File size: 27,893 Bytes

task,task_display,modality_group,modality_display,status,score,primary_metric,primary_metric_value,target_variant,target_source_overlap,reason,accuracy,macro_f1,balanced_accuracy,num_classes,num_train,num_test,unseen_test_classes,unseen_test_class_count,mse,mae,r2,micro_f1,exact_match,precision,recall,num_objects,mrr,top1_accuracy,top5_accuracy,top10_accuracy,median_rank,mean_rank,num_queries
timeline_action,Current Action Recognition,all_features,All Features,computed,0.00905456968081885,macro_f1,0.00905456968081885,,false,,0.017241379310344827,0.00905456968081885,0.01720647773279352,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,video,Video,computed,0.0066280033140016575,macro_f1,0.0066280033140016575,,false,,0.011494252873563218,0.0066280033140016575,0.0036199095022624436,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,depth,Depth,computed,0.0030075187969924814,macro_f1,0.0030075187969924814,,false,,0.005747126436781609,0.0030075187969924814,0.001619433198380567,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,pose_slam,Pose + SLAM,computed,0.0,macro_f1,0.0,,false,,0.0,0.0,0.0,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,motion_capture,Motion Capture,computed,0.0055147058823529415,macro_f1,0.0055147058823529415,,false,,0.008620689655172414,0.0055147058823529415,0.0028846153846153848,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,inertial,Inertial,computed,0.003055767761650115,macro_f1,0.003055767761650115,,false,,0.005747126436781609,0.003055767761650115,0.0018099547511312218,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,audio,Audio,computed,0.006925207756232688,macro_f1,0.006925207756232688,,false,,0.014367816091954023,0.006925207756232688,0.004048582995951417,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,language,Language,computed,0.027777777777777776,macro_f1,0.027777777777777776,,false,,0.05747126436781609,0.027777777777777776,0.03615384615384616,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_action,Current Action Recognition,no_language,All Except Language,computed,0.0043859649122807015,macro_f1,0.0043859649122807015,,false,,0.008620689655172414,0.0043859649122807015,0.0024291497975708503,19,813,348,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,all_features,All Features,computed,0.011256354393609296,macro_f1,0.011256354393609296,,false,,0.02586206896551724,0.011256354393609296,0.02788220551378446,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,video,Video,computed,0.011740041928721174,macro_f1,0.011740041928721174,,false,,0.040229885057471264,0.011740041928721174,0.01637426900584795,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,depth,Depth,computed,0.009467455621301775,macro_f1,0.009467455621301775,,false,,0.022988505747126436,0.009467455621301775,0.010796221322537112,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,pose_slam,Pose + SLAM,computed,0.002331002331002331,macro_f1,0.002331002331002331,,false,,0.0028735632183908046,0.002331002331002331,0.001349527665317139,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,motion_capture,Motion Capture,computed,0.006756756756756756,macro_f1,0.006756756756756756,,false,,0.008620689655172414,0.006756756756756756,0.0043859649122807015,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,inertial,Inertial,computed,0.004662004662004662,macro_f1,0.004662004662004662,,false,,0.005747126436781609,0.004662004662004662,0.002699055330634278,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,audio,Audio,computed,0.016194331983805668,macro_f1,0.016194331983805668,,false,,0.022988505747126436,0.016194331983805668,0.010796221322537112,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,language,Language,computed,0.04828150572831424,macro_f1,0.04828150572831424,,false,,0.14655172413793102,0.04828150572831424,0.0939327485380117,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
