SOTAVerified

Video Summarization

Video Summarization aims to generate a short synopsis that summarizes the video content by selecting its most informative and important parts. The produced summary is usually composed of a set of representative video frames (a.k.a. video key-frames), or video fragments (a.k.a. video key-fragments) that have been stitched in chronological order to form a shorter video. The former type of a video summary is known as video storyboard, and the latter type is known as video skim.

Source: Video Summarization Using Deep Neural Networks: A Survey Image credit: iJRASET

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 280 papers

TitleStatusHype
A Paradigm for Building Generalized Models of Human Image Perception Through Data Fusion—0
Creating Summaries from User Videos—0
A Memory Network Approach for Story-based Temporal Summarization of 360° Videos—0
Co-Regularized Deep Representations for Video Summarization—0
Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization—0
DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization—0
A Survey on Patch-based Synthesis: GPU Implementation and Optimization—0
Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance—0
Detecting Engagement in Egocentric Video—0
Discovery of Shared Semantic Spaces for Multi-Scene Video Query and Summarization—0
Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers—0
Enhancing Video Summarization via Vision-Language Embedding—0
Conditional Modeling Based Automatic Video Summarization—0
A Novel Trustworthy Video Summarization Algorithm Through a Mixture of LoRA Experts—0
Comprehensive Video Understanding: Video summarization with content-based video recommender design—0
Compare and Select: Video Summarization with Multi-Agent Reinforcement Learning—0
A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks—0
A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation—0
Facilitating the Production of Well-tailored Video Summaries for Sharing on Social Media—0
Common Action Discovery and Localization in Unconstrained Videos—0
Submodular Maximization in Clean Linear Time—0
CNN-Based Prediction of Frame-Level Shot Importance for Video Summarization—0
A Graph-based Ranking Approach to Extract Key-frames for Static Video Summarization—0
EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos—0
CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion—0
Show:102550
← PrevPage 3 of 12Next →
All datasetsSumMeTvSumShot2Story20KQuery-Focused Video Summarization DatasetMr. HiSumVideoXum

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PGL-SUMF1-score (Canonical)55.6—Unverified
2RR-STGF1-score (Canonical)54.5—Unverified
3DSNetF1-score (Canonical)53—Unverified
4VASNetF1-score (Canonical)49.71—Unverified
5M-AVSF1-score (Canonical)44.4—Unverified
6CSTAKendall's Tau0.25—Unverified
#ModelMetricClaimedVerifiedStatus
1RR-STGF1-score (Canonical)63—Unverified
2DSNetF1-score (Canonical)62.1—Unverified
3VASNetF1-score (Canonical)61.42—Unverified
4M-AVSF1-score (Canonical)61—Unverified
5PGL-SUMF1-score (Canonical)61—Unverified
6CSTAKendall's Tau0.19—Unverified
#ModelMetricClaimedVerifiedStatus
1Shotluck-Holmes (3.1B)CIDEr152.3—Unverified
2Shotluck-Holmes (3.1B)CIDEr63.2—Unverified
3SUM-shotCIDEr8.6—Unverified
#ModelMetricClaimedVerifiedStatus
1EgoVLPv2F1 (avg)52.08—Unverified
2EgoVLPF1 (avg)49.72—Unverified
#ModelMetricClaimedVerifiedStatus
1PGL-SUMMAP (50%)61.6—Unverified
#ModelMetricClaimedVerifiedStatus
1VTSUM-BLIP1 shot Micro-F123.5—Unverified