paper-with-me

Papers

Zero-Shot Video Question Answering with Procedural Programs

2023-12-01 · Rohan Choudhury, Koichiro Niinuma, Kris M. Kitani, László A. Jeni

We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. We present Procedural Video Querying (ProViQ), which uses a large language model to generate such programs from an input question and an API of visual modules in the prompt, then executes them to obtain the output. Recent similar procedural approaches have proven successful for image question answering, but videos remain challenging: we provide ProViQ with modules intended for video understanding, allowing it to generalize to a wide variety of videos. This code generation framework additionally enables ProViQ to perform other video tasks in addition to question answering, such as multi-object tracking or basic video editing. ProViQ achieves state-of-the-art results on a diverse range of benchmarks, with improvements of up to 25% on short, long, open-ended, and multimodal video question-answering datasets. Our project page is at https://rccchoudhury.github.io/proviq2023.

📄 PDF Abstract BibTeX arXiv:2312.00937

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationLanguage ModelingLanguage ModellingLarge Language ModelMulti-Object TrackingObject TrackingQuestion AnsweringVideo EditingVideo Question AnsweringVideo UnderstandingVisual Question Answering (VQA)Zero-Shot Video Question Answer

Similar Papers 제목 키워드 기반

ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation

2025-05-21 · Tony Montes, Fernando Lozano

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 mech…

Decision MakingLanguage ModelingLanguage ModellingObject Tracking+3

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

2022-06-16 · Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev 외

Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle thi…

Fill MaskLanguage ModelingLanguage ModellingMasked Language Modeling+8

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

2024-09-30 · Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai 외

In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-to-end models. However, long video under…

EgoSchemaLanguage ModellingLarge Language ModelQuestion Answering+3

BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding

2026-05-12 · Patrick Knab, Orgest Xhelili, Inis Buzi, Drago Andres Guggiana Nilo 외 arxiv

Scene understanding is central to general physical intelligence, and video is a primary modality for capturing both state and temporal dynamics of a scene. Yet understanding physical processes remains difficult, as model…

Visual Question AnsweringActivity RecognitionObject LocalizationScene Understanding

Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts

2023-09-27 · Deniz Engin, Yannis Avrithis

Recent vision-language models are driven by large-scale pretrained models. However, adapting pretrained models on limited data presents challenges such as overfitting, catastrophic forgetting, and the cross-modal gap bet…

Few-shot Video Question AnsweringPrompt LearningQuestion AnsweringVideo Question Answering+1