Copertina

PooDLe: Pooled and dense self-supervised learning from naturalistic videos

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Alex N., Hoang, Christopher, Xiong, Yuwen, LeCun, Yann, Ren, Mengye
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Intuitive physics understanding emerges from self-supervised pretraining on natural videos
di: Garrido, Quentin, et al.
Pubblicazione: (2025)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
di: Balestriero, Randall, et al.
Pubblicazione: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
di: Balestriero, Randall, et al.
Pubblicazione: (2024)

A hierarchical loss and its problems when classifying non-hierarchically
di: Wu, Cinna, et al.
Pubblicazione: (2017)

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
di: Hoang, Christopher, et al.
Pubblicazione: (2025)

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
di: Moutakanni, Théo, et al.
Pubblicazione: (2024)

Self-supervised learning of video representations from a child's perspective
di: Orhan, A. Emin, et al.
Pubblicazione: (2024)

Video Representation Learning with Joint-Embedding Predictive Architectures
di: Drozdov, Katrina, et al.
Pubblicazione: (2024)

The Entropy Enigma: Success and Failure of Entropy Minimization
di: Press, Ori, et al.
Pubblicazione: (2024)

URLOST: Unsupervised Representation Learning without Stationarity or Topology
di: Yun, Zeyu, et al.
Pubblicazione: (2023)

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
di: Goswami, Raktim Gautam, et al.
Pubblicazione: (2024)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
di: Balestriero, Randall, et al.
Pubblicazione: (2025)

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
di: Denton, Remi, et al.
Pubblicazione: (2014)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
di: Tong, Shengbang, et al.
Pubblicazione: (2024)

Blockwise Self-Supervised Learning at Scale
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2023)

Discrete JEPA: Learning Discrete Token Representations without Reconstruction
di: Baek, Junyeob, et al.
Pubblicazione: (2025)

Learning Latent Action World Models In The Wild
di: Garrido, Quentin, et al.
Pubblicazione: (2026)

Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
di: Kuang, Yilun, et al.
Pubblicazione: (2026)

Navigation World Models
di: Bar, Amir, et al.
Pubblicazione: (2024)

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
di: Ren, Mengye
Pubblicazione: (2026)

Variance-Covariance Regularization Improves Representation Learning
di: Zhu, Jiachen, et al.
Pubblicazione: (2023)

Hierarchical World Models as Visual Whole-Body Humanoid Controllers
di: Hansen, Nicklas, et al.
Pubblicazione: (2024)

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
di: Zeevi, Tal, et al.
Pubblicazione: (2024)

Transformers without Normalization
di: Zhu, Jiachen, et al.
Pubblicazione: (2025)

Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
di: Chakraborty, Deep, et al.
Pubblicazione: (2024)

Learning and Leveraging World Models in Visual Representation Learning
di: Garrido, Quentin, et al.
Pubblicazione: (2024)

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
di: Tong, Shengbang, et al.
Pubblicazione: (2024)

Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning
di: Lê, Hoàng-Ân, et al.
Pubblicazione: (2024)

EgoPet: Egomotion and Interaction Data from an Animal's Perspective
di: Bar, Amir, et al.
Pubblicazione: (2024)

From Generated Human Videos to Physically Plausible Robot Trajectories
di: Ni, James, et al.
Pubblicazione: (2025)

Representation Learning for Spatiotemporal Physical Systems
di: Qu, Helen, et al.
Pubblicazione: (2026)

Breast tumor classification based on self-supervised contrastive learning from ultrasound videos
di: Tang, Yunxin, et al.
Pubblicazione: (2024)

Back to the Features: DINO as a Foundation for Video World Models
di: Baldassarre, Federico, et al.
Pubblicazione: (2025)

Whole-Body Conditioned Egocentric Video Prediction
di: Bai, Yutong, et al.
Pubblicazione: (2025)

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
di: Sobal, Vlad, et al.
Pubblicazione: (2024)

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
di: Mur-Labadia, Lorenzo, et al.
Pubblicazione: (2026)

Multimodal self-supervised learning for lesion localization
di: Yang, Hao, et al.
Pubblicazione: (2024)

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
di: Rudman, William, et al.
Pubblicazione: (2025)

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos
di: Yang, Yanlai, et al.
Pubblicazione: (2025)

ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generation
di: Lu, Jack, et al.
Pubblicazione: (2024)