timeline_subtask,Current Subtask Recognition,no_language,All Except Language,computed,0.007427055702917773,macro_f1,0.007427055702917773,,false,,0.020114942528735632,0.007427055702917773,0.009446693657219972,15,813,348,Move bottle to coffee equipment|Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,all_features,All Features,computed,0.46213292117465227,macro_f1,0.46213292117465227,,false,,0.8591954022988506,0.46213292117465227,0.4503012048192771,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,video,Video,computed,0.46625766871165636,macro_f1,0.46625766871165636,,false,,0.8735632183908046,0.46625766871165636,0.4578313253012048,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,depth,Depth,computed,0.4604651162790698,macro_f1,0.4604651162790698,,false,,0.853448275862069,0.4604651162790698,0.44728915662650603,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,pose_slam,Pose + SLAM,computed,0.48444444444444446,macro_f1,0.48444444444444446,,false,,0.9396551724137931,0.48444444444444446,0.4924698795180723,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,motion_capture,Motion Capture,computed,0.5439056356487549,macro_f1,0.5439056356487549,,false,,0.896551724137931,0.5439056356487549,0.5591114457831325,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,inertial,Inertial,computed,0.48520710059171596,macro_f1,0.48520710059171596,,false,,0.9425287356321839,0.48520710059171596,0.4939759036144578,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,audio,Audio,computed,0.48444444444444446,macro_f1,0.48444444444444446,,false,,0.9396551724137931,0.48444444444444446,0.4924698795180723,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,language,Language,computed,0.7051957831325302,macro_f1,0.7051957831325302,,false,,0.9482758620689655,0.7051957831325302,0.7051957831325302,2,813,348,,0,,,,,,,,,,,,,,,
transition_detection,Action Transition Detection,no_language,All Except Language,computed,0.45454545454545453,macro_f1,0.45454545454545453,,false,,0.8333333333333334,0.45454545454545453,0.4367469879518072,2,813,348,,0,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,all_features,All Features,computed,0.004971002485501243,macro_f1,0.004971002485501243,future action label from windows.csv,false,,0.008645533141210375,0.004971002485501243,0.0027573529411764708,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,video,Video,computed,0.006349206349206349,macro_f1,0.006349206349206349,future action label from windows.csv,false,,0.011527377521613832,0.006349206349206349,0.003472222222222222,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,depth,Depth,computed,0.001594896331738437,macro_f1,0.001594896331738437,future action label from windows.csv,false,,0.002881844380403458,0.001594896331738437,0.0008223684210526315,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,pose_slam,Pose + SLAM,computed,0.0,macro_f1,0.0,future action label from windows.csv,false,,0.0,0.0,0.0,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,motion_capture,Motion Capture,computed,0.00322061191626409,macro_f1,0.00322061191626409,future action label from windows.csv,false,,0.005763688760806916,0.00322061191626409,0.001736111111111111,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,inertial,Inertial,computed,0.00196078431372549,macro_f1,0.00196078431372549,future action label from windows.csv,false,,0.002881844380403458,0.00196078431372549,0.0010416666666666667,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,audio,Audio,computed,0.004761904761904762,macro_f1,0.004761904761904762,future action label from windows.csv,false,,0.008645533141210375,0.004761904761904762,0.0026041666666666665,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,language,Language,computed,0.04193971166448231,macro_f1,0.04193971166448231,future action label from windows.csv,false,,0.1844380403458213,0.04193971166448231,0.07142857142857142,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
