@inproceedings{cai-etal-2025-pixel,
title = "Pixel-Level Reasoning Segmentation via Multi-turn Conversations",
author = "Cai, Dexian and
Yang, Xiaocui and
Liu, YongKang and
Wang, Daling and
Feng, Shi and
Zhang, Yifei and
Poria, Soujanya",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.864/",
doi = "10.18653/v1/2025.acl-long.864",
pages = "17660--17679",
ISBN = "979-8-89176-251-0",
abstract = "Existing visual perception systems focus on region-level segmentation in single-turn dialogues, relying on complex and explicit query instructions. Such systems cannot reason at the pixel level and comprehend dynamic user intent that changes over interaction. Our work tackles this issue by introducing a novel task, Pixel-level Reasoning Segmentation (Pixel-level RS) based on multi-turn conversations, tracking evolving user intent via multi-turn interactions for fine-grained segmentation. To establish a benchmark for this novel task, we build a Pixel-level ReasonIng Segmentation Dataset Based on Multi-Turn Conversations (PRIST), comprising 24k utterances from 8.3k multi-turn conversational scenarios with segmentation targets. Building on PRIST, we further propose MIRAS, a Multi-turn Interactive ReAsoning Segmentation framework, integrates pixel-level segmentation with robust multi-turn conversation understanding, generating pixel-grounded explanations aligned with user intent. The PRIST dataset and MIRSA framework fill the gap in pixel-level reasoning segmentation. Experimental results on the PRIST dataset demonstrate that our method outperforms current segmentation-specific baselines in terms of segmentation and LLM-based reasoning metrics. The code and data are available at: https://anonymous.4open.science/r/PixelRS/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2025-pixel">
<titleInfo>
<title>Pixel-Level Reasoning Segmentation via Multi-turn Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dexian</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">YongKang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daling</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Existing visual perception systems focus on region-level segmentation in single-turn dialogues, relying on complex and explicit query instructions. Such systems cannot reason at the pixel level and comprehend dynamic user intent that changes over interaction. Our work tackles this issue by introducing a novel task, Pixel-level Reasoning Segmentation (Pixel-level RS) based on multi-turn conversations, tracking evolving user intent via multi-turn interactions for fine-grained segmentation. To establish a benchmark for this novel task, we build a Pixel-level ReasonIng Segmentation Dataset Based on Multi-Turn Conversations (PRIST), comprising 24k utterances from 8.3k multi-turn conversational scenarios with segmentation targets. Building on PRIST, we further propose MIRAS, a Multi-turn Interactive ReAsoning Segmentation framework, integrates pixel-level segmentation with robust multi-turn conversation understanding, generating pixel-grounded explanations aligned with user intent. The PRIST dataset and MIRSA framework fill the gap in pixel-level reasoning segmentation. Experimental results on the PRIST dataset demonstrate that our method outperforms current segmentation-specific baselines in terms of segmentation and LLM-based reasoning metrics. The code and data are available at: https://anonymous.4open.science/r/PixelRS/.</abstract>
<identifier type="citekey">cai-etal-2025-pixel</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.864</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.864/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>17660</start>
<end>17679</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pixel-Level Reasoning Segmentation via Multi-turn Conversations
%A Cai, Dexian
%A Yang, Xiaocui
%A Liu, YongKang
%A Wang, Daling
%A Feng, Shi
%A Zhang, Yifei
%A Poria, Soujanya
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F cai-etal-2025-pixel
%X Existing visual perception systems focus on region-level segmentation in single-turn dialogues, relying on complex and explicit query instructions. Such systems cannot reason at the pixel level and comprehend dynamic user intent that changes over interaction. Our work tackles this issue by introducing a novel task, Pixel-level Reasoning Segmentation (Pixel-level RS) based on multi-turn conversations, tracking evolving user intent via multi-turn interactions for fine-grained segmentation. To establish a benchmark for this novel task, we build a Pixel-level ReasonIng Segmentation Dataset Based on Multi-Turn Conversations (PRIST), comprising 24k utterances from 8.3k multi-turn conversational scenarios with segmentation targets. Building on PRIST, we further propose MIRAS, a Multi-turn Interactive ReAsoning Segmentation framework, integrates pixel-level segmentation with robust multi-turn conversation understanding, generating pixel-grounded explanations aligned with user intent. The PRIST dataset and MIRSA framework fill the gap in pixel-level reasoning segmentation. Experimental results on the PRIST dataset demonstrate that our method outperforms current segmentation-specific baselines in terms of segmentation and LLM-based reasoning metrics. The code and data are available at: https://anonymous.4open.science/r/PixelRS/.
%R 10.18653/v1/2025.acl-long.864
%U https://aclanthology.org/2025.acl-long.864/
%U https://doi.org/10.18653/v1/2025.acl-long.864
%P 17660-17679
Markdown (Informal)
[Pixel-Level Reasoning Segmentation via Multi-turn Conversations](https://aclanthology.org/2025.acl-long.864/) (Cai et al., ACL 2025)
ACL
- Dexian Cai, Xiaocui Yang, YongKang Liu, Daling Wang, Shi Feng, Yifei Zhang, and Soujanya Poria. 2025. Pixel-Level Reasoning Segmentation via Multi-turn Conversations. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17660–17679, Vienna, Austria. Association for Computational Linguistics.