Papers with Code · CC BY-SA 4.0

AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)

Audio-visual Question Answering › AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0) 5 평가 기록 1 datasets

A more reliable and balanced version of original MUSIC-AVQA benchmark for Audio-Visual Question Answering, proposed in the paper "Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering"

논문

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

2203.14072 2022-03-26 이 페이지의 평가 1건

Accuracy: 71.02

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

2407.01851 2024-07-01 이 페이지의 평가 1건

Accuracy: 79.15

Question-Aware Gaussian Experts for Audio-Visual Question Answering

2503.04459 2025-03-06 이 페이지의 평가 1건

Accuracy: 76.43

Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering

2310.06238 2023-10-10 이 페이지의 평가 1건

Accuracy: 75.44

Vision Transformers are Parameter-Efficient Audio-Visual Learners

2212.07983 2022-12-15 이 페이지의 평가 1건

Accuracy: 73.18