next_action,Next-Action Prediction,no_language,All Except Language,computed,0.004576659038901602,macro_f1,0.004576659038901602,future action label from windows.csv,false,,0.008645533141210375,0.004576659038901602,0.0024671052631578946,19,810,347,Place item on table|Wait/Prepare for pouring|Pour coffee|Pour milk into coffee,4,,,,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,all_features,All Features,computed,0.11919872659288855,mae,7.3893513679504395,future hand feature vector from shared_windows.npz,true,,,,,,,,,,4377.7705078125,7.3893513679504395,-4562.174276179636,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,video,Video,computed,0.4956350584748486,mae,1.0176135301589966,future hand feature vector from shared_windows.npz,false,,,,,,,,,,1.7896661758422852,1.0176135301589966,-0.8654605965108897,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,depth,Depth,computed,0.04014931629731973,mae,23.907024383544922,future hand feature vector from shared_windows.npz,false,,,,,,,,,,72553.34375,23.907024383544922,-75625.0610993949,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,pose_slam,Pose + SLAM,computed,0.5611809661721311,mae,0.7819563746452332,future hand feature vector from shared_windows.npz,false,,,,,,,,,,1.2600995302200317,0.7819563746452332,-0.3134661692106211,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,motion_capture,Motion Capture,computed,0.0839705207556719,mae,10.908941268920898,future hand feature vector from shared_windows.npz,true,,,,,,,,,,6293.8876953125,10.908941268920898,-6559.441194341517,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,inertial,Inertial,computed,0.5679183061202404,mae,0.7608166337013245,future hand feature vector from shared_windows.npz,false,,,,,,,,,,1.1916581392288208,0.7608166337013245,-0.24212624676650907,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,audio,Audio,computed,0.4677426495622507,mae,1.137927770614624,future hand feature vector from shared_windows.npz,false,,,,,,,,,,3.675895929336548,1.137927770614624,-2.831574197208222,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,language,Language,computed,0.451525705011023,mae,1.2147133350372314,future hand feature vector from shared_windows.npz,false,,,,,,,,,,2.3450045585632324,1.2147133350372314,-1.4443180759924243,,,,,,,,,,,,
hand_trajectory_forecast,Future Hand Motion Forecasting,no_language,All Except Language,computed,0.10781931019562568,mae,8.274776458740234,future hand feature vector from shared_windows.npz,true,,,,,,,,,,5327.0849609375,8.274776458740234,-5551.693117832905,,,,,,,,,,,,
contact_prediction,Contact State Prediction,all_features,All Features,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,video,Video,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,depth,Depth,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,pose_slam,Pose + SLAM,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,motion_capture,Motion Capture,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,inertial,Inertial,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,audio,Audio,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,language,Language,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
contact_prediction,Contact State Prediction,no_language,All Except Language,computed,1.0,macro_f1,1.0,contact proxy derived from body_contacts feature block,false,,1.0,1.0,1.0,1,813,348,,0,,,,,,,,,,,,,,,
object_relevance,Relevant Object Prediction,all_features,All Features,computed,0.1830870279146141,micro_f1,0.1830870279146141,object sets exported from annotation.hdf5 caption_frame_info_map,true,,,0.06426101593989779,,,813,348,,,,,,0.1830870279146141,0.031609195402298854,0.20667284522706209,0.1643330876934414,34,,,,,,,
object_relevance,Relevant Object Prediction,video,Video,computed,0.14804270462633454,micro_f1,0.14804270462633454,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.04379950367755125,,,813,348,,,,,,0.14804270462633454,0.008620689655172414,0.14315209910529939,0.15327929255711129,34,,,,,,,
