.png){kind=icon}
.png){kind=icon}
Return
Audio-Visual Segmentation with Semantics
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-024-02261-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source; 2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires to generate semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on the AVSBench dataset compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code can be found at https://github.com/OpenNLPLab/AVSBench.
Keywords:
Audio-visual segmentation
Multi-modal segmentation
Audio-visual learning
AVSBench
Semantic segmentation
Video segmentation
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
View more organizations