Decompose the Sounds and Pixels, Recompose the Events
Varshanth R. Rao, Md Ibrahim Khalil, Haoda Li, Peng Dai, Juwei Lu
Abstract
In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recomposition Network (EDRNet) to tackle the Audio-Visual Event (AVE) localization problem in the supervised and weakly supervised settings. AVEs in the real world exhibit common unravelling patterns (termed as Event Progress Checkpoints (EPC)), which humans can perceive through the cooperation of their auditory and visual senses. Unlike earlier methods which attempt to recognize entire event sequences, the EDR-Net models EPCs and inter-EPC relationships using stacked temporal convolutions. Based on the postulation that EPC representations are theoretically consistent for an event category, we introduce the State Machine Based Video Fusion, a novel augmentation technique that blends source videos using different EPC template sequences. Additionally, we design a new loss function called the Land-Shore-Sea loss to compactify continuous foreground and background representations. Lastly, to alleviate the issue of confusing events during weak supervision, we propose a prediction stabilization method called Bag to Instance Label Correction. Experiments on the AVE dataset show that our collective framework outperforms the state-of-the-art by a sizable margin.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- A Light Weight Model for Active Speaker Detection cites LoCoNet: Long-Short Context Network for Active Speaker Detection
- LoCoNet: Long-Short Context Network for Active Speaker Detection cites A Light Weight Model for Active Speaker Detection
Cited by top-tier papers2
Builds on2
Related papers
- Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action LocalizationJun-Tae Lee, Mihir Jain, Hyoungwoo Park, Sungrack YunICLR 2021 · 73 citations
- Learning Event-Specific Localization Preferences for Audio-Visual Event LocalizationShiping Ge, Zhiwei Jiang, Yafeng Yin, Cong Wang et al.ACM MM 2023 · 12 citations
- Cross-modal Background Suppression for Audio-Visual Event LocalizationYan Xia, Zhou ZhaoCVPR 2022 · 62 citations
- CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event LocalizationXiang He, Xiangxi Liu, Yang Li, Dongcheng Zhao et al.ACM MM 2024 · 8 citations
- CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event LocalizationJinxing Zhou, Ziheng Zhou, Yanghao Zhou, Yuxin Mao et al.AAAI 2026 · 4 citations
