# Background Subtraction on CDnet 2014 (full) Source: [Background Subtraction on CDnet 2014 (full)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:53.145Z Evaluation of Background Subtraction performance on the CDnet 2014 dataset, reporting F-Measure scores across various challenging video categories (e.g., shadow, night, PTZ). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Background Subtraction | | Dataset (including any stated split) | CDnet 2014 (full) | | Metric | F1 (baseline) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [F1 (baseline)](): Higher is better; unit: PERCENT. - [F1 (Overall)](): Higher is better; unit: PERCENT. - [F1 (camjitt)](): Higher is better; unit: PERCENT. - [F1 (dynbg)](): Higher is better; unit: PERCENT. - [F1 (intmot)](): Higher is better; unit: PERCENT. - [F1 (shadow)](): Higher is better; unit: PERCENT. - [F1 (thermal)](): Higher is better; unit: PERCENT. - [F1 (badwea)](): Higher is better; unit: PERCENT. - [F1 (lowfr)](): Higher is better; unit: PERCENT. - [F1 (night)](): Higher is better; unit: PERCENT. - [F1 (PTZ)](): Higher is better; unit: PERCENT. - [F1 (turbul)](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 (baseline) | Result date | Report paper | | --- | --- | --- | --- | | FgSegNetv2 | 99.78 | Not recorded | 68fa6eea1e209131cea42e0f | | MU-Net2 | 99 | Not recorded | 68fa6eea1e209131cea42e0f | | BSPVGAN | 98.37 | Not recorded | 68fa6eea1e209131cea42e0f | | CascadeCNN | 97.86 | Not recorded | 68fa6eea1e209131cea42e0f | | ZBS | 96.53 | Not recorded | 68fa6eea1e209131cea42e0f | | BSUV-Net 2.0 | 96.2 | Not recorded | 68fa6eea1e209131cea42e0f | | SemanticBGS | 96.04 | Not recorded | 68fa6eea1e209131cea42e0f | | RTSS | 95.97 | Not recorded | 68fa6eea1e209131cea42e0f | | STPNet | 95.87 | Not recorded | 68fa6eea1e209131cea42e0f | | IUTIS-5 | 95.67 | Not recorded | 68fa6eea1e209131cea42e0f | | RT-SBS-v2 | 95.35 | Not recorded | 68fa6eea1e209131cea42e0f | | SuBSENSE | 95.03 | Not recorded | 68fa6eea1e209131cea42e0f | | WisenetMD | 94.87 | Not recorded | 68fa6eea1e209131cea42e0f | | PAWCS | 93.97 | Not recorded | 68fa6eea1e209131cea42e0f | | SWCD | 92.14 | Not recorded | 68fa6eea1e209131cea42e0f | | FgSegNet | 69.26 | Not recorded | 68fa6eea1e209131cea42e0f | ### FgSegNetv2 F1 (baseline): 99.78. Result ID: 699087413a6c314849013993. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### MU-Net2 F1 (baseline): 99. Result ID: 699087413a6c314849013991. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### BSPVGAN F1 (baseline): 98.37. Result ID: 699087413a6c314849013992. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### CascadeCNN F1 (baseline): 97.86. Result ID: 699087413a6c314849013990. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### ZBS F1 (baseline): 96.53. Result ID: 699087423a6c31484901399f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### BSUV-Net 2.0 F1 (baseline): 96.2. Result ID: 699087413a6c314849013996. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### SemanticBGS F1 (baseline): 96.04. Result ID: 699087423a6c31484901399c. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### RTSS F1 (baseline): 95.97. Result ID: 699087423a6c31484901399d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### STPNet F1 (baseline): 95.87. Result ID: 699087413a6c314849013995. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### IUTIS-5 F1 (baseline): 95.67. Result ID: 699087413a6c314849013997. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised"}. This record does not assert independent reproduction. ### RT-SBS-v2 F1 (baseline): 95.35. Result ID: 699087423a6c31484901399e. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### SuBSENSE F1 (baseline): 95.03. Result ID: 699087423a6c314849013999. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### WisenetMD F1 (baseline): 94.87. Result ID: 699087423a6c31484901399a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### PAWCS F1 (baseline): 93.97. Result ID: 699087423a6c314849013998. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### SWCD F1 (baseline): 92.14. Result ID: 699087423a6c31484901399b. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction. ### FgSegNet F1 (baseline): 69.26. Result ID: 699087413a6c314849013994. [Reporting paper]() Recorded evaluation configuration: {"Learning Paradigm":"Supervised","Evaluation Protocol":"unseen video"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.