50 Salads Benchmark (Action Segmentation)

28 rows 22 with code listed 5 metrics Dataset page

Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.

Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation

The archive carries no text for this table; the description above is the archive's text for the task Action Segmentation. archive 2025-07-28

Over time archive 2025-07-28

Metric Extra training data

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: F1@50% (higher is better), F1@25% (higher is better), F1@10% (higher is better), Acc (higher is better). Not inferred (points only, no best-so-far line): Edit. Points are placed at the row's paper date; 27 of 28 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

								Paper	Code		Ran Syntology	Report
1	Br-Prompt+ASPnet (RGB, flow, accelerometer)	88.5	91.6	92.7	91.4	87.5	✓	Paper	–	2023	no code linked	report
2	Semantic2Graph	87.3	90.2	91.5	88.6	89.1	✓	Paper	–	2022	no code linked	report
3	BaFormer	83.9	88.4	89.3	89.5	84.2	–	Paper	Code	2024	linked, not harvested	report
4	DiffAct	83.7	89.2	90.1	88.9	85.0	–	Paper	Code	2023	5 of 9 ran · 4 unverified	report
5	SF-TMN(ASFormer)	82.9	88.0	89.1	89.8	84.4	–	Paper	–	2023	no code linked	report
6	LTContext	82.0	87.7	89.4	87.7	83.2	–	Paper	Code	2023	6 of 6 ran · 0 unverified	report
7	UVAST	81.7	87.6	89.1	87.4	83.9	–	Paper	Code	2022	2 of 2 ran · 0 unverified	report
8	Br-Prompt+ASFormer	81.3	87.8	89.2	88.1	83.8	✓	Paper	Code	2022	2 of 2 ran · 0 unverified	report
9	EUT	81	87.5	89.2	87.4	82.9	–	Paper	Code	2022	linked, not harvested	report
10	CETNet	80.1	86.5	87.6	86.9	81.7	–	Paper	Code	2022	linked, not harvested	report
11	DPRN	79.4	86.3	87.8	87.2	82.0	–	Paper	–	2022	no code linked	report
12	ASFormer+ASRF	79.3	85.4	85.1	85.9	81.9	–	Paper	Code	2021	1 of 1 ran · 0 unverified	report
13	ASRF + HASR	78.5	85.7	86.6	83.9	81.0	–	Paper	Code	2021	linked, not harvested	report
14	ASRF	77.3	83.5	84.9	84.5	79.3	–	Paper	Code	2020	0 of 11 ran · 11 unverified	report
15	ASFormer	76.0	83.4	85.1	85.6	79.6	–	Paper	Code	2021	1 of 1 ran · 0 unverified	report
16	ETSN	75.4	83.9	85.2	82.0	78.8	–	Paper	Code	2021	linked, not harvested	report
17	BCN	74	81.3	82.3	84.4	74.3	–	Paper	Code		linked, not harvested	report
18	SSTDA	73.8	81.5	83.0	83.2	75.8	–	Paper	Code	2020	3 of 3 ran · 0 unverified	report
19	C2F-TCN	72.6	81.8	84.3	84.9	76.4	–	Paper	Code	2021	linked, not harvested	report
20	DA	72.5	80.1	82.0	83.2	75.2	–	Paper	–	2021	no code linked	report
21	MS-TCN++	70.1	78.5	80.7	83.7	74.3	–	Paper	Code	2020	linked, not harvested	report
22	G2L (MS-TCN)	69.8	78	80.3	82.2	73.4	–	Paper	Code	2021	3 of 3 ran · 0 unverified	report
23	MS-TCN++(sh)	68.3	76.6	78.7	82.2	70.7	–	Paper	Code	2020	linked, not harvested	report
24	AUL	67.1	81.3	84.4	77.9	77.0	–	Paper	Code	2023	linked, not harvested	report
25	DTGRM	66.1	75.9	79.1	80	72	–	Paper	Code	2020	linked, not harvested	report
26	DS-TCN	65.78	74.43	77.0	80.0	70.0	–	Paper	–	2021	no code linked	report
27	MS-TCN	64.5	74.0	76.3	80.7	67.9	–	Paper	Code	2019	linked, not harvested	report
28	TW-FINCH (K=avg/activity)				66.5		–	Paper	Code	2021	5 of 7 ran · 2 unverified	report

All 28 rows shown. 28 link to a paper page on this site; 3 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 10 rows have a graph line, from 9 distinct papers; 9 rows (8 papers) have at least one sample that ran. Counting each paper once: Syntology ran 27 of 44 samples; 17 unverified. Separately, 14 of those 44 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections