Copertina

Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Renyu, Kirilenko, Vladimir, You, Yao, Wolfe, Crag
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

Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection
di: Xu, Yuting, et al.
Pubblicazione: (2024)

PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment
di: Huang, Dingbang, et al.
Pubblicazione: (2025)

Enhancing Dataset Distillation via Label Inconsistency Elimination and Learning Pattern Refinement
di: Zhou, Chuhao, et al.
Pubblicazione: (2024)

SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters
di: Tanaka, Shohei, et al.
Pubblicazione: (2024)

DGM4+: Dataset Extension for Global Scene Inconsistency
di: Singh, Gagandeep, et al.
Pubblicazione: (2025)

Manga Generation via Layout-controllable Diffusion
di: Chen, Siyu, et al.
Pubblicazione: (2024)

SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation
di: Cory, Oliver, et al.
Pubblicazione: (2026)

Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
di: Jiang, Weihao, et al.
Pubblicazione: (2024)

OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
di: Kang, Hengrui, et al.
Pubblicazione: (2025)

Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation
di: Zhangli, Qilong, et al.
Pubblicazione: (2024)

Self-supervised Photographic Image Layout Representation Learning
di: Zhao, Zhaoran, et al.
Pubblicazione: (2024)

Diachronic Document Dataset for Semantic Layout Analysis
di: Clérice, Thibault, et al.
Pubblicazione: (2024)

Generating Animated Layouts as Structured Text Representations
di: Shin, Yeonsang, et al.
Pubblicazione: (2025)

Inconsistency-Based Data-Centric Active Open-Set Annotation
di: Mao, Ruiyu, et al.
Pubblicazione: (2024)

HYDRA: Unifying Multi-modal Generation and Understanding via Representation-Harmonized Tokenization
di: Qiu, Xuerui, et al.
Pubblicazione: (2026)

CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation
di: Wang, Haoxuan, et al.
Pubblicazione: (2025)

AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding Annotation
di: Hu, Rongsheng, et al.
Pubblicazione: (2026)

Scaling Audio-Visual Quality Assessment Dataset via Crowdsourcing
di: Yang, Renyu, et al.
Pubblicazione: (2026)

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation
di: Tsai, Yu-Ju, et al.
Pubblicazione: (2024)

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
di: Xiang, Qiang, et al.
Pubblicazione: (2025)

Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
di: Wang, Donghua, et al.
Pubblicazione: (2024)

Learning Tracking Representations from Single Point Annotations
di: Wu, Qiangqiang, et al.
Pubblicazione: (2024)

Aggregated Structural Representation with Large Language Models for Human-Centric Layout Generation
di: Jin, Jiongchao, et al.
Pubblicazione: (2025)

ReLayout: Versatile and Structure-Preserving Design Layout Editing via Relation-Aware Design Reconstruction
di: Lin, Jiawei, et al.
Pubblicazione: (2026)

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
di: Fan, Weichen, et al.
Pubblicazione: (2025)

LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
di: Zheng, Guangcong, et al.
Pubblicazione: (2023)

Adaptive Learning of Consistency and Inconsistency Information for Fake News Detection
di: Li, Aohan, et al.
Pubblicazione: (2024)

PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments
di: You, Yang, et al.
Pubblicazione: (2023)

MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
di: Jiang, Zheng, et al.
Pubblicazione: (2026)

MALeR: Improving Compositional Fidelity in Layout-Guided Generation
di: Saxena, Shivank, et al.
Pubblicazione: (2025)

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
di: Wu, Size, et al.
Pubblicazione: (2025)

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
di: Wang, Jiahao, et al.
Pubblicazione: (2025)

RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning
di: Wang, Jiacheng, et al.
Pubblicazione: (2024)

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
di: Luo, Chuwei, et al.
Pubblicazione: (2024)

TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering
di: Mao, Dongxing, et al.
Pubblicazione: (2026)

ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
di: Jiang, Zhouqiang, et al.
Pubblicazione: (2024)

Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking
di: Guo, Xucheng, et al.
Pubblicazione: (2025)

Object-Centric Learning with Slot Mixture Module
di: Kirilenko, Daniil, et al.
Pubblicazione: (2023)

AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
di: Chen, Weixing, et al.
Pubblicazione: (2025)

LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
di: Chen, Yuzhuo, et al.
Pubblicazione: (2025)