# CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation

Source: [CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation](<https://www.sota2.com/research/paper/6a434d5eba73165dbb743708>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-01T05:00:04.992Z

Authors: Jinhong Hu, Xiaoping Wang, Shuyin Huang, Guojin Zhong, Kaitai Liu, Kai Lu

Published: 2026-06-27T04:07:31.000Z

## Abstract

Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing. However, traditional Image Change Captioning (ICC) methods lack spatial grounding, limiting their precision. We introduce Image Change Captioning and Segmentation (ICCS), a new multimodal task that jointly requires structured change description and pixel-level localization. To address ICCS, we propose the Change-aware Captioning and Reasoning Chain (CCRC), a dual-chain framework that decouples semantic reasoning from spatial segmentation. The first chain, Chain-of-Change-Captioning (CCC), enhances fine-grained change perception via a visual fusion module based on Multi-Head Change-aware Attention inserted between the visual and language components of a Multimodal Large Language Model (MLLM). CCC also determines whether a change is segmentable. If not, it alone generates the caption. Otherwise, the second chain, Chain-of-Change-Segmenting (CCS), is activated, leveraging spatial priors from CCC and refining masks with a Change-aware Token Refiner for accurate boundary localization. We evaluate CCRC on both synthetic and real-world change detection benchmarks with pixel-level supervision. Experiments show CCRC achieves state-of-the-art performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Change Captioning on CLEVR-Change](<https://www.sota2.com/research/sota/image-change-captioning-on-clevr-change.md>): Image Change Captioning; CLEVR-Change; BLEU-4: 58.3.

- [Image Change Captioning on Image-Editing-Request](<https://www.sota2.com/research/sota/image-change-captioning-on-image-editing-request.md>): Image Change Captioning; Image-Editing-Request; BLEU-4: 15.3.

- [Image Change Captioning and Segmentation on CLEVR-Change](<https://www.sota2.com/research/sota/image-change-captioning-and-segmentation-on-clevr-change.md>): Image Change Captioning and Segmentation; CLEVR-Change; BLEU-4: 58.3.

- [Image Change Captioning and Segmentation on Image-Editing-Request](<https://www.sota2.com/research/sota/image-change-captioning-and-segmentation-on-image-editing-request.md>): Image Change Captioning and Segmentation; Image-Editing-Request; BLEU-4: 15.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.28724>)

[PDF](<https://arxiv.org/pdf/2606.28724.pdf>)