Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Video Question AnsweringSimilar Papers 제목 키워드 기반
TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors
Dense video captioning aims to interpret and describe all temporally localized events throughout an input video. Recent state-of-the-art methods leverage large language models (LLMs) to provide detailed moment descriptio…
Dense Video CaptioningMoment RetrievalMomentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. How…
Language ModelingLanguage ModellingLarge Language ModelGrounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection
Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements intr…
Action DetectionDecoderMoment RetrievalNatural Language Queries+3D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching
Videos showcasing specific products are increasingly important for E-commerce. Key moments naturally exist as the first appearance of a specific product, presentation of its distinctive features, the presence of a buying…
Highlight DetectionMoment RetrievalBackground-aware Moment Detection for Video Moment Retrieval
Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query. This task is prone to suffer the weak alignment problem innate in video datasets. Due to the ambiguity, …
Moment RetrievalNatural Language Moment RetrievalRetrieval