AI Paper Atlas

Research map / Video / Video segmentation and tracking

Improving Sequential Determinantal Point Processes for Supervised Video Summarization

Aidean Sharghi, Ali Borji, Chengtao Li, Tianbao Yang, Boqing Gong

ECCV 2018 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 43 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train SeqDPP with the large-margin algorithm instead of MLESeqDPP · Egocentric video summarization (12 videos)AUC (Pi filter): 9.71 -> 15.05Improved
train SeqDPP with the large-margin algorithm instead of MLESeqDPP · Egocentric video summarization (12 videos)AUC (Gaussian filter): 9.56 -> 14.69Improved
replace the conditional DPPs of SeqDPP with GDPP to accept an expected summary length (SeqGDPP)SeqDPP · Egocentric video