mlsanityData to 14 Oct 2026

Efficient Object Localization Using Convolutional Networks

arXiv 1411.4280 ↗First posted 16 Nov 2014cs.CVcited by 227

Not on the map. Why?

Abstract (arXiv)

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC dataset and outperforms all existing approaches on the MPII-human-pose dataset.

Key facts. Cited by 227 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 75; 2022: 38; 2023: 50; 2024: 28; 2025: 22; 2026: 13.

227 papers.

Sort:

By area:

  1. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  2. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  3. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  4. 2022Masked World Models for Visual Controlcited by 170
  5. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  6. 2022What to Hide from Your Students: Attention-Guided Masked Image Modelingcited by 118
  7. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  8. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
  9. 2021TransFER: Learning Relation-aware Facial Expression Representations with Transformerscited by 85
  10. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  11. 2024When Do We Not Need Larger Vision Models?cited by 67
  12. 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformerscited by 59
38 more
  1. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  2. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
  3. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  4. 2022A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmarkcited by 45
  5. 2021Reflash Dropout in Image Super-Resolutioncited by 41
  6. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 41
  7. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  8. 2021AutoDropout: Learning Dropout Patterns to Regularize Deep Networkscited by 35
  9. 2024LoRA Dropout as a Sparsity Regularizer for Overfitting Controlcited by 35
  10. 2023Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Wordscited by 34
  11. 2023Emergence of Maps in the Memories of Blind Navigation Agentscited by 33
  12. 2021Uncertainty guided semi-supervised segmentation of retinal layers in OCT imagescited by 29
  13. 2023OCELOT: Overlapped Cell on Tissue Dataset for Histopathologycited by 29
  14. 2021Contextual Dropout: An Efficient Sample-Dependent Dropout Modulecited by 26
  15. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  16. 2022Towards Improving Calibration in Object Detection Under Domain Shiftcited by 26
  17. 2021Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detectioncited by 24
  18. 2021Network Augmentation for Tiny Deep Learningcited by 24
  19. 2021Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videoscited by 23
  20. 2023Ego3DPose: Capturing 3D Cues from Binocular Egocentric Viewscited by 22
  21. 2023Dropout Reduces Underfittingcited by 21
  22. 2023DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalizationcited by 21
  23. 2022NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Resultscited by 20
  24. 2022Improving GANs with A Dynamic Discriminatorcited by 20
  25. 2023Learning to Skip for Language Modelingcited by 19
  26. 2024Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Maskingcited by 19
  27. 2021Hard-Attention for Scalable Image Classificationcited by 18
  28. 2021Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Datacited by 18
  29. 2021Differentiable Network Pruning for Microcontrollerscited by 16
  30. 2024Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworkscited by 16
  31. 2021Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilationcited by 15
  32. 2023Source-free Domain Adaptive Human Pose Estimationcited by 15
  33. 2021Improving Weakly-supervised Object Localization via Causal Interventioncited by 14
  34. 2024DropKAN: Regularizing KANs by masking post-activationscited by 14
  35. 2022Gait Recognition with Mask-based Regularizationcited by 13
  36. 2022Federated Learning of Large Models at the Edge via Principal Sub-Model Trainingcited by 13
  37. 2024Attention-Propagation Network for Egocentric Heatmap to 3D Pose Liftingcited by 13
  38. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12

50 most cited of 227 All 227 (JSON)