# Temporal Forgery Localization on LAV-DF cross-dataset evaluation from AV-Deepfake1M (test) Source: [Temporal Forgery Localization on LAV-DF cross-dataset evaluation from AV-Deepfake1M (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:10:04.419Z Evaluation of Temporal Forgery Localization performance using cross-dataset evaluation methodology derived from AV-Deepfake1M, tested on the specified test set, reporting mAP and AR metrics across various IoU thresholds. 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 | Temporal Forgery Localization | | Dataset (including any stated split) | LAV-DF cross-dataset evaluation from AV-Deepfake1M (test) | | Metric | mAP@IoU=0.1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [mAP@IoU=0.1](): Higher is better; unit: PERCENT. - [mAP@IoU=0.2](): Higher is better; unit: PERCENT. - [mAP@IoU=0.3](): Higher is better; unit: PERCENT. - [mAP@IoU=0.4](): Higher is better; unit: PERCENT. - [mAP@IoU=0.5](): Higher is better; unit: PERCENT. - [mAP@IoU=0.6](): Higher is better; unit: PERCENT. - [mAP@IoU=0.7](): Higher is better; unit: PERCENT. - [Average mAP](): Higher is better; unit: PERCENT. - [AR@20](): Higher is better; unit: PERCENT. - [AR@10](): Higher is better; unit: PERCENT. - [AR@5](): Higher is better; unit: PERCENT. - [AR@2](): Higher is better; unit: PERCENT. - [Average AR](): Higher is better; unit: PERCENT. ## Recorded results | Method | mAP@IoU=0.1 | Result date | Report paper | | --- | --- | --- | --- | | RT-DeepLoc | 21.81 | Not recorded | 697c3b08a8b01e76cc8da49d | | UMMAFormer | 13.93 | Not recorded | 697c3b08a8b01e76cc8da49d | | MFMS | 13.48 | Not recorded | 697c3b08a8b01e76cc8da49d | | CoLA | 1.35 | Not recorded | 697c3b08a8b01e76cc8da49d | | LOCO | 0.27 | Not recorded | 697c3b08a8b01e76cc8da49d | ### RT-DeepLoc mAP@IoU=0.1: 21.81. Result ID: 69977b9e5698665ec4d00957. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly"}. This record does not assert independent reproduction. ### UMMAFormer mAP@IoU=0.1: 13.93. Result ID: 69977b9e5698665ec4d00953. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully"}. This record does not assert independent reproduction. ### MFMS mAP@IoU=0.1: 13.48. Result ID: 69977b9e5698665ec4d00954. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully"}. This record does not assert independent reproduction. ### CoLA mAP@IoU=0.1: 1.35. Result ID: 69977b9e5698665ec4d00955. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Supervision":"weakly"}. This record does not assert independent reproduction. ### LOCO mAP@IoU=0.1: 0.27. Result ID: 69977b9e5698665ec4d00956. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.