modeling_zhaocui/deep_learning/Q1/outputs/method_comparison/retrieval_summary.csv

1	method	direction	n	r_at_1_mean	r_at_1_std	r_at_5_mean	r_at_5_std	mrr_mean	mrr_std
2	M1	text_to_audio	5	0.0012000000569969416	0.001643167750561775	0.007000000309199094	0.0015811389419980182	0.008951337542384863	0.0015105744211016399
3	M1	audio_to_text	5	0.0028000001097097994	0.0014832398031884779	0.006000000238418579	0.0021213204717563106	0.009594007954001426	0.0008820339883026645
4	M1	text_to_vision	5	0.0020000000949949026	0.0020000001240987344	0.007000000402331352	0.0031622779576235397	0.009382870234549045	0.0038973032823256706
5	M1	vision_to_text	5	0.005000000214204192	0.0038729835451934104	0.007000000402331352	0.004301162959612636	0.010874488297849894	0.0033759486781861315
6	M1	audio_to_vision	5	0.0010000000474974513	0.0010000000474974513	0.008600000198930502	0.004037325898109636	0.010010761767625808	0.0028143308073864106
7	M1	vision_to_audio	5	0.002000000048428774	0.0009999999892897908	0.008000000286847353	0.0036742348045336777	0.009903422184288501	0.0023425375089251867
8	M2	text_to_audio	5	0.0014000000432133675	0.0011401754384133685	0.009200000390410423	0.0022803508359855447	0.010239988192915916	0.0015598764796833854
9	M2	audio_to_text	5	0.004000000143423677	0.0015811388683705022	0.009200000483542681	0.0030331502218969453	0.011443204618990422	0.0018186032524210385
10	M2	text_to_vision	5	0.003600000194273889	0.003209361472308511	0.008800000487826764	0.004764451893141854	0.011315117496997118	0.004998444639556679
11	M2	vision_to_text	5	0.00680000027641654	0.001923538612521058	0.009200000576674939	0.0013038406947566386	0.013902883604168892	0.0007593274807152007
12	M2	audio_to_vision	5	0.0014000000664964318	0.0005477225835205916	0.006800000183284282	0.003346640098121672	0.009431831166148185	0.0017045066129491178
13	M2	vision_to_audio	5	0.002000000118277967	0.0018708288289165209	0.00640000025741756	0.0032093615938253205	0.00967191495001316	0.002293345042131113
14	M3	text_to_audio	15	0.01966666733690848	0.009707631019479971	0.043000001646578315	0.020511321663901527	0.03803744154671828	0.014634778360297347
15	M3	audio_to_text	15	0.009066667081788183	0.009353889531597692	0.020933334335374334	0.013084706401165278	0.023117945653696854	0.011741696228606028
16	M3	text_to_vision	15	0.0062666668944681685	0.00413118239876218	0.013800000709791978	0.007466114240091005	0.01513038482517004	0.005506734651604392
17	M3	vision_to_text	15	0.00506666685299327	0.003634490987677242	0.011266667147477467	0.005573748401698712	0.01275980711604158	0.003981040361844423
18	M3	audio_to_vision	15	0.006400000179807345	0.0033974781354081164	0.0142666673908631	0.007215723836767552	0.016017937225600083	0.005224730877211012
19	M3	vision_to_audio	15	0.00426666682275633	0.0024630605290560273	0.00913333367401113	0.005111145810859167	0.012493464909493924	0.0045251231363594895
20	M4	text_to_audio	15	0.007066666963510215	0.01601546933258453	0.01226666709408164	0.019414526078011158	0.014511969638988376	0.018944261404425476
21	M4	audio_to_text	15	0.00046666668883214396	0.0005163978040219006	0.002266666820893685	0.00252039318928005	0.005223872559145093	0.0023624842688679767
22	M4	text_to_vision	15	0.0016000000604738792	0.0011832159931418852	0.00760000046963493	0.005852960507593743	0.0100666221541663	0.005020802122090484
23	M4	vision_to_text	15	0.0014666667130465308	0.0010600988416483645	0.007333333759258191	0.005300494367735815	0.009886658145114779	0.004472077112598579
24	M4	audio_to_vision	15	0.002133333380334079	0.0009154754048125681	0.010533333849161863	0.004405624197684311	0.012994256491462389	0.00403471312250859
25	M4	vision_to_audio	15	0.00206666673378398	0.0007037315398609183	0.010266667200873296	0.003712270612174926	0.012846407542626063	0.003972973272038369