DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
Video multimodal large language models struggle with precise local spatiotemporal perception when videos differ only in a short time span or small region. DELTAVID converts cross-video spot-the-difference into a trainable perception signal, and introduces DELTAVID-10K and DELTAVID-Bench for scalable training and evaluation. Experiments show improvements on multiple video understanding benchmarks, moving models toward fine-grained evidence reasoning.
-->
[Submitted on 26 Jun 2026]
Title:DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
View a PDF of the paper titled DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences, by Yankai Yang and 6 other authors
View PDF HTML (experimental)
Abstract:Video multimodal large language models have made strong progress on open-ended video understanding, but they still lack precise local spatiotemporal perception. When two videos share almost the same global semantics and differ only in a short time span or a small region, current models often fail to find the change and provide reliable evidence. We propose DELTAVID, a verifiable proxy-task framework that enhances fine-grained spatiotemporal perception with cross-video differences. The key idea is to turn cross-video spot-the-difference into a trainable perception signal, where a model identifies local changes, judges temporal boundaries, and organizes spatial evidence by comparing similar videos. To make this signal scalable to train and reliable to evaluate, we further introduce DELTAVID-10K and DELTAVID-Bench, which convert controllable local differences in real videos into evidence-labeled training and test samples. Experiments show that DELTAVID substantially improves performance on cross-video difference understanding and transfers the learned local evidence ability to general video understanding benchmarks, including MMVU, MLVU, Video-MME, VideoHolmes, VideoMMMU, LVBench, TempCompass, and LongVideoBench. These results show that cross-video differences are not only an effective way to diagnose fine-grained perception failures, but also a scalable proxy supervision that moves Video MLLMs from coarse semantic understanding toward fine-grained spatiotemporal evidence reasoning.
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.02551 [cs.CV]
(or arXiv:2607.02551v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.02551
arXiv-issued DOI via DataCite
Submission history
From: Yankai Yang [view email] [v1] Fri, 26 Jun 2026 16:05:57 UTC (17,660 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences, by Yankai Yang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-07
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)