object_relevance,Relevant Object Prediction,depth,Depth,computed,0.20134228187919462,micro_f1,0.20134228187919462,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.0649677953734521,,,813,348,,,,,,0.20134228187919462,0.011494252873563218,0.18484288354898337,0.2210759027266028,34,,,,,,,
object_relevance,Relevant Object Prediction,pose_slam,Pose + SLAM,computed,0.19528071602929212,micro_f1,0.19528071602929212,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.05592381693865655,,,813,348,,,,,,0.19528071602929212,0.0,0.21798365122615804,0.17686072218128224,34,,,,,,,
object_relevance,Relevant Object Prediction,motion_capture,Motion Capture,computed,0.11607786589762077,micro_f1,0.11607786589762077,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.045395437036303915,,,813,348,,,,,,0.11607786589762077,0.0028735632183908046,0.11362032462949895,0.11864406779661017,34,,,,,,,
object_relevance,Relevant Object Prediction,inertial,Inertial,computed,0.1716082659478886,micro_f1,0.1716082659478886,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.04806995854957751,,,813,348,,,,,,0.1716082659478886,0.0,0.21979286536248563,0.14075165806927045,34,,,,,,,
object_relevance,Relevant Object Prediction,audio,Audio,computed,0.15894039735099336,micro_f1,0.15894039735099336,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.0640376063191102,,,813,348,,,,,,0.15894039735099336,0.005747126436781609,0.16859504132231404,0.1503316138540899,34,,,,,,,
object_relevance,Relevant Object Prediction,language,Language,computed,0.23021032504780117,micro_f1,0.23021032504780117,object sets exported from annotation.hdf5 caption_frame_info_map,true,,,0.0947530205484707,,,813,348,,,,,,0.23021032504780117,0.15229885057471265,0.23926868044515104,0.22181282240235814,34,,,,,,,
object_relevance,Relevant Object Prediction,no_language,All Except Language,computed,0.15813953488372093,micro_f1,0.15813953488372093,object sets exported from annotation.hdf5 caption_frame_info_map,false,,,0.05335536055344564,,,813,348,,,,,,0.15813953488372093,0.011494252873563218,0.15368567454798332,0.16285924834193072,34,,,,,,,
caption_grounding,Language-to-Time Grounding,all_features,All Features,computed,0.20975713431835175,mrr,0.20975713431835175,,true,,,,,,,,,,,,,,,,,,0.20975713431835175,0.08908045977011494,0.32471264367816094,0.4454022988505747,13.0,23.19827651977539,348
caption_grounding,Language-to-Time Grounding,video,Video,computed,0.022670436650514603,mrr,0.022670436650514603,,false,,,,,,,,,,,,,,,,,,0.022670436650514603,0.0028735632183908046,0.02586206896551724,0.034482758620689655,162.0,161.4770050048828,348
caption_grounding,Language-to-Time Grounding,depth,Depth,computed,0.02443847246468067,mrr,0.02443847246468067,,false,,,,,,,,,,,,,,,,,,0.02443847246468067,0.0028735632183908046,0.020114942528735632,0.03735632183908046,114.0,137.90805053710938,348
caption_grounding,Language-to-Time Grounding,pose_slam,Pose + SLAM,computed,0.02946249581873417,mrr,0.02946249581873417,,false,,,,,,,,,,,,,,,,,,0.02946249581873417,0.008620689655172414,0.028735632183908046,0.04597701149425287,143.5,155.4712677001953,348
caption_grounding,Language-to-Time Grounding,motion_capture,Motion Capture,computed,0.030569594353437424,mrr,0.030569594353437424,,false,,,,,,,,,,,,,,,,,,0.030569594353437424,0.008620689655172414,0.02586206896551724,0.04885057471264368,110.5,130.32470703125,348
caption_grounding,Language-to-Time Grounding,inertial,Inertial,computed,0.02470344305038452,mrr,0.02470344305038452,,false,,,,,,,,,,,,,,,,,,0.02470344305038452,0.0028735632183908046,0.022988505747126436,0.04597701149425287,123.0,138.61207580566406,348
caption_grounding,Language-to-Time Grounding,audio,Audio,computed,0.03902389109134674,mrr,0.03902389109134674,,false,,,,,,,,,,,,,,,,,,0.03902389109134674,0.011494252873563218,0.04885057471264368,0.07758620689655173,141.0,152.14942932128906,348
caption_grounding,Language-to-Time Grounding,language,Language,computed,0.24527303874492645,mrr,0.24527303874492645,,true,,,,,,,,,,,,,,,,,,0.24527303874492645,0.12643678160919541,0.34770114942528735,0.47126436781609193,12.0,15.106322288513184,348
