mlsanityData to 7 Oct 2026

Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023

arXiv 2306.08998 ↗First posted 15 Jun 2023cs.SD cs.CV eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

In this report, we describe the technical details of our submission to the EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023, by Team "AcieLee" (username: YuqiLi). The task is to classify the audio caused by interactions between objects, or from events of the camera wearer. We conducted exhaustive experiments and found learning rate step decay, backbone frozen, label smoothing and focal loss contribute most to the performance improvement. After training, we combined multiple models from different stages and integrated them into a single model by assigning fusion weights. This proposed method allowed us to achieve 3rd place in the CVPR 2023 workshop of EPIC-SOUNDS Audio-Based Interaction Recognition Challenge.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

21 of 30 references.

References · 21

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  4. 2019When Does Label Smoothing Help?cited by 985
  5. 2017Focal Loss for Dense Object Detectioncited by 749
  6. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  7. 2020Rescaling Egocentric Visioncited by 529
  8. 2020ResNeSt: Split-Attention Networkscited by 445
  9. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  10. 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
  11. 2022Cross-Image Relational Knowledge Distillation for Semantic Segmentationcited by 117
  12. 2019The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squarescited by 67
9 more
  1. 2022MixGen: A New Multi-Modal Data Augmentationcited by 61
  2. 2023Epic-Sounds: A Large-scale Dataset of Actions That Soundcited by 47
  3. 2021Hierarchical Self-supervised Augmented Knowledge Distillationcited by 44
  4. 2021Mutual Contrastive Learning for Visual Representation Learningcited by 42
  5. 2022Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognitioncited by 36
  6. 2022MixSKD: Self-Knowledge Distillation from Mixup for Image Recognitioncited by 30
  7. 2022M&M Mix: A Multimodal Multiview Transformer Ensemblecited by 19
  8. 2019Gated Convolutional Networks with Hybrid Connectivity for Image Classificationcited by 14
  9. 2020The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)cited by 6

Built on by

Not cited yet.