GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Minghan, Chen, Tongna, Lv, Tianrui, Zhang, Yishuai, An, Suchao, Zhou, Guodong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912967218429952
author Li, Minghan
Chen, Tongna
Lv, Tianrui
Zhang, Yishuai
An, Suchao
Zhou, Guodong
author_facet Li, Minghan
Chen, Tongna
Lv, Tianrui
Zhang, Yishuai
An, Suchao
Zhou, Guodong
contents Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We introduce GenState-AI, an AI-generated benchmark centered on controlled state transitions, where each query is paired with a main video, a temporal hard negative that differs only in the decisive end-state, and a semantic hard negative with content substitution, enabling fine-grained diagnosis of temporal vs. semantic confusions beyond appearance matching. Using Wan2.2-TI2V-5B, we generate short clips whose meaning depends on precise changes in position, quantity, and object relations, providing controllable evaluation conditions for state-aware retrieval. We evaluate two representative MLLM-based baselines, and observe consistent and interpretable failure patterns: both frequently confuse the main video with the temporal hard negative and over-prefer temporally plausible but end-state-incorrect clips, indicating insufficient grounding to decisive end-state evidence, while being comparatively less sensitive to semantic substitutions. We further introduce triplet-based diagnostic analyses, including relative-order statistics and breakdowns across transition categories, to make temporal vs. semantic failure sources explicit. GenState-AI provides a focused testbed for state-aware, temporally and semantically sensitive text-to-video retrieval, and will be released on huggingface.co.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14426
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
Li, Minghan
Chen, Tongna
Lv, Tianrui
Zhang, Yishuai
An, Suchao
Zhou, Guodong
Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We introduce GenState-AI, an AI-generated benchmark centered on controlled state transitions, where each query is paired with a main video, a temporal hard negative that differs only in the decisive end-state, and a semantic hard negative with content substitution, enabling fine-grained diagnosis of temporal vs. semantic confusions beyond appearance matching. Using Wan2.2-TI2V-5B, we generate short clips whose meaning depends on precise changes in position, quantity, and object relations, providing controllable evaluation conditions for state-aware retrieval. We evaluate two representative MLLM-based baselines, and observe consistent and interpretable failure patterns: both frequently confuse the main video with the temporal hard negative and over-prefer temporally plausible but end-state-incorrect clips, indicating insufficient grounding to decisive end-state evidence, while being comparatively less sensitive to semantic substitutions. We further introduce triplet-based diagnostic analyses, including relative-order statistics and breakdowns across transition categories, to make temporal vs. semantic failure sources explicit. GenState-AI provides a focused testbed for state-aware, temporally and semantically sensitive text-to-video retrieval, and will be released on huggingface.co.
title GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
topic Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
url https://arxiv.org/abs/2603.14426