paper-with-me

Papers

CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering

2024-05-13 · Yuanyuan Jiang, Jianqin Yin

While vision-language pretrained models (VLMs) excel in various multimodal understanding tasks, their potential in fine-grained audio-visual reasoning, particularly for audio-visual question answering (AVQA), remains largely unexplored. AVQA presents specific challenges for VLMs due to the requirement of visual understanding at the region level and seamless integration with audio modality. Previous VLM-based AVQA methods merely used CLIP as a feature encoder but underutilized its knowledge, and mistreated audio and video as separate entities in a dual-stream framework as most AVQA methods. This paper proposes a new CLIP-powered target-aware single-stream (TASS) network for AVQA using the image-text matching knowledge of the pretrained model through the audio-visual matching characteristic of nature. It consists of two key components: the target-aware spatial grounding module (TSG+) and the single-stream joint temporal grounding module (JTG). Specifically, we propose a TSG+ module to transfer the image-text matching knowledge from CLIP models to our region-text matching process without corresponding ground-truth labels. Moreover, unlike previous separate dual-stream networks that still required an additional audio-visual fusion module, JTG unifies audio-visual fusion and question-aware temporal grounding in a simplified single-stream architecture. It treats audio and video as a cohesive entity and further extends the pretrained image-text knowledge to audio-text matching by preserving their temporal correlation with our proposed cross-modal synchrony (CMS) loss. Extensive experiments conducted on the MUSIC-AVQA benchmark verified the effectiveness of our proposed method over existing state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2405.07451

Code (0)

등록된 구현이 없습니다.

Tasks

Audio-visual Question AnsweringAudio-Visual Question Answering (AVQA)Image-text matchingQuestion AnsweringText MatchingVisual Question AnsweringVisual Reasoning

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation

2026-02-05 · Luoxi Zhang, Chun Xie, Itaru Kitahara arxiv

Implicit SDF-based methods for single-view 3D reconstruction achieve high-quality surfaces but require large labeled datasets, limiting their scalability. We propose MetaSSP, a novel semi-supervised framework that exploi…

Single-View 3D Reconstruction

Towards 3D Semantic Scene Completion for Autonomous Driving: A Meta-Learning Framework Empowered by Deformable Large-Kernel Attention and Mamba Model

2024-11-06 · Yansong Qu, Zilin Huang, Zihao Sheng, Tiantian Chen 외

Semantic scene completion (SSC) is essential for achieving comprehensive perception in autonomous driving systems. However, existing SSC methods often overlook the high deployment costs in real-world applications. Tradit…

3D Semantic Scene CompletionAutonomous DrivingAutonomous VehiclesMamba+2

FrostNet: Towards Quantization-Aware Network Architecture Search

2020-06-17 · Taehoon Kim, Youngjoon Yoo, Jihoon Yang

INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances o…

Object DetectionQuantizationSemantic Segmentation

TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting

2025-09-25 · Xiaonan Hu, Xuebing Li, Jinyu Xu, Abdulkadir Duran Adan 외 arxiv

Accurate plant counting provides valuable information for agriculture such as crop yield prediction, plant density assessment, and phenotype quantification. Vision-based approaches are currently the mainstream solution. …

Crop Yield Prediction

Multi-Task Audio Source Separation

2021-07-14 · Lu Zhang, Chenxing Li, Feng Deng, Xiaorui Wang

The audio source separation tasks, such as speech enhancement, speech separation, and music source separation, have achieved impressive performance in recent studies. The powerful modeling capabilities of deep neural net…

Audio Source SeparationMulti-task Audio Source SeperationMusic Source SeparationSpeech Enhancement+1