & vision-language2023

      Improved Baselines with Visual Instruction Tuning

      Haotian Liu · 6,015 citations · Papers With Code

    63. 63
      Self-supervised learning2013 · published 2014

      DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

      Jeff Donahue · 4,019 citations · OpenAlex

      Award
    64. 64
      Self-supervised learning2020

      Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

      Mathilde Caron · 5,285 citations · Papers With Code

    65. 65
      Computer vision2015

      ImageNet Large Scale Visual Recognition Challenge

      Olga Russakovsky · 39,012 citations · OpenAlex

    66. 66
      Computer vision1991

      Eigenfaces for Recognition

      Matthew Turk · 13,733 citations · OpenAlex

    67. 67
      Multimodal & vision-language2019

      LXMERT: Learning Cross-Modality Encoder Representations from Transformers

      Hao Tan · 3,070 citations · Papers With Code

    68. 68
      Multimodal & vision-language2021

      Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

      Junnan Li · 3,002 citations · Papers With Code

    69. 69
      Self-supervised learning2008

      Visualizing Data using t-SNE

      Laurens van der Maaten · 52,306 citations · Semantic Scholar

    70. 70
      Self-supervised learning2021

      Barlow Twins: Self-Supervised Learning via Redundancy Reduction

      Jure Zbontar · 3,315 citations · Papers With Code

    71. 71
      Multimodal & vision-language2025

      Qwen2.5-VL Technical Report

      6,243 citations · Papers With Code

    72. 72
      Multimodal & vision-language2023 · published 2024

      Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

      Shilong Liu · 5,288 citations · Papers With Code

    73. 73
      Computer vision2024

      SAM 2: Segment Anything in Images and Videos

      Ravi · 4,567 citations · Papers With Code

    74. 74
      Computer vision2009 · published 2010

      The PASCAL Visual Object Classes (VOC) Challenge

      Mark Everingham · 19,569 citations · OpenAlex

    75. 75
      Self-supervised learning2014

      Distributed Representations of Sentences and Documents

      Quoc Le · 9,861 citations · Papers With Code

    76. 76
      Computer vision2006

      Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

      Svetlana Lazebnik · 7,893 citations · OpenAlex

      Award
    77. 77
      Multimodal & vision-language2023

      MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

      Deyao Zhu · 3,402 citations · Papers With Code

    78. 78
      Self-supervised learning2008

      Extracting and composing robust features with denoising autoencoders

      Pascal Vincent · 7,436 citations · OpenAlex

    79. 79
      Multimodal & vision-language2016 · published 2017

      Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

      Ranjay Krishna · 6,803 citations · Papers With Code

    80. 80
      Multimodal & vision-language2024

      Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

      Gemini Team · 4,110 citations · Papers With Code

    81. 81
      Self-supervised learning2023

      Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

      Mahmoud Assran · 1,442 citations · Papers With Code

    82. 82
      Multimodal & vision-language2024

      Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

      Peng Wang · 5,243 citations · Papers With Code

    83. 83
      Multimodal & vision-language2019 · published 2020

      UNITER: UNiversal Image-TExt Representation Learning

      Yen-Chun Chen · 2,055 citations · OpenAlex

    84. 84
      Self-supervised learning2020 · published 2021

      Exploring Simple Siamese Representation Learning

      Xinlei Chen · 5,313 citations · Papers With Code

    85. 85
      Computer vision2017

      Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

      João Carreira · 10,065 citations · Papers With Code

    Ranked on another page

    Also relevant

    Top 500 papers ranked on another domain page that matter here too.

    1. Generative models2013 · published 2014

      Auto-Encoding Variational Bayes

      Diederik P. Kingma · 20,065 citations · OpenAlex

      AwardEditor's note
    2. Deep learning2015

      Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

      Sergey Ioffe · 48,020 citations · Papers With Code

      AwardEditor's note
    3. Language, speech & LLMs2017

      Attention Is All You Need

      Ashish Vaswani · 197,211 citations · Papers With Code

      Editor's note
    4. Generative models2015 · published 2016

      Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

      Alec Radford · 15,333 citations · Papers With Code

      Award
    5. Language, speech & LLMs2014

      GloVe: Global Vectors for Word Representation

      Jeffrey Pennington · 35,748 citations · Semantic Scholar

      Award
    6. Language, speech & LLMs2013

      Efficient Estimation of Word Representations in Vector Space

      Tomas Mikolov · 35,287 citations · Papers With Code

      Editor's note
    7. Deep learning1986

      Learning representations by back-propagating errors

      David E. Rumelhart · 31,877 citations · OpenAlex

      Editor's note
    8. Language, speech & LLMs2018

      BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

      Jacob Devlin · 122,869 citations · Papers With Code

      Editor's note
    9. AI for science2015

      U-Net: Convolutional Networks for Biomedical Image Segmentation

      Olaf Ronneberger · 103,099 citations · Papers With Code

      Editor's note
    10. Deep learning1998

      Gradient-Based Learning Applied to Document Recognition

      Yann LeCun · 58,786 citations · OpenAlex

      Editor's note
    11. Generative models2014

      Generative Adversarial Nets

      Ian Goodfellow · 4,477 citations · OpenAlex

      AwardEditor's note
    12. Generative models2021 · published 2022

      High-Resolution Image Synthesis with Latent Diffusion Models

      Robin Rombach · 28,168 citations · Papers With Code

      Editor's note

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0), and Semantic Scholar logoSemantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.