paper-with-me

Papers

CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios

2024-03-07 · Qilang Ye, Zitong Yu, Rui Shao, Xinyu Xie, Philip Torr, Xiaochun Cao

This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowledge required for large language models. 2) CAT is trained on a mixed multimodal dataset, allowing direct application in audio-visual scenarios. Notably, we collect an audio-visual joint instruction dataset named AVinstruct, to further enhance the capacity of CAT to model cross-semantic correlations. 3) we propose AI-assisted ambiguity-aware direct preference optimization, a strategy specialized in retraining the model to favor the non-ambiguity response and improve the ability to localize specific audio-visual objects. Extensive experimental results demonstrate that CAT outperforms existing methods on multimodal tasks, especially in Audio-Visual Question Answering (AVQA) tasks. The codes and the collected instructions are released at https://github.com/rikeilong/Bay-CAT.

📄 PDF Abstract BibTeX arXiv:2403.04640

Code (1)

rikeilong/bay-cat 공식 구현 pytorch

Tasks

Audio-visual Question AnsweringAudio-Visual Question Answering (AVQA)Language ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelQuestion AnsweringVideo-based Generative Performance BenchmarkingVisual Question AnsweringZero-Shot Video Question Answer

Similar Papers 제목 키워드 기반

LOVA3: Learning to Visual Question Answering, Asking and Assessment

2024-05-23 · Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Zechen Bai 외

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to …

Question AnsweringVisual Question Answering

LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning

2024-08-15 · Jiajie Li, Garrett Skinner, Gene Yang, Brian R Quaranto 외

Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal model…

Answer GenerationQuestion-Answer-GenerationQuestion AnsweringVideo Question Answering

Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches

2023-09-21 · Deepak Gupta, Kush Attal, Dina Demner-Fushman

The increase in the availability of online videos has transformed the way we access information and knowledge. A growing number of individuals now prefer instructional videos as they offer a series of step-by-step proced…

Visual Question Decomposition on Multimodal Large Language Models

2024-09-28 · Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen 외

Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the questio…

Visual Question Answering (VQA)

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models

2024-05-22 · Qiji Zhou, Ruochen Zhou, Zike Hu, Panzhong Lu 외

Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Lar…

Multimodal ReasoningVisual Question AnsweringVisual Reasoning