cs.CVFeb 3, 2026

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

Authors: Byeongju Woo, Zilin Wang, Byeonghyun Pak, Sangwoo Mo, Stella X. Yu

Organizations: Agency for Defense Development · University of Michigan · POSTECH

Abstract

Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidence. We propose a hierarchical vision-language learning principle for understanding scenes as part-to-whole compositions: before forming a whole-scene representation, a model should uncover what semantic parts appear where in the image. To this end, we propose CAFT (Cross-domain Alignment of Forest and Trees), a vision-language model that jointly learns local text-region alignment at intermediate representations and global image-text alignment at the final representation. Exploiting the organization of long captions, where local descriptions often correspond to scene parts, CAFT employs a fine-to-coarse image encoder and a part-whole text encoder to discover localized part semantics and progressively compose them into a global image-text representation. Trained on 30M image-text pairs, CAFT achieves state-of-the-art performance on six long-text retrieval benchmarks and exhibits strong scaling behavior. Experiments show that CAFT learns fine-grained representations that localize textual semantics in image regions without explicit region-level supervision.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning

    Jul 3, 2026Chengzhen Yu, Canran Xiao, Siyuan Ma +1VLM RobustnessContrastive Learning

  2. FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning

    May 26, 2026Hyungyu Choi, Young Kyun Jang, Chanho EomVLM AdaptationText-Image Alignment