SOTAVerified

Supervised Video Summarization

Supervised video summarization rely on datasets with human-labeled ground-truth annotations (either in the form of video summaries, as in the case of the SumMe dataset, or in the form of frame-level importance scores, as in the case of the TVSum dataset), based on which they try to discover the underlying criterion for video frame/fragment selection and video summarization.

Source: Video Summarization Using Deep Neural Networks: A Survey

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–28 of 28 papers

TitleStatusHype
Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsCode0
Discriminative Feature Learning for Unsupervised Video SummarizationCode0
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web PriorCode0
Improving Sequential Determinantal Point Processes for Supervised Video Summarization—0
How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization—0
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness RewardCode0
Video Summarization with Attention-Based Encoder-Decoder Networks—0
Diverse Sequential Subset Selection for Supervised Video Summarization—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.