mlsanityData to 14 Oct 2026

Match Cutting: Finding Cuts with Smooth Visual Transitions

arXiv 2210.05766 ↗First posted 11 Oct 2022cs.CV cs.LG cs.MMcited by 12

Not on the map. Why?

Abstract (arXiv)

A match cut is a transition between a pair of shots that uses similar framing, composition, or action to fluidly bring the viewer from one scene to the next. Match cuts are frequently used in film, television, and advertising. However, finding shots that work together is a highly manual and time-consuming process that can take days. We propose a modular and flexible system to efficiently find high-quality match cut candidates starting from millions of shot pairs. We annotate and release a dataset of approximately 20k labeled pairs that we use to evaluate our system, using both classification and metric learning approaches that leverage a variety of image, video, audio, and audio-visual feature extractors. In addition, we release code and embeddings for reproducing our experiments at github.com/netflix/matchcut.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 45 of its 82 references that are in the map. First posted on arXiv 11 Oct 2022.

Builds on

45 of 82 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  9. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,866
33 more
  1. 2017Billion-scale similarity search with GPUscited by 2,497
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  3. 2017The Kinetics Human Action Video Datasetcited by 1,909
  4. 2018SlowFast Networks for Video Recognitioncited by 1,867
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  6. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  7. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  8. 2021Video Swin Transformercited by 1,091
  9. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  11. 2016Simple Online and Realtime Trackingcited by 868
  12. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  13. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
  14. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  15. 2021AudioCLIP: Extending CLIP to Image, Text and Audiocited by 339
  16. 2018A Short Note about Kinetics-600cited by 333
  17. 2019Self-Supervised Learning by Cross-Modal Audio-Video Clusteringcited by 267
  18. 2020MovieNet: A Holistic Dataset for Movie Understandingcited by 206
  19. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 171
  20. 2022Multiview Transformers for Video Recognitioncited by 148
  21. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  22. 2019Text-based Editing of Talking-head Videocited by 103
  23. 2020Condensed Movies: Story Based Retrieval with Contextual Embeddingscited by 95
  24. 2017MovieGraphs: Towards Understanding Human-Centric Situations from Videoscited by 67
  25. 2020PyTorch Metric Learningcited by 57
  26. 2020A Unified Framework for Shot Type Classification Based on Subject Centric Lenscited by 44
  27. 2016Full Flow: Optical Flow Estimation By Global Optimization over Regular Gridscited by 34
  28. 2021MovieCuts: A New Dataset and Benchmark for Cut Type Recognitioncited by 26
  29. 2020Movie Summarization via Sparse Graph Constructioncited by 22
  30. 2021Learning to Cut by Watching Moviescited by 18
  31. 2018From Trailers to Storylines: An Efficient Way to Learn from Moviescited by 10
  32. 2020Hierarchical Encoders for Modeling and Interpreting Screenplayscited by 2
  33. 2021Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Showscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 5; 2025: 4.

12 papers.

  1. 2025Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generationcited by 13
  2. 2024Long Story Short: Story-level Video Understanding from 20K Short Filmscited by 12
  3. 2023Long-range Multimodal Pretraining for Movie Understandingcited by 7
  4. 2025VEU-Bench: Towards Comprehensive Understanding of Video Editingcited by 7
  5. 2023SmoothHess: ReLU Network Feature Interactions via Stein's Lemmacited by 5
  6. 2024Generative Timelines for Instructed Visual Assemblycited by 5
  7. 2024MatchDiffusion: Training-free Generation of Match-cutscited by 5
  8. 2022VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Spacecited by 4
  9. 2024Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videoscited by 4
  10. 2025Cin'easte: A Fine-grained Contextual Movie Question Answering Benchmarkcited by 2
  11. 2025V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptationcited by 1
  12. 2024Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learningcited by 0