Saved in:
Bibliographic Details
Main Authors: Montes, Tony, Lozano, Fernando
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.15928
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915297713192960
author Montes, Tony
Lozano, Fernando
author_facet Montes, Tony
Lozano, Fernando
contents Recent advancements in Video Question Answering (VideoQA) have introduced LLM-based agents, modular frameworks, and procedural solutions, yielding promising results. These systems use dynamic agents and memory-based mechanisms to break down complex tasks and refine answers. However, significant improvements remain in tracking objects for grounding over time and decision-making based on reasoning to better align object references with language model outputs, as newer models get better at both tasks. This work presents an LLM-brained agent for zero-shot Video Question Answering (VideoQA) that combines a Chain-of-Thought framework with grounding reasoning alongside YOLO-World to enhance object tracking and alignment. This approach establishes a new state-of-the-art in VideoQA and Video Understanding, showing enhanced performance on NExT-QA, iVQA, and ActivityNet-QA benchmarks. Our framework also enables cross-checking of grounding timeframes, improving accuracy and providing valuable support for verification and increased output reliability across multiple video domains. The code is available at https://github.com/t-montes/viqagent.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
Montes, Tony
Lozano, Fernando
Computer Vision and Pattern Recognition
Computation and Language
I.4.8
Recent advancements in Video Question Answering (VideoQA) have introduced LLM-based agents, modular frameworks, and procedural solutions, yielding promising results. These systems use dynamic agents and memory-based mechanisms to break down complex tasks and refine answers. However, significant improvements remain in tracking objects for grounding over time and decision-making based on reasoning to better align object references with language model outputs, as newer models get better at both tasks. This work presents an LLM-brained agent for zero-shot Video Question Answering (VideoQA) that combines a Chain-of-Thought framework with grounding reasoning alongside YOLO-World to enhance object tracking and alignment. This approach establishes a new state-of-the-art in VideoQA and Video Understanding, showing enhanced performance on NExT-QA, iVQA, and ActivityNet-QA benchmarks. Our framework also enables cross-checking of grounding timeframes, improving accuracy and providing valuable support for verification and increased output reliability across multiple video domains. The code is available at https://github.com/t-montes/viqagent.
title ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
topic Computer Vision and Pattern Recognition
Computation and Language
I.4.8
url https://arxiv.org/abs/2505.15928