# Object Detection on Charades (test) Source: [Object Detection on Charades (test)]() Collection index: [llms.txt]() Data updated: 2026-02-27T06:11:37.997Z Evaluation of Object Detection performance on the test split of the Charades dataset, reporting mAP and class-specific metrics. 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 | Object Detection | | Dataset (including any stated split) | Charades (test) | | Metric | mAP | | 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](): Higher is better; unit: PERCENT. - [AP (bed)](): Higher is better; unit: SCALAR. - [AP (broom)](): Higher is better; unit: SCALAR. - [AP (chair)](): Higher is better; unit: SCALAR. - [AP (cup)](): Higher is better; unit: SCALAR. - [AP (dish)](): Higher is better; unit: SCALAR. - [AP (door)](): Higher is better; unit: SCALAR. - [AP (laptop)](): Higher is better; unit: SCALAR. - [AP (mirror)](): Higher is better; unit: SCALAR. - [AP (pillow)](): Higher is better; unit: SCALAR. - [AP (refri)](): Higher is better; unit: SCALAR. - [AP (shelf)](): Higher is better; unit: SCALAR. - [AP (sofa)](): Higher is better; unit: SCALAR. - [AP (table)](): Higher is better; unit: SCALAR. - [AP (tv)](): Higher is better; unit: SCALAR. - [AP (towel)](): Higher is better; unit: SCALAR. - [AP (vacuum)](): Higher is better; unit: SCALAR. - [AP (window)](): Higher is better; unit: SCALAR. ## Recorded results | Method | mAP | Result date | Report paper | | --- | --- | --- | --- | | TD-Graph LSTM | 1.98 | Not recorded | 68fa638a1e209131ce9ff69f | | TD-Graph LSTM w/o graph | 1.55 | Not recorded | 68fa638a1e209131ce9ff69f | | TD-Graph LSTM w/o LSTM | 1.16 | Not recorded | 68fa638a1e209131ce9ff69f | | ContextLocNet | 1.12 | Not recorded | 68fa638a1e209131ce9ff69f | | WSDDN | 0.65 | Not recorded | 68fa638a1e209131ce9ff69f | ### TD-Graph LSTM mAP: 1.98. Result ID: 69a1358335dfcabb00e58139. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG-CNN-F","Region Proposal method":"EdgeBoxes"}. This record does not assert independent reproduction. ### TD-Graph LSTM w/o graph mAP: 1.55. Result ID: 69a1358335dfcabb00e58138. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG-CNN-F","Region Proposal method":"EdgeBoxes"}. This record does not assert independent reproduction. ### TD-Graph LSTM w/o LSTM mAP: 1.16. Result ID: 69a1358335dfcabb00e58137. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"VGG-CNN-F","Region Proposal method":"EdgeBoxes"}. This record does not assert independent reproduction. ### ContextLocNet mAP: 1.12. Result ID: 69a1358335dfcabb00e58136. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG-CNN-F","Region Proposal method":"EdgeBoxes"}. This record does not assert independent reproduction. ### WSDDN mAP: 0.65. Result ID: 69a1358335dfcabb00e58135. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG-CNN-F","Region Proposal method":"EdgeBoxes"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.