UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022
Not on the map. Why?
Abstract (arXiv)
This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Unified Context Network (UniCon) and Extended UniCon which are designed for robust scene-level ASD. We augment the architecture with a simple GRU-based module that allows information of recurring identities to flow across scenes through read and update operations. We report a best result of 94.47% mAP on the AVA-ActiveSpeaker test set, which continues to rank first on this year's challenge leaderboard and significantly pushes the state-of-the-art.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 25 references that are in the map. First posted on arXiv 22 Jun 2022.
Builds on
17 of 25 references.
References · 17
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
- 2021Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detectioncited by 113
- 2019AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detectioncited by 83
- 2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 74
- 2020Active Speakers in Contextcited by 41
- 2021MAAS: Multi-modal Assignation for Active Speaker Detectioncited by 36
- 2021How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wildcited by 31
- 2021UniCon: Unified Context Network for Robust Active Speaker Detectioncited by 28
5 more
- 2019Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)cited by 26
- 2022End-to-End Active Speaker Detectioncited by 25
- 2021Learning Spatial-Temporal Graphs for Active Speaker Detectioncited by 4
- 2021APES: Audiovisual Person Search in Untrimmed Videocited by 3
- 2021Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusioncited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.