Supervised Video Summarization On Tvsum

評価指標

F1-score (Augmented)

F1-score (Canonical)

Kendall's Tau

Spearman's Rho

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	F1-score (Augmented)	F1-score (Canonical)	Kendall's Tau	Spearman's Rho	Paper Title	Repository
CLIP-It	69.0	66.3	0.108	0.147	CLIP-It! Language-Guided Video Summarization
DMASum	-	61.4	0.203	0.267	Query Twice: Dual Mixture Attention Meta Learning for Video Summarization	-
VJMHT	61.9	60.9	0.097	0.105	Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
DR-DSN	59.8	58.1	-	-	Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
PGL-SUM	-	61.0	0.157	0.206	Combining Global and Local Attention with Positional Encoding for Video Summarization
CSTA	-	-	0.194	0.255	CSTA: CNN-based Spatiotemporal Attention for Video Summarization
MAVS [DBLP:conf/mm/FengLKZ18]	-	67.5	-	-	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
SSPVS(+Text)	-	60.4	0.181	0.238	Progressive Video Summarization via Multimodal Self-supervised Learning
iPTNet	64.2	63.4	0.134	0.163	Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer	-
DSNet	63.9	62.1	-	-	DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
SSPVS	61.8	60.3	0.177	0.233	Progressive Video Summarization via Multimodal Self-supervised Learning
re-SEQ2SEQ [DBLP:conf/eccv/ZhangGS18]	-	63.9	-	-	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
VASNet [DBLP:conf/accv/FajtlSAMR18]	-	59.8	-	-	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
MC-VSA [DBLP:journals/corr/abs-2006-01410]	-	63.7	-	-	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
MSVA	-	61.5	0.190	0.210	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
CSNet	57.1	58.5	-	-	Discriminative Feature Learning for Unsupervised Video Summarization
PGL-SUM (maximum learning capacity)	-	62.7	-	-	Combining Global and Local Attention with Positional Encoding for Video Summarization
M-AVS [DBLP:journals/corr/abs-1708-09545]	-	61	-	-	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
RR-STG	63.6	63.0	0.162	0.212	Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization	-
A2Summ	-	63.4	0.137	0.165	Align and Attend: Multimodal Summarization with Dual Contrastive Losses

0 of 21 row(s) selected.