Supervised Video Summarization On Summe

評価指標

F1-score (Canonical)

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 (Canonical)	Paper Title	Repository
MC-VSA [DBLP:journals/corr/abs-2006-01410]	51.6	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
iPTNet	54.5	Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer	-
RR-STG	53.4	Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization	-
VASNet [DBLP:conf/accv/FajtlSAMR18]	48	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
CLIP-It	54.2	CLIP-It! Language-Guided Video Summarization
PGL-SUM	55.6	Combining Global and Local Attention with Positional Encoding for Video Summarization
re-SEQ2SEQ [DBLP:conf/eccv/ZhangGS18]	44.9	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
HMT	44.1	Hierarchical Multimodal Transformer to Summarize Videos	-
VJMHT	50.6	Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
MAVS [DBLP:conf/mm/FengLKZ18]	43.1	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
DR-DSN	42.1	Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward
DMASum	54.3	Query Twice: Dual Mixture Attention Meta Learning for Video Summarization	-
CSTA	-	CSTA: CNN-based Spatiotemporal Attention for Video Summarization
PGL-SUM (maximum learning capacity)	57.1	Combining Global and Local Attention with Positional Encoding for Video Summarization
SSPVS	48.7	Progressive Video Summarization via Multimodal Self-supervised Learning
MSVA	53.4	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
DSNet	50.2	DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
A2Summ	55.0	Align and Attend: Multimodal Summarization with Dual Contrastive Losses
M-AVS [DBLP:journals/corr/abs-1708-09545]	44.4	Supervised Video Summarization via Multiple Feature Sets with Parallel Attention
CSNet	48.6	Discriminative Feature Learning for Unsupervised Video Summarization

0 of 21 row(s) selected.