Video on SumMe

Metric: F1-score (Canonical) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	F1-score (Canonical)▼	Extra Data	Paper	Date↕	Code
1	PGL-SUM (maximum learning capacity)	57.1	No	-	-	Code
2	PGL-SUM	55.6	No	-	-	Code
3	PGL-SUM	55.6	No	-	-	Code
4	A2Summ	55	No	Align and Attend: Multimodal Summarization with ...	2023-03-13	Code
5	RR-STG	54.5	No	-	-	-
6	iPTNet	54.5	Yes	-	-	-
7	DMASum	54.3	No	Query Twice: Dual Mixture Attention Meta Learnin...	2020-08-19	-
8	CLIP-It	54.2	No	CLIP-It! Language-Guided Video Summarization	2021-07-01	Code
9	RR-STG	53.4	No	-	-	-
10	MSVA	53.4	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
11	DSNet	53	No	-	-	Code
12	MC-VSA [DBLP:journals/corr/abs-2006-01410]	51.6	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
13	SSPVS(+Text)	50.7	No	Progressive Video Summarization via Multimodal S...	2022-01-07	Code
14	VJMHT	50.6	No	Video Joint Modelling Based on Hierarchical Tran...	2021-12-27	Code
15	DSNet	50.2	No	-	-	Code
16	VASNet	49.71	No	Summarizing Videos with Attention	2018-12-05	Code
17	SSPVS	48.7	No	Progressive Video Summarization via Multimodal S...	2022-01-07	Code
18	CSNet	48.6	No	Discriminative Feature Learning for Unsupervised...	2018-11-24	Code
19	VASNet [DBLP:conf/accv/FajtlSAMR18]	48	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
20	re-SEQ2SEQ [DBLP:conf/eccv/ZhangGS18]	44.9	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
21	M-AVS	44.4	No	Video Summarization with Attention-Based Encoder...	2017-08-31	-
22	M-AVS [DBLP:journals/corr/abs-1708-09545]	44.4	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
23	HMT	44.1	No	Hierarchical Multimodal Transformer to Summarize...	2021-09-22	-
24	MAVS [DBLP:conf/mm/FengLKZ18]	43.1	No	Supervised Video Summarization via Multiple Feat...	2021-04-23	Code
25	DR-DSN	42.1	No	Deep Reinforcement Learning for Unsupervised Vid...	2017-12-29	Code

#1PGL-SUM (maximum learning capacity)
57.1
F1-score (Canonical)
No paperCode
#2PGL-SUM
55.6
F1-score (Canonical)
No paperCode
#3PGL-SUM
55.6
F1-score (Canonical)
No paperCode
#4A2SummSOTA
55
F1-score (Canonical)· 2023-03-13
Align and Attend: Multimodal Summarization with Dual Contrastive Losses Code
#5RR-STG
54.5
F1-score (Canonical)
No paper
#6iPTNet
54.5
F1-score (Canonical)· Extra Data
No paper
#7DMASumSOTA
54.3
F1-score (Canonical)· 2020-08-19
Query Twice: Dual Mixture Attention Meta Learning for Video Summarization
#8CLIP-It
54.2
F1-score (Canonical)· 2021-07-01
CLIP-It! Language-Guided Video Summarization Code
#9RR-STG
53.4
F1-score (Canonical)
No paper
#10MSVA
53.4
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#11DSNet
53
F1-score (Canonical)
No paperCode
#12MC-VSA [DBLP:journals/corr/abs-2006-01410]
51.6
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#13SSPVS(+Text)
50.7
F1-score (Canonical)· 2022-01-07
Progressive Video Summarization via Multimodal Self-supervised Learning Code
#14VJMHT
50.6
F1-score (Canonical)· 2021-12-27
Video Joint Modelling Based on Hierarchical Transformer for Co-summarization Code
#15DSNet
50.2
F1-score (Canonical)
No paperCode
#16VASNetSOTA
49.71
F1-score (Canonical)· 2018-12-05
Summarizing Videos with Attention Code
#17SSPVS
48.7
F1-score (Canonical)· 2022-01-07
Progressive Video Summarization via Multimodal Self-supervised Learning Code
#18CSNetSOTA
48.6
F1-score (Canonical)· 2018-11-24
Discriminative Feature Learning for Unsupervised Video Summarization Code
#19VASNet [DBLP:conf/accv/FajtlSAMR18]
48
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#20re-SEQ2SEQ [DBLP:conf/eccv/ZhangGS18]
44.9
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#21M-AVSSOTA
44.4
F1-score (Canonical)· 2017-08-31
Video Summarization with Attention-Based Encoder-Decoder Networks
#22M-AVS [DBLP:journals/corr/abs-1708-09545]
44.4
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#23HMT
44.1
F1-score (Canonical)· 2021-09-22
Hierarchical Multimodal Transformer to Summarize Videos
#24MAVS [DBLP:conf/mm/FengLKZ18]
43.1
F1-score (Canonical)· 2021-04-23
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention Code
#25DR-DSN
42.1
F1-score (Canonical)· 2017-12-29
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward Code