Fusing Visual and Textual Cues for Sequential Image Difference Captioning

Alexander Black, Jing Shi, Yifei Fan, John Collomosse

Keywords: Visual Language Models, Change Summarization, Multi-modal Analysis

TL;DR: Summarize in natural language a sequence of image edits using visual and textual cues

Abstract: We present FVTC - a technique for image difference captioning that is able to benefit from additional visual and/or textual inputs. FVTC is able to succinctly summarize multiple manipulations that were applied to an image in a sequence. Optionally, it can take several intermediate thumbnails of the image editing sequence as input, as well as coarse machine-generated annotations of the individual manipulations. We demonstrate that the presence of intermediate images and/or auxiliary textual information improves the model's captioning performance. To train FVTC, we introduce METS - a new dataset of image editing sequences, with textual machine annotations of each editorial step and human edit summarization captions after the 5th, 10th and 15th manipulation.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6691