Table 3.

Number of labeled MIM patches in training and validation sets for each patch-based MIM dataset.

		Experiment
Dataset		110		150		170		270		280		All
		P	NP	P	NP	P	NP	P	NP	P	NP	P	NP	Total
	Training	350	279	523	932	121	97	528	784	634	806	2156	2898	5054
Patch-based small RAFT-MIM${}^{Q_{12}}$	Validation	67	53	89	161	20	21	91	169	108	162	375	566	941
	Total	417	332	612	1093	141	118	619	953	742	968	2531	3464	5995
	Training	156	124	249	419	53	42	236	379	324	354	1018	1318	2336
Patch-based small RAFT-MIM${}^{Q_{25}}$	Validation	33	26	35	82	9	12	56	53	67	89	200	262	462
	Total	189	150	284	501	62	54	292	432	391	443	1218	1580	2798
	Training	237	131	298	354	95	38	540	439	698	326	1868	1288	3156
Patch-based medium RAFT-MIM${}^{Q_{12}}$	Validation	45	26	55	64	16	8	98	105	126	81	340	284	624
	Total	282	157	353	418	111	46	638	544	824	407	2208	1572	3780
	Training	107	58	142	151	42	14	242	219	338	146	871	585	1459
Patch-based medium RAFT-MIM${}^{Q_{25}}$	Validation	22	14	20	37	8	6	56	27	68	32	174	116	290
	Total	129	72	162	188	50	20	298	246	406	178	1045	704	1749

P: pushing samples. NP: non-pushing samples. All: all experiments. 110, 150, 170, 270, and 280: names of the video experiments.