mlsanityData to 7 Oct 2026

TransNet V2: An effective deep network architecture for fast shot transition detection

arXiv 2008.04838 ↗First posted 11 Aug 2020cs.CVcited by 166

Not on the map. Why?

Abstract (arXiv)

Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachable ideal. In this paper, we share the current version of our deep network TransNet V2 that reaches state-of-the-art performance on respected benchmarks. A trained instance of the model is provided so it can be instantly utilized by the community for a highly efficient analysis of large video archives. Furthermore, the network architecture, as well as our experience with the training process, are detailed, including simple code snippets for convenient usage of the proposed model and visualization of results.

Key facts. Cited by 166 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 15; 2023: 8; 2024: 19; 2025: 51; 2026: 70.

166 papers.

Sort:

By area:

  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  2. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  3. 2026Advancing Open-source World Modelscited by 144
  4. 2024GameGen-X: Interactive Open-world Game Video Generationcited by 124
  5. 2025LongCat-Video Technical Reportcited by 73
  6. 2025Multi-subject Open-set Personalization in Video Generationcited by 65
  7. 2025Towards Understanding Camera Motions in Any Videocited by 62
  8. 2025HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narrativescited by 51
  9. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 50
  10. 2024Mind the Time: Temporally-Controlled Multi-Event Video Generationcited by 39
  11. 2024MEMO: Memory-Guided Diffusion for Expressive Talking Video Generationcited by 38
  12. 2025RoboScape: Physics-informed Embodied World Modelcited by 38
38 more
  1. 2024SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanationscited by 37
  2. 2026Infinite Worlds with Versatile Interactionscited by 37
  3. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 33
  4. 2025DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversationscited by 31
  5. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 31
  6. 2024Imagine360: Immersive 360 Video Generation from Perspective Anchorcited by 27
  7. 2022ClothFormer:Taming Video Virtual Try-on in All Modulecited by 26
  8. 2025CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Modelscited by 26
  9. 2024FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Processcited by 25
  10. 2022The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editingcited by 24
  11. 2026WorldMark: A Unified Benchmark Suite for Interactive Video World Modelscited by 24
  12. 2023AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detectioncited by 22
  13. 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Modelscited by 22
  14. 2026ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytellingcited by 22
  15. 2021Improving the Perceptual Quality of 2D Animation Interpolationcited by 20
  16. 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generationcited by 19
  17. 2022PACS: A Dataset for Physical Audiovisual CommonSense Reasoningcited by 17
  18. 2023Meta-Personalizing Vision-Language Models to Find Named Instances in Videocited by 16
  19. 2025Cut2Next: Generating Next Shot via In-Context Tuningcited by 15
  20. 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Treecited by 15
  21. 2024LLM-AD: Large Language Model based Audio Description Systemcited by 14
  22. 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videoscited by 14
  23. 2022Temporal Perceiver: A General Architecture for Arbitrary Boundary Detectioncited by 12
  24. 2022Match Cutting: Finding Cuts with Smooth Visual Transitionscited by 12
  25. 2025DanceTogether! Identity-Preserving Multi-Person Interactive Video Generationcited by 12
  26. 2026SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing modelcited by 11
  27. 2026LPM 1.0: Video-based Character Performance Modelcited by 11
  28. 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generationcited by 10
  29. 2025Video-EM: Event-Centric Episodic Memory for Long-Form Video Understandingcited by 10
  30. 2024Large Model based Sequential Keyframe Extraction for Video Summarizationcited by 9
  31. 2024Towards Automated Movie Trailer Generationcited by 9
  32. 2025MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generationcited by 9
  33. 2022Synopses of Movie Narratives: a Video-Language Dataset for Story Understandingcited by 8
  34. 2026MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generationcited by 8
  35. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 8
  36. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 8
  37. 2022Zero-shot Video Moment Retrieval With Off-the-Shelf Modelscited by 7
  38. 2023Long-range Multimodal Pretraining for Movie Understandingcited by 7

50 most cited of 166 All 166 (JSON)