Saved in:
Bibliographic Details
Main Authors: Liu, Jinyuan, Wang, Yang, Zhao, Zeyu, Li, Weixin, Wang, Song, Han, Ruize
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11411
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917403060862976
author Liu, Jinyuan
Wang, Yang
Zhao, Zeyu
Li, Weixin
Wang, Song
Han, Ruize
author_facet Liu, Jinyuan
Wang, Yang
Zhao, Zeyu
Li, Weixin
Wang, Song
Han, Ruize
contents Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded references. However, existing methods are developed and evaluated in an offline regime, where the entire video is available at inference time and future frames can be exploited for retrospective disambiguation, deviating from real-world deployments that require strictly causal, frame-by-frame decisions. We study Online Reasoning Video Object Segmentation (ORVOS), where models must incrementally interpret queries using only past and current frames without revisiting previous predictions, while handling referent shifts as events unfold. To support evaluation, we introduce ORVOSB, a benchmark with frame-level causal annotations and referent-shift labels, comprising 210 videos, 12,907 annotated frames, and 512 queries across five reasoning categories. We further propose a baseline with continually-updated segmentation prompts and a structured temporal token reservoir for long-horizon reasoning under bounded computation. Experiments show that existing methods struggle under strict causality and referent shifts, while our baseline establishes a strong foundation for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11411
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Online Reasoning Video Object Segmentation
Liu, Jinyuan
Wang, Yang
Zhao, Zeyu
Li, Weixin
Wang, Song
Han, Ruize
Computer Vision and Pattern Recognition
Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded references. However, existing methods are developed and evaluated in an offline regime, where the entire video is available at inference time and future frames can be exploited for retrospective disambiguation, deviating from real-world deployments that require strictly causal, frame-by-frame decisions. We study Online Reasoning Video Object Segmentation (ORVOS), where models must incrementally interpret queries using only past and current frames without revisiting previous predictions, while handling referent shifts as events unfold. To support evaluation, we introduce ORVOSB, a benchmark with frame-level causal annotations and referent-shift labels, comprising 210 videos, 12,907 annotated frames, and 512 queries across five reasoning categories. We further propose a baseline with continually-updated segmentation prompts and a structured temporal token reservoir for long-horizon reasoning under bounded computation. Experiments show that existing methods struggle under strict causality and referent shifts, while our baseline establishes a strong foundation for future research.
title Online Reasoning Video Object Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.11411