# Patch-level Sounding Object Tracking for Audio-Visual Question Answering

arXiv: https://arxiv.org/abs/2412.10749 · HTML: https://mlsanity.com/paper/2412.10749/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videos](https://mlsanity.com/paper/2110.05122/) (2021)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [Vision Transformers are Parameter-Efficient Audio-Visual Learners](https://mlsanity.com/paper/2212.07983/) (2022)
- [Positive Sample Propagation along the Audio-Visual Event Line](https://mlsanity.com/paper/2104.00239/) (2021)
- [Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering](https://mlsanity.com/paper/2104.14085/) (2021)
- [A Simple Baseline for Audio-Visual Scene-Aware Dialog](https://mlsanity.com/paper/1904.05876/) (2019)
- [Contrastive Positive Sample Propagation along the Audio-Visual Event Line](https://mlsanity.com/paper/2211.09980/) (2022)
- [TAVGBench: Benchmarking Text to Audible-Video Generation](https://mlsanity.com/paper/2404.14381/) (2024)
- [Contrastive Video Question Answering via Video Graph Transformer](https://mlsanity.com/paper/2302.13668/) (2023)
- [Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks](https://mlsanity.com/paper/2311.05152/) (2023)
- [Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture](https://mlsanity.com/paper/2403.07347/) (2024)
- [Towards Open-Vocabulary Audio-Visual Event Localization](https://mlsanity.com/paper/2411.11278/) (2024)
- [Label-anticipated Event Disentanglement for Audio-Visual Video Parsing](https://mlsanity.com/paper/2407.08126/) (2024)
- [Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling](https://mlsanity.com/paper/2406.00919/) (2024)
- [Improving Audio-Visual Video Parsing with Pseudo Visual Labels](https://mlsanity.com/paper/2303.02344/) (2023)
- [Hierarchical Conditional Relation Networks for Multimodal Video Question Answering](https://mlsanity.com/paper/2010.10019/) (2020)
- [Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios](https://mlsanity.com/paper/2305.12397/) (2023)

## Built on by (most cited first, 13 of 13)

- [Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration](https://mlsanity.com/paper/2412.12628/) (2024)
- [Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation](https://mlsanity.com/paper/2506.23271/) (2025)
- [SimToken: A Simple Baseline for Referring Audio-Visual Segmentation](https://mlsanity.com/paper/2509.17537/) (2025)
- [AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering](https://mlsanity.com/paper/2510.18346/) (2025)
- [Spatial Audio Motion Understanding and Reasoning](https://mlsanity.com/paper/2509.14666/) (2025)
- [Query-Guided Spatial-Temporal-Frequency Interaction for Music Audio-Visual Question Answering](https://mlsanity.com/paper/2601.19821/) (2026)
- [Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation](https://mlsanity.com/paper/2602.03892/) (2026)
- [RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition](https://mlsanity.com/paper/2503.03104/) (2025)
- [Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization](https://mlsanity.com/paper/2603.14750/) (2026)
- [CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment](https://mlsanity.com/paper/2602.08309/) (2026)
- [AV-Unified: A Unified Framework for Audio-visual Scene Understanding](https://mlsanity.com/paper/2603.06530/) (2026)
- [Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026](https://mlsanity.com/paper/2608.22337/) (2026)
- [Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation](https://mlsanity.com/paper/2610.12783/) (2026)

## Abstract (arXiv)

Answering questions related to audio-visual scenes, i.e., the AVQA task, is becoming increasingly popular. A critical challenge is accurately identifying and tracking sounding objects related to the question along the timeline. In this paper, we present a new Patch-level Sounding Object Tracking (PSOT) method. It begins with a Motion-driven Key Patch Tracking (M-KPT) module, which relies on visual motion information to identify salient visual patches with significant movements that are more likely to relate to sounding objects and questions. We measure the patch-wise motion intensity map between neighboring video frames and utilize it to construct and guide a motion-driven graph network. Meanwhile, we design a Sound-driven KPT (S-KPT) module to explicitly track sounding patches. This module also involves a graph network, with the adjacency matrix regularized by the audio-visual correspondence map. The M-KPT and S-KPT modules are performed in parallel for each temporal segment, allowing balanced tracking of salient and sounding objects. Based on the tracked patches, we further propose a Question-driven KPT (Q-KPT) module to retain patches highly relevant to the question, ensuring the model focuses on the most informative clues. The audio-visual-question features are updated during the processing of these modules, which are then aggregated for final answer prediction. Extensive experiments on standard datasets demonstrate the effectiveness of our method, achieving competitive performance even compared to recent large-scale pretraining-based approaches.