No article text was recorded for this version.
aspect ratio distortion
Version 1 of 1251 papers432 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers
- Blog: NARAIM: Native Aspect Ratio Autoregressive Image Models
- Blog: Aspect-Ratio-Preserving Multi-Patch Image Aesthetics Score Prediction
- Blog: ARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment
- Blog: What is the right way to represent document images?
- Blog: Best Practices for a Handwritten Text Recognition System
- Blog: Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs
- Blog: ScreenAI: A Vision-Language Model for UI and Infographics Understanding
- Blog: PAID: A Framework of Product-Centric Advertising Image Design
- Blog: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
- Blog: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
- Blog: Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
- Blog: SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
- Blog: Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework
- Blog: Physical-space Multi-body Mesh Detection Achieved by Local Alignment and Global Dense Learning
- Blog: Image Aesthetics Prediction Using Multiple Patches Preserving the Original Aspect Ratio of Contents
- Blog: NARAIM: Native Aspect Ratio Autoregressive Image Models
- Blog: A deep architecture for unified aesthetic prediction
- Blog: Learning Photography Aesthetics with Deep CNNs
- Blog: Best Practices for a Handwritten Text Recognition System
- Blog: Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks
- Blog: Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation
- Blog: Conviformers: Convolutionally guided Vision Transformer
- Blog: All the attention you need: Global-local, spatial-channel attention for image retrieval
- Blog: Video Recognition in Portrait Mode
- Blog: Exploiting Offset-guided Network for Pose Estimation and Tracking
- Blog: MiDaS v3.1 - A Model Zoo for Robust Monocular Relative Depth Estimation
- Blog: HATFormer: Historic Handwritten Arabic Text Recognition with Transformers
- Blog: Deep Cropping via Attention Box Prediction and Aesthetics Assessment
- Blog: End-to-End Deep Kronecker-Product Matching for Person Re-identification
- Blog: Attention-Mechanism-based Tracking Method for Intelligent Internet of Vehicles
- Blog: Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs
- Blog: Theme Aware Aesthetic Distribution Prediction with Full Resolution Photos
- Blog: Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment
- Blog: AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
- Blog: SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Blog: Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
- Blog: OCM3D: Object-Centric Monocular 3D Object Detection
- Blog: TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
- Blog: A2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes.
- Blog: Composition-Preserving Deep Photo Aesthetics Assessment
- Blog: Expression Analysis Based on Face Regions in Real-world Conditions
- Blog: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
- Blog: Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
- Blog: Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
- Blog: Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment
- Blog: Semantic-Aware Transformation-Invariant RoI Align
- Blog: Is Image Size Important? A Robustness Comparison of Deep Learning Methods for Multi-scale Cell Image Classification Tasks: from Convolutional Neural Networks to Visual Transformers
- Blog: What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
- Blog: FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
- Blog: Multi-Dimensional Quality Assessment for UGC Videos via Modular Multi-Modal Vision-Language Models
- Blog: The Shape of Art History in the Eyes of the Machine
- Blog: TokenPacker: Efficient Visual Projector for Multimodal LLM
- Blog: Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
- Blog: Contour-Maintaining-Based Image Adaption for an Efficient Ambulance Service in Intelligent Transportation Systems
- Blog: Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning
- Blog: LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images
- Blog: TokenPacker: Efficient Visual Projector for Multimodal LLM
- Blog: MUSIQ: Multi-scale Image Quality Transformer
- Blog: RoomDiffusion: A Specialized Diffusion Model in the Interior Design Industry
Showing 60 of 251 papers.
History & citation
Current · Permanent link
- Native Resolution Encoding for Vision-Language Models merged into this direction (53% overlap)
- Composition Preserving Architectures for Image Aesthetic Assessment merged into this direction (100% overlap)
- Aspect Ratio Preserving Visual Representation Learning merged into this direction (77% overlap)
- Aspect Ratio Preserving Vision for Document Understanding merged into this direction (85% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_aspect_ratio_distortion_d6ae125f,
title = {aspect ratio distortion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/aspect-ratio-distortion/rdr_d6ae125f5fba4a9b8edf9d66f1519f88},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_aspect_ratio_distortion_d6ae125f_v1,
title = {aspect ratio distortion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/aspect-ratio-distortion/rdr_d6ae125f5fba4a9b8edf9d66f1519f88/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}