# Fingerspelling Detection on ChicagoFSWild (test) Source: [Fingerspelling Detection on ChicagoFSWild (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:21.628Z Evaluation of Fingerspelling Detection performance on the test split of the ChicagoFSWild dataset, measured using Average Precision (AP) across various IoU thresholds and Mean Segment Area (MSA). 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 | Fingerspelling Detection | | Dataset (including any stated split) | ChicagoFSWild (test) | | Metric | AP@0.1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [AP@0.1](): Higher is better; unit: PERCENT. - [AP@0.3](): Higher is better; unit: PERCENT. - [AP@0.5](): Higher is better; unit: PERCENT. - [AP@0.0](): Higher is better; unit: PERCENT. - [AP@0.2](): Higher is better; unit: PERCENT. - [AP@0.4](): Higher is better; unit: PERCENT. - [MSA (Mean Segment Area)](): Higher is better; unit: PERCENT. - [AP@Acc=0.0](): Higher is better; unit: PERCENT. - [AP@Acc=0.2](): Higher is better; unit: PERCENT. - [AP@Acc=0.4](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP@0.1 | Result date | Report paper | | --- | --- | --- | --- | | GT | 100 | Not recorded | 68fa69b41e209131cea239aa | | GT | 100 | Not recorded | 68fa69b41e209131cea239aa | | multi-task model | 49.5 | Not recorded | 68fa69b41e209131cea239aa | | multi-task model | 49.5 | Not recorded | 68fa69b41e209131cea239aa | | Base 3 | 44.7 | Not recorded | 68fa69b41e209131cea239aa | | Base 3 | 44.7 | Not recorded | 68fa69b41e209131cea239aa | | BMN | 44.2 | Not recorded | 68fa69b41e209131cea239aa | | BMN | 44.2 | Not recorded | 68fa69b41e209131cea239aa | | BMN | 44.2 | Not recorded | 68fa69b41e209131cea239aa | | Base 2 | 31 | Not recorded | 68fa69b41e209131cea239aa | | Base 2 | 31 | Not recorded | 68fa69b41e209131cea239aa | | MS-TCN | 28.2 | Not recorded | 68fa69b41e209131cea239aa | | Base 1 | 12.1 | Not recorded | 68fa69b41e209131cea239aa | | Base 1 | 12.1 | Not recorded | 68fa69b41e209131cea239aa | ### GT AP@0.1: 100. Result ID: 698dda8dffc3901de09919ab. [Reporting paper]() Recorded evaluation configuration: {"source":"ground-truth fingerspelling segments"}. This record does not assert independent reproduction. ### GT AP@0.1: 100. Result ID: 698dda8dffc3901de09919bf. [Reporting paper]() Recorded evaluation configuration: {"segment source":"ground-truth"}. This record does not assert independent reproduction. ### multi-task model AP@0.1: 49.5. Result ID: 698dda8dffc3901de09919aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### multi-task model AP@0.1: 49.5. Result ID: 698dda8dffc3901de09919be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base 3 AP@0.1: 44.7. Result ID: 698dda8dffc3901de09919a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"type":"region-based model"}. This record does not assert independent reproduction. ### Base 3 AP@0.1: 44.7. Result ID: 698dda8dffc3901de09919bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BMN AP@0.1: 44.2. Result ID: 698dda8dffc3901de09919a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BMN AP@0.1: 44.2. Result ID: 698dda8dffc3901de09919a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BMN AP@0.1: 44.2. Result ID: 698dda8dffc3901de09919bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base 2 AP@0.1: 31. Result ID: 698dda8dffc3901de09919a7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base 2 AP@0.1: 31. Result ID: 698dda8dffc3901de09919bb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MS-TCN AP@0.1: 28.2. Result ID: 698dda8dffc3901de09919a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base 1 AP@0.1: 12.1. Result ID: 698dda8dffc3901de09919a6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base 1 AP@0.1: 12.1. Result ID: 698dda8dffc3901de09919ba. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.