No article text was recorded for this version.
cross-attention localization
Version 1 of 134 papers43 conceptsfrozen 2026-10-04
Papers in this version
- Blog: InstructRestore: Region-Customized Image Restoration with Human Instructions
- Blog: Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing
- Blog: Your Text Encoder Can Be An Object-Level Watermarking Controller
- Blog: Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models
- Blog: Unleashing Text-to-Image Diffusion Models for Visual Perception
- Blog: Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation
- Blog: DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
- Blog: Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
- Blog: Segmentation-Free Guidance for Text-to-Image Diffusion Models
- Blog: InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
- Blog: Free-ATM: Harnessing Free Attention Masks for Representation Learning on Diffusion-Generated Images
- Blog: DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
- Blog: Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models
- Blog: Zero-shot spatial layout conditioning for text-to-image diffusion models
- Blog: Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation
- Blog: AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
- Blog: Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
- Blog: Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
- Blog: No Annotations for Object Detection in Art Through Stable Diffusion
- Blog: From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
- Blog: Teaching Diffusion Models to Ground Alpha Matte
- Blog: Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision
- Blog: Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
- Blog: DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
- Blog: Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models
- Blog: Unsupervised Semantic Correspondence Using Stable Diffusion
- Blog: Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
- Blog: Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models
- Blog: SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Models
- Blog: Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation
- Blog: Conceptrol: Concept Control of Zero-shot Personalized Image Generation
- Blog: Unsupervised Discovery of Facial Landmarks and Head Pose
- Blog: DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
- Blog: CCLAP: Controllable Chinese Landscape Painting Generation via Latent Diffusion Model
History & citation
Current · Permanent link
- This direction split from Object Localization with Internal Diffusion Attention Maps (94% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_attention_localization_59711569,
title = {cross-attention localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-attention-localization/rdr_59711569681b456597ab8ab27df28bf1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_attention_localization_59711569_v1,
title = {cross-attention localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-attention-localization/rdr_59711569681b456597ab8ab27df28bf1/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}