Unsupervised Video Summarization On Tvsum

Metrics

F1-score

Parameters (M)

training time (s)

Results

Performance results of various models on this benchmark

				Paper Title
SegSum	62	5.25	-	Integrate the temporal scheme for unsupervised video summarization via attention mechanism
RS-SUM	61.4	-	-	Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative Score.
AC-SUM-GAN	60.6	26.75	9380	AC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial Networks for Unsupervised Video Summarization
CSNet	58.8	100.76	1797	Discriminative Feature Learning for Unsupervised Video Summarization
SUM-GAN-sl	58.4	23.31	3895	A Stepwise, Label-based Approach for Improving the Adversarial Training in Unsupervised Video Summarization
SUM-GAN-AAE	58.3	24.31	5423	Unsupervised Video Summarization via Attention-Driven Adversarial Learning
Cycle-SUM	57.6	-	-	Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
DR-DSN	57.6	2.63	58.8	Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward

0 of 8 row(s) selected.