Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models
On the map: Multimodal LLMs / vision-language models → Video understanding with MLLMs
Abstract (arXiv)
In this technical report, we introduce a framework to address Grounded Video Question Answering (GVQA) task for the ICCV 2025 Perception Test Challenge. The GVQA task demands robust multimodal models capable of complex reasoning over video content, grounding the resulting answers visually, and tracking the referenced objects temporally. To achieve this capability, our proposed approach decomposes the GVQA task into a three-stage pipeline: (1) Video Reasoning & QA, (2) Spatio-temporal Grounding and (3) Tracking. Our key contribution is the introduction of a trigger moment, derived from our proposed CORTEX prompt, which pinpoints the single most visible frame of a target object to serve as a robust anchor for grounding and tracking. To this end, we achieve the HOTA score of 0.4968, which marks a significant improvement over the previous year's winning score of 0.2704 on GVQA task.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 8 of its 10 references that are in the map. First posted on arXiv 4 Nov 2025.
Builds on
8 of 10 references.
References · 8
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
- 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
- 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 321
- 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 310
- 2023Can I Trust Your Answer? Visually Grounded Video Question Answeringcited by 133
- 2025Cross-modal Causal Relation Alignment for Video Question Groundingcited by 12
- 2024Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmarkcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering
- 2025Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in
- 2025MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering
- 2024Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering
- 2025Bridging Vision Language Models and Symbolic Grounding for Video Question Answering
- 2023Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios
- 2025CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models
- 2026VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification