paper-with-me

홈 › Papers

Audio-Visual LLM for Video Understanding

2023-12-11 · Fangxun Shu, Lei Zhang, Hao Jiang, Cihang Xie

This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of modality-specific tokens engineered to activate the appropriate visual and/or auditory encoder selectively. This mechanism is pivotal in enabling end-to-end joint training with video data at different modalities, including visual-only, audio-only, and audio-visual formats. Moreover, we introduce a high-quality video instruction dataset, derived from GPT-4. This dataset allows Audio-Visual LLM to adeptly process a variety of task-oriented video instructions, ranging from multi-turn conversations and audio-visual narratives to complex reasoning tasks. Extensive experiments demonstrate that Audio-Visual LLM impressively achieves strong zero-shot results across a range of video understanding tasks. For example, Audio-Visual LLM achieves an accuracy of 53.7% on MSRVTT-QA, outperforming non-LLM-based InterVideo by 6.6% and LLM-based Valley by 4.4%, respectively. Additionally, our Audio-Visual LLM also achieves competitive performance on audio tasks (e.g., AudioCaps).

📄 PDF Abstract BibTeX arXiv:2312.06720

Code (0)

등록된 구현이 없습니다.

Tasks

AudioCapsLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelVideo Understanding

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context

2024-11-25 · Jungang Li, Sicheng Tao, Yibo Yan, Xiaojie Gu 외

Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively int…

Large Language ModelMMEVideo MMEVideo Understanding

ACVUBench: Audio-Centric Video Understanding Benchmark

2025-03-25 · Yudong Yang, Jimin Zhuang, Guangzhi Sun, Changli Tang 외

Audio often serves as an auxiliary modality in video understanding tasks of audio-visual large language models (LLMs), merely assisting in the comprehension of visual information. However, a thorough understanding of vid…

Video Understanding

Aligned Better, Listen Better for Audio-Visual Large Language Models

2025-04-02 · Yuxin Guo, Shuailei Ma, Shijie Ma, Xiaoyi Bao 외

Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter…

Video Understanding

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding

2024-03-24 · Yunlong Tang, Daiki Shimada, Jing Bi, Mingqian Feng 외

Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video …

Dense Video CaptioningTemporal LocalizationVideo CaptioningVideo Understanding

video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models

2024-06-22 · Guangzhi Sun, Wenyi Yu, Changli Tang, Xianzhao Chen 외

Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end a…

DiversityLanguage ModelingLanguage ModellingLarge Language Model+1