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

Authors: Zhangbin Li, Jinxing Zhou, Jing Zhang, Shengeng Tang, Kun Li, Dan Guo

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on standard datasets demonstrate the effectiveness of our method, achieving competitive performance even compared to recent large-scale pretraining-based approaches. Extensive quantitative and qualitative results validate the effectiveness of our method.
Researcher Affiliation Academia School of Computer Science and Information Engineering, Hefei University of Technology EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes the methodology using textual explanations and mathematical formulations, but it does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code, nor does it provide links to a code repository or mention code in supplementary materials.
Open Datasets Yes We primarily conduct experiments on the widely-used and challenging MUSICAVQA (Li et al. 2022) dataset.
Dataset Splits Yes Following the standard protocol in the pioneering work (Li et al. 2022), we adopt the answer prediction accuracy (%) as the metric for model evaluation.
Hardware Specification Yes All experiments are conducted on an NVIDIA A40 GPU.
Software Dependencies No The paper mentions models and optimizers like CLIP-Vi T-L/14, CLAP, and Adam W optimizer, but it does not provide specific version numbers for core software dependencies such as programming languages (e.g., Python), deep learning frameworks (e.g., PyTorch, TensorFlow), or CUDA.
Experiment Setup Yes During model training, we use the Adam W optimizer with an initial learning rate of 1e-4, which decays by 0.1 every 16 epochs. The batch size and epochs are set to 16 and 35, respectively. The numbers of graph layers in Gm t , Gs t , and Gq t are empirically set to 3, 3, and 2, respectively.