CVMMNov 18, 2024

Towards Open-Vocabulary Audio-Visual Event Localization

arXiv:2411.11278v333 citationsh-index: 16CVPR
Originality Incremental advance
AI Analysis

This work addresses the limitation of closed-set models in handling unseen event categories for researchers and practitioners in multimodal AI, though it is incremental as it builds on prior open-set approaches by adding explicit semantics.

The paper tackles the problem of audio-visual event localization in an open-vocabulary setting, enabling explicit category prediction for both seen and unseen events, and introduces a new dataset (OV-AVEBench with 24,800 videos across 67 scenes) and baseline methods, achieving results that demonstrate feasibility but without specific performance numbers.

The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL) problem, which requires localizing audio-visual events and predicting explicit categories for both seen and unseen data at inference. To address this new task, we propose the OV-AVEBench dataset, comprising 24,800 videos across 67 real-life audio-visual scenes (seen:unseen = 46:21), each with manual segment-level annotation. We also establish three evaluation metrics for this task. Moreover, we investigate two baseline approaches, one training-free and one using a further fine-tuning paradigm. Specifically, we utilize the unified multimodal space from the pretrained ImageBind model to extract audio, visual, and textual (event classes) features. The training-free baseline then determines predictions by comparing the consistency of audio-text and visual-text feature similarities. The fine-tuning baseline incorporates lightweight temporal layers to encode temporal relations within the audio and visual modalities, using OV-AVEBench training data for model fine-tuning. We evaluate these baselines on the proposed OV-AVEBench dataset and discuss potential directions for future work in this new field.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes