LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
This work addresses a bottleneck in multimodal captioning for applications like accessibility or content analysis, but it is incremental as it builds on existing audio-visual methods with a novel fusion technique.
The paper tackles the problem of ineffective fusion of audio and visual data in automated audio captioning by introducing LAVCap, an LLM-based framework that uses optimal transport for alignment and attention, resulting in improved performance on the AudioCaps dataset.
Automated audio captioning is a task that generates textual descriptions for audio content, and recent studies have explored using visual information to enhance captioning quality. However, current methods often fail to effectively fuse audio and visual data, missing important semantic cues from each modality. To address this, we introduce LAVCap, a large language model (LLM)-based audio-visual captioning framework that effectively integrates visual information with audio to improve audio captioning performance. LAVCap employs an optimal transport-based alignment loss to bridge the modality gap between audio and visual features, enabling more effective semantic extraction. Additionally, we propose an optimal transport attention module that enhances audio-visual fusion using an optimal transport assignment map. Combined with the optimal training strategy, experimental results demonstrate that each component of our framework is effective. LAVCap outperforms existing state-of-the-art methods on the AudioCaps dataset, without relying on large datasets or post-processing. Code is available at https://github.com/NAVER-INTEL-Co-Lab/gaudi-lavcap.