caption_grounding,Language-to-Time Grounding,no_language,All Except Language,computed,0.03208239749073982,mrr,0.03208239749073982,,false,,,,,,,,,,,,,,,,,,0.03208239749073982,0.0028735632183908046,0.040229885057471264,0.06896551724137931,132.0,137.30746459960938,348
cross_modal_retrieval,Cross-Modal Window Retrieval,all_features,All Features,computed,0.972757875919342,mrr,0.972757875919342,,true,,,,,,,,,,,,,,,,,,0.972757875919342,0.9683908045977011,0.9741379310344828,0.9798850574712644,1.0,2.0862069129943848,348
cross_modal_retrieval,Cross-Modal Window Retrieval,video,Video,computed,0.9701701402664185,mrr,0.9701701402664185,,true,,,,,,,,,,,,,,,,,,0.9701701402664185,0.9626436781609196,0.9798850574712644,0.9798850574712644,1.0,3.844827651977539,348
cross_modal_retrieval,Cross-Modal Window Retrieval,depth,Depth,computed,0.6656051278114319,mrr,0.6656051278114319,,true,,,,,,,,,,,,,,,,,,0.6656051278114319,0.5660919540229885,0.7902298850574713,0.8620689655172413,1.0,5.729885101318359,348
cross_modal_retrieval,Cross-Modal Window Retrieval,pose_slam,Pose + SLAM,computed,0.42622581124305725,mrr,0.42622581124305725,,false,,,,,,,,,,,,,,,,,,0.42622581124305725,0.3017241379310345,0.5488505747126436,0.6551724137931034,4.0,15.623562812805176,348
cross_modal_retrieval,Cross-Modal Window Retrieval,motion_capture,Motion Capture,computed,0.2553335726261139,mrr,0.2553335726261139,,false,,,,,,,,,,,,,,,,,,0.2553335726261139,0.15804597701149425,0.35344827586206895,0.3994252873563218,21.5,49.181034088134766,348
cross_modal_retrieval,Cross-Modal Window Retrieval,inertial,Inertial,computed,0.2840072810649872,mrr,0.2840072810649872,,false,,,,,,,,,,,,,,,,,,0.2840072810649872,0.16379310344827586,0.3735632183908046,0.5229885057471264,10.0,20.577587127685547,348
cross_modal_retrieval,Cross-Modal Window Retrieval,audio,Audio,computed,0.02334633097052574,mrr,0.02334633097052574,,false,,,,,,,,,,,,,,,,,,0.02334633097052574,0.005747126436781609,0.014367816091954023,0.031609195402298854,152.5,161.44540405273438,348
cross_modal_retrieval,Cross-Modal Window Retrieval,language,Language,computed,0.031006580218672752,mrr,0.031006580218672752,,false,,,,,,,,,,,,,,,,,,0.031006580218672752,0.005747126436781609,0.031609195402298854,0.05747126436781609,138.0,146.83045959472656,348
cross_modal_retrieval,Cross-Modal Window Retrieval,no_language,All Except Language,computed,0.9725185036659241,mrr,0.9725185036659241,,true,,,,,,,,,,,,,,,,,,0.9725185036659241,0.9683908045977011,0.9741379310344828,0.9770114942528736,1.0,2.181034564971924,348
modality_reconstruction,Sensor-to-Visual Reconstruction,all_features,All Features,computed,0.20013932390163613,mae,3.9965193271636963,,true,,,,,,,,,,4488.36962890625,3.9965193271636963,0.4789615393741845,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,video,Video,computed,0.611318891594774,mae,0.635807454586029,,true,,,,,,,,,,8679.7548828125,0.635807454586029,-0.007601057526781085,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,depth,Depth,computed,0.062215385980961393,mae,15.07319450378418,,true,,,,,,,,,,38000.71875,15.07319450378418,-3.4113648334674167,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,pose_slam,Pose + SLAM,computed,0.5359235021455191,mae,0.8659379482269287,,false,,,,,,,,,,8678.9697265625,0.8659379482269287,-0.007509963078260462,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,motion_capture,Motion Capture,computed,0.07724422027114182,mae,11.945952415466309,,false,,,,,,,,,,16462.224609375,11.945952415466309,-0.911039534454414,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,inertial,Inertial,computed,0.5185351442505587,mae,0.9285095930099487,,false,,,,,,,,,,8680.1376953125,0.9285095930099487,-0.007645498747803181,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,audio,Audio,computed,0.4237932455142579,mae,1.359641194343567,,false,,,,,,,,,,8681.8916015625,1.359641194343567,-0.007849137404613904,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,language,Language,computed,0.411308516935754,mae,1.4312649965286255,,false,,,,,,,,,,8681.390625,1.4312649965286255,-0.00779095493123938,,,,,,,,,,,,
