Copertina

Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Henry, Maxim, Deliège, Adrien, Piérard, Sébastien, Van Droogenbroeck, Marc
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multi-domain performance analysis with scores tailored to user preferences
di: Piérard, Sébastien, et al.
Pubblicazione: (2025)

What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely $F_1$
di: Piérard, Sébastien, et al.
Pubblicazione: (2025)

A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
di: Piérard, Sébastien, et al.
Pubblicazione: (2025)

Foundations of the Theory of Performance-Based Ranking
di: Piérard, Sébastien, et al.
Pubblicazione: (2024)

The Tile: A 2D Map of Ranking Scores for Two-Class Classification
di: Piérard, Sébastien, et al.
Pubblicazione: (2024)

LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation
di: Henry, Maxim, et al.
Pubblicazione: (2025)

Summarizing the performances of a background subtraction algorithm measured on several videos
di: Piérard, Sébastien, et al.
Pubblicazione: (2020)

A Hitchhiker's Guide to Understanding Performances of Two-Class Classifiers
di: Halin, Anaïs, et al.
Pubblicazione: (2024)

SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
di: Cioppa, Anthony, et al.
Pubblicazione: (2022)

Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance
di: Piérard, Sébastien, et al.
Pubblicazione: (2022)

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
di: Held, Jan, et al.
Pubblicazione: (2024)

Semi-Supervised Training to Improve Player and Ball Detection in Soccer
di: Vandeghen, Renaud, et al.
Pubblicazione: (2022)

Triangle Splatting for Real-Time Radiance Field Rendering
di: Held, Jan, et al.
Pubblicazione: (2025)

A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles
di: Fonder, Michaël, et al.
Pubblicazione: (2023)

Adaptive Self-Training for Object Detection
di: Vandeghen, Renaud, et al.
Pubblicazione: (2022)

A Universal Protocol to Benchmark Camera Calibration for Sports
di: Magera, Floriane, et al.
Pubblicazione: (2024)

BroadTrack: Broadcast Camera Tracking for Soccer
di: Magera, Floriane, et al.
Pubblicazione: (2024)

Deep learning for action spotting in association football videos
di: Giancola, Silvio, et al.
Pubblicazione: (2024)

Online Distillation with Continual Learning for Cyclic Domain Shifts
di: Houyon, Joachim, et al.
Pubblicazione: (2023)

TrackMAE: Video Representation Learning via Track Mask and Predict
di: Vandeghen, Renaud, et al.
Pubblicazione: (2026)

X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model
di: Held, Jan, et al.
Pubblicazione: (2024)

Real-Time Semantic Background Subtraction
di: Cioppa, Anthony, et al.
Pubblicazione: (2020)

SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries
di: Mkhallati, Hassan, et al.
Pubblicazione: (2023)

Investigating Event-Based Cameras for Video Frame Interpolation in Sports
di: Deckyvere, Antoine, et al.
Pubblicazione: (2024)

Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders
di: Eymaël, Alexandre, et al.
Pubblicazione: (2024)

Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement
di: Akazan, Ange-Clément, et al.
Pubblicazione: (2026)

Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
di: Gérin, Benoît, et al.
Pubblicazione: (2024)

TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
di: Tursynbek, Nurislam, et al.
Pubblicazione: (2026)

OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videos
di: Benzakour, Yassine, et al.
Pubblicazione: (2024)

Can Geometry Save Central Views for Sports Field Registration?
di: Magera, Floriane, et al.
Pubblicazione: (2025)

VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
di: Held, Jan, et al.
Pubblicazione: (2023)

Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
di: Zhang, Zhilong, et al.
Pubblicazione: (2026)

Survey and synthesis of state of the art in driver monitoring
di: Halin, Anaïs, et al.
Pubblicazione: (2021)

RVLM: Recursive Vision-Language Models with Adaptive Depth
di: Mayumu, Nicanor, et al.
Pubblicazione: (2026)

Towards AI-Powered Video Assistant Referee System (VARS) for Association Football
di: Held, Jan, et al.
Pubblicazione: (2024)

GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
di: Huang, Lianming, et al.
Pubblicazione: (2025)

Efficient-VLN: A Training-Efficient Vision-Language Navigation Model
di: Zheng, Duo, et al.
Pubblicazione: (2025)

Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking
di: Yang, Xiangyang, et al.
Pubblicazione: (2024)

Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
di: Hsieh, Yi-Kuan, et al.
Pubblicazione: (2025)

Resource Efficient Perception for Vision Systems
di: Subramanyam, A V, et al.
Pubblicazione: (2024)