# AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes

arXiv: https://arxiv.org/abs/2610.01861 · HTML: https://mlsanity.com/paper/2610.01861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2311.13165/) (2023)
- [Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale](https://mlsanity.com/paper/1812.00417/) (2018)
- [Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions](https://mlsanity.com/paper/2308.14263/) (2023)
- [Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning](https://mlsanity.com/paper/2309.11500/) (2023)
- [Automated Audio Captioning: An Overview of Recent Progress and New Challenges](https://mlsanity.com/paper/2205.05949/) (2022)
- [AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models](https://mlsanity.com/paper/2411.18953/) (2024)
- [A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis](https://mlsanity.com/paper/2011.00030/) (2020)
- [Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions](https://mlsanity.com/paper/2407.04416/) (2024)
- [Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments](https://mlsanity.com/paper/2307.07757/) (2023)

## Abstract (arXiv)

Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory and visual information remain limited. In this paper, we introduce AVSD-Scenes, a paired audio-visual scene description dataset for urban environments. The dataset contains 12,291 audio-visual scene descriptions generated from the TAU Urban Audio-Visual Scenes dataset. To construct the dataset, we first generate audio- and visual-based descriptions using Qwen2-Audio-7B and Qwen2.5-VL-7B, respectively. These modality-specific descriptions are then combined using large language models, namely Qwen3-14B, Mistral-Small-3.2-24B-Instruct-2506, and Gemma-3-27B-it, to produce multimodal descriptions that capture complementary information from both modalities. We benchmark AVSD-Scenes using semantic alignment, cross-modal retrieval, scene classification, LLM-as-a-judge evaluation, and human subjective assessment. Results show that multimodal descriptions improve semantic alignment and cross-modal retrieval performance compared with modality-specific descriptions while preserving strong scene-discriminative information. The generated descriptions achieve up to 94.5% accuracy in urban scene classification, while combining audio, visual, and description embeddings further improves accuracy to 95.4%. Furthermore, the descriptions remain highly scene-discriminative even when scene labels are removed from the prompting instructions, indicating that they capture semantic information derived from the audio-visual content rather than merely reflecting label information.