mlsanityData to 14 Oct 2026

EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023

arXiv 2306.16606 ↗First posted 29 Jun 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present EgoCOL, an egocentric camera pose estimation method for open-world 3D object localization. Our method leverages sparse camera pose reconstructions in a two-fold manner, video and scan independently, to estimate the camera pose of egocentric frames in 3D renders with high recall and precision. We extensively evaluate our method on the Visual Query (VQ) 3D object localization Ego4D benchmark. EgoCOL can estimate 62% and 59% more camera poses than the Ego4D baseline in the Ego4D Visual Queries 3D Localization challenge at CVPR 2023 in the val and test sets, respectively. Our code is publicly available at https://github.com/BCV-Uniandes/EgoCOL

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

31 of 41 references.

References · 31

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  4. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  5. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
  6. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  7. 2021Grounded Language-Image Pre-trainingcited by 1,156
  8. 2021Scaling Vision Transformerscited by 999
  9. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  10. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  11. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  12. 2021Revisiting Skeleton-based Action Recognitioncited by 257
19 more
  1. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
  2. 2021Group-Free 3D Object Detection via Transformerscited by 215
  3. 2021Anticipative Video Transformercited by 200
  4. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  5. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  6. 2022Multiview Transformers for Video Recognitioncited by 148
  7. 2022Multimodal Token Fusion for Vision Transformerscited by 136
  8. 2018Grounded Human-Object Interaction Hotspots from Videocited by 129
  9. 2018When will you do what? - Anticipating Temporal Occurrences of Activitiescited by 107
  10. 2019What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attentioncited by 105
  11. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 99
  12. 2022Surface Representation for Point Cloudscited by 84
  13. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  14. 2022RBGNet: Ray-based Grouping for 3D Object Detectioncited by 40
  15. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  16. 2015You-Do, I-Learn: Unsupervised Multi-User egocentric Approach Towards Video-Based Guidancecited by 17
  17. 2022Scalable SoftGroup for 3D Instance Segmentation on Point Cloudscited by 15
  18. 2022Negative Frames Matter in Egocentric Visual Query 2D Localizationcited by 14
  19. 2022Estimating more camera poses for ego-centric videos is essential for VQ3Dcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Visioncited by 3
  2. 2024Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localizationcited by 1
  3. 2026EgoHieraLoc: A Cortically Inspired Hierarchical Segmentation-Guided Framework for Egocentric Visual Query Localizationcited by 0