mlsanityData to 7 Oct 2026

Slow-Fast Auditory Streams For Audio Recognition

arXiv 2103.03516 ↗First posted 5 Mar 2021cs.SD cs.CV eess.AScited by 56

Not on the map. Why?

Abstract (arXiv)

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state-of-the-art results on both.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 5 Mar 2021.

Builds on

18 of 29 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018SlowFast Networks for Video Recognitioncited by 1,862
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  5. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  6. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  7. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  8. 2016SoundNet: Learning Sound Representations from Unlabeled Videocited by 244
  9. 2020Audiovisual SlowFast Networks for Video Recognitioncited by 144
  10. 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 84
  11. 2019The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classificationcited by 22
  12. 2017Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networkscited by 14
6 more
  1. 2020Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentationcited by 13
  2. 2019State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutionscited by 11
  3. 2017Timbre Analysis of Music Audio Signals with Convolutional Neural Networkscited by 10
  4. 2019Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modelingcited by 9
  5. 2019Multi-stream Network With Temporal Attention For Environmental Sound Classificationcited by 6
  6. 2018Acoustic Features Fusion using Attentive Multi-channel Deep Architecturecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 12; 2024: 12; 2025: 8; 2026: 3.

56 papers.

Sort:

By area:

  1. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  2. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  3. 2021Attention Bottlenecks for Multimodal Fusioncited by 361
  4. 2021Wav2CLIP: Learning Robust Audio Representations From CLIPcited by 210
  5. 2022Contrastive Audio-Visual Masked Autoencodercited by 142
  6. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  7. 2021PolyViT: Co-training Vision Transformers on Images, Videos and Audiocited by 58
  8. 2022MAViL: Masked Audio-Video Learnerscited by 56
  9. 2022Audiovisual Masked Autoencoderscited by 47
  10. 2023Epic-Sounds: A Large-scale Dataset of Actions That Soundcited by 47
  11. 2023PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformercited by 46
  12. 2021With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognitioncited by 41
38 more
  1. 2021Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognitioncited by 35
  2. 2022Supervised and Unsupervised Learning of Audio Representations for Music Understandingcited by 34
  3. 2022UAVM: Towards Unifying Audio and Visual Modelscited by 20
  4. 2025The iNaturalist Sounds Datasetcited by 17
  5. 2023Multiscale Audio Spectrogram Transformer for Efficient Audio Classificationcited by 16
  6. 2024HeAR -- Health Acoustic Representationscited by 15
  7. 2024TIM: A Time Interval Machine for Audio-Visual Action Recognitioncited by 15
  8. 2023Zorro: the masked multimodal transformercited by 13
  9. 2024SoundingActions: Learning How Actions Sound from Narrated Egocentric Videoscited by 11
  10. 2022MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalizationcited by 10
  11. 2022SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognitioncited by 8
  12. 2024Harnessing Temporal Causality for Advanced Temporal Action Detectioncited by 8
  13. 2025Breaking the Encoder Barrier for Seamless Video-Language Understandingcited by 8
  14. 2025TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervisioncited by 8
  15. 2024Exploring Missing Modality in Multimodal Egocentric Datasetscited by 7
  16. 2021V-SlowFast Network for Efficient Visual Sound Separationcited by 6
  17. 2024Egocentric zone-aware action recognition across environmentscited by 6
  18. 2021A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classificationcited by 4
  19. 2022OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videoscited by 4
  20. 2022Learning Temporal Resolution in Spectrogram for Audio Classificationcited by 4
  21. 2023DiffSED: Sound Event Detection with Denoising Diffusioncited by 4
  22. 2024Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classificationcited by 4
  23. 2024Explore the Limits of Omni-modal Pretraining at Scalecited by 4
  24. 2022Play It Back: Iterative Attention for Audio Recognitioncited by 3
  25. 2022MAST: Multiscale Audio Spectrogram Transformerscited by 3
  26. 2023Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learningcited by 3
  27. 2023Centre Stage: Centricity-based Audio-Visual Temporal Action Detectioncited by 3
  28. 2024ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutionscited by 2
  29. 2025textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Timecited by 2
  30. 2026Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Modelscited by 2
  31. 2022Refining Action Boundaries for One-stage Detectioncited by 1
  32. 2023Exploring Efficient-Tuned Learning Audio Representation Method from BriVLcited by 1
  33. 2023UniBriVL: Robust Universal Representation and Generation of Audio Driven Diffusion Modelscited by 1
  34. 2024Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classificationcited by 1
  35. 2024DETECLAP: Enhancing Audio-Visual Representation Learning with Object Informationcited by 1
  36. 2026Sounding Highlights: Dual-Pathway Audio Encoders for Audio-Visual Video Highlight Detectioncited by 1
  37. 2021The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learningcited by 0
  38. 2023AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023cited by 0

50 most cited of 56 All 56 (JSON)