SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.01146 · 2023

AVSegFormer: Audio-Visual Segmentation with Transformer

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.01146")
get_code_for_paper("2307.01146")
have("2307.01146")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2307.01146.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2307.01146.svg)](https://syntology.ai/paper/2307.01146)

Connect an agent — have() is free.