7 papers
Hallucination Localization in Video Captioning
Shota Nakada, Kazuhiro Saito, Yuchi Ishikawa +3
We propose a novel task, hallucination localization in video captioning, which aims to identify hallucinations in video captions at the span level (i.e. individual words or phrases…
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
Yuchi Ishikawa, Shota Nakada, Hokuto Munakata +3
In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrai…
DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information
Shota Nakada, Taichi Nishimura, Hokuto Munakata +2
Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details…
Language-based Audio Moment Retrieval
Hokuto Munakata, Taichi Nishimura, Shota Nakada +1
In this paper, we propose and design a new task called audio moment retrieval (AMR). Unlike conventional language-based audio retrieval tasks that search for short audio clips from…
Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
Taichi Nishimura, Shota Nakada, Hokuto Munakata +1
We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the…
On the Audio Hallucinations in Large Audio-Video Language Models
Taichi Nishimura, Shota Nakada, Masayoshi Kondo
Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on v…
Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval
Taichi Nishimura, Shota Nakada, Masayoshi Kondo
In this paper, we propose an efficient and high-performance method for partially relevant video retrieval, which aims to retrieve long videos that contain at least one moment relev…