mlsanityData to 14 Oct 2026

Temporal Slowness in Central Vision Drives Semantic Object Learning

arXiv 2602.04462 ↗First posted 4 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field of view with high resolution and it learns similar representations for visual inputs occurring close in time. This emphasizes slowly changing information around gaze locations. This study investigates the role of central vision and slowness learning in the formation of semantic object representations from human-like visual experience. We simulate five months of human-like visual experience using the Ego4D dataset and a state-of-the-art gaze prediction model. We extract image crops around predicted gaze locations to train a time-contrastive Self-Supervised Learning model. Our results show that exploiting temporal slowness when learning from central visual field experience improves the encoding of different facets of object semantics. Specifically, focusing on central vision strengthens the extraction of foreground object features, while considering temporal slowness, especially in conjunction with eye movements, allows the model to encode broader semantic information about objects. These findings provide new insights into the mechanisms by which humans may develop semantic object representations from natural visual experience. Our code will be made public upon acceptance. Code is available at https://github.com/t9s9/central-vision-ssl.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 54 of its 93 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

54 of 93 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2013Describing Textures in the Wildcited by 2,125
  9. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  10. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  12. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
38 more
  1. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  3. 2019Contrastive Multiview Codingcited by 1,301
  4. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  5. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  7. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 395
  8. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 343
  9. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  10. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  11. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 218
  12. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 173
  13. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  14. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 114
  15. 2021Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspectivecited by 81
  16. 2020Self-supervised learning through the eyes of a childcited by 61
  17. 2020Watching the World Go By: Representation Learning from Unlabeled Videoscited by 59
  18. 2022Mugs: A Multi-Granular Self-Supervised Learning Frameworkcited by 54
  19. 2022In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimationcited by 51
  20. 2015Learning image representations tied to ego-motioncited by 42
  21. 2023Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videocited by 40
  22. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  23. 2020Biologically Inspired Mechanisms for Adversarial Robustnesscited by 29
  24. 2015Slow and steady feature analysis: higher order temporal coherence in videocited by 28
  25. 2020Emergent Properties of Foveated Perceptual Systemscited by 24
  26. 2023Learning high-level visual representations from a child's perspective without strong inductive biasescited by 22
  27. 2024Dimensions underlying the representational alignment of deep neural networks with humanscited by 22
  28. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  29. 2024The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiencescited by 17
  30. 2022Time to augment self-supervised visual representation learningcited by 15
  31. 2021On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentationcited by 12
  32. 2019ViCo: Word Embeddings from Visual Co-occurrencescited by 10
  33. 2024Self-supervised visual learning from interactions with objectscited by 10
  34. 2022Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classificationcited by 7
  35. 2023Are Vision Transformers More Data Hungry Than Newborn Visual Systems?cited by 7
  36. 2024Self-supervised learning of video representations from a child's perspectivecited by 6
  37. 2023Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Playcited by 5
  38. 2024Learning Object Semantic Similarity with Self-Supervisioncited by 5

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.