modality_reconstruction,Sensor-to-Visual Reconstruction,no_language,All Except Language,computed,0.198028246205017,mae,4.0497846603393555,,true,,,,,,,,,,4352.54638671875,4.0497846603393555,0.49472875505192115,,,,,,,,,,,,
temporal_order,Temporal Order Verification,all_features,All Features,computed,0.5172413793103449,macro_f1,0.5172413793103449,,false,,0.5172413793103449,0.5172413793103449,0.5172413793103449,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,video,Video,computed,0.5172413793103449,macro_f1,0.5172413793103449,,false,,0.5172413793103449,0.5172413793103449,0.5172413793103449,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,depth,Depth,computed,0.49424869738982513,macro_f1,0.49424869738982513,,false,,0.4942528735632184,0.49424869738982513,0.49425287356321834,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,pose_slam,Pose + SLAM,computed,0.5258620689655172,macro_f1,0.5258620689655172,,false,,0.5258620689655172,0.5258620689655172,0.5258620689655172,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,motion_capture,Motion Capture,computed,0.4942528735632184,macro_f1,0.4942528735632184,,false,,0.4942528735632184,0.4942528735632184,0.4942528735632184,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,inertial,Inertial,computed,0.5,macro_f1,0.5,,false,,0.5,0.5,0.5,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,audio,Audio,computed,0.4425287356321839,macro_f1,0.4425287356321839,,false,,0.4425287356321839,0.4425287356321839,0.4425287356321839,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,language,Language,computed,0.4236751152073733,macro_f1,0.4236751152073733,,false,,0.47126436781609193,0.4236751152073733,0.47126436781609193,2,1624,696,,0,,,,,,,,,,,,,,,
temporal_order,Temporal Order Verification,no_language,All Except Language,computed,0.5057471264367817,macro_f1,0.5057471264367817,,false,,0.5057471264367817,0.5057471264367817,0.5057471264367817,2,1624,696,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,all_features,All Features,computed,0.4159692457248906,macro_f1,0.4159692457248906,,false,,0.4479768786127168,0.4159692457248906,0.44797687861271673,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,video,Video,computed,0.49488307322727143,macro_f1,0.49488307322727143,,false,,0.4985549132947977,0.49488307322727143,0.4985549132947977,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,depth,Depth,computed,0.46659963973021656,macro_f1,0.46659963973021656,,false,,0.4682080924855491,0.46659963973021656,0.4682080924855491,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,pose_slam,Pose + SLAM,computed,0.4929686094043242,macro_f1,0.4929686094043242,,false,,0.5057803468208093,0.4929686094043242,0.5057803468208092,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,motion_capture,Motion Capture,computed,0.4133918268956141,macro_f1,0.4133918268956141,,false,,0.4638728323699422,0.4133918268956141,0.4638728323699422,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,inertial,Inertial,computed,0.48899072503396884,macro_f1,0.48899072503396884,,false,,0.49421965317919075,0.48899072503396884,0.49421965317919075,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,audio,Audio,computed,0.5152624305034046,macro_f1,0.5152624305034046,,false,,0.5187861271676301,0.5152624305034046,0.5187861271676301,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,language,Language,computed,0.4942161609504254,macro_f1,0.4942161609504254,,false,,0.5,0.4942161609504254,0.5,2,1614,692,,0,,,,,,,,,,,,,,,
misalignment_detection,Cross-Modal Misalignment Detection,no_language,All Except Language,computed,0.4136154066851563,macro_f1,0.4136154066851563,,false,,0.44942196531791906,0.4136154066851563,0.4494219653179191,2,1614,692,,0,,,,,,,,,,,,,,,