paper-with-me

Papers

Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos

2025-07-16 · Yuchi Ishikawa, Shota Nakada, Hokuto Munakata, Kazuhiro Saito, Tatsuya Komatsu, Yoshimitsu Aoki

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 pretrained text encoder into contrastive audio-visual masked autoencoders, enabling the model to learn across audio, visual and text modalities. To train LG-CAV-MAE, we introduce an automatic method to generate audio-visual-text triplets from unlabeled videos. We first generate frame-level captions using an image captioning model and then apply CLAP-based filtering to ensure strong alignment between audio and captions. This approach yields high-quality audio-visual-text triplets without requiring manual annotations. We evaluate LG-CAV-MAE on audio-visual retrieval tasks, as well as an audio-visual classification task. Our method significantly outperforms existing approaches, achieving up to a 5.6% improvement in recall@10 for retrieval tasks and a 3.2% improvement for the classification task.

📄 PDF Abstract BibTeX arXiv:2507.11967

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningRepresentation LearningRetrieval

Similar Papers 제목 키워드 기반

Contrastive Audio-Visual Masked Autoencoder

2022-10-02 · Yuan Gong, Andrew Rouditchenko, Alexander H. Liu, David Harwath 외

In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by co…

Audio ClassificationAudio TaggingContrastive LearningMulti-modal Classification+4

Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning

2026-04-09 · Linge Wang, Yingying Chen, Bingke Zhu, Lu Zhou 외 arxiv

Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, jointly optimizing these objectives in a single forward pass forces the…

Representation LearningVideo Retrieval

Text-Guided Video Masked Autoencoder

2024-08-01

Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such…

TVLT: Textless Vision-Language Transformer

2022-09-28 · Zineng Tang, Jaemin Cho, Yixin Nie, Mohit Bansal

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specif…

Automatic Speech Recognition (ASR)Image RetrievalMultimodal Sentiment AnalysisQuestion Answering+5

HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

2024-01-11 · Licai Sun, Zheng Lian, Bin Liu, JianHua Tao

Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines. Previous efforts in this area are dominated by the supervised…

Contrastive LearningDynamic Facial Expression RecognitionEmotion RecognitionRepresentation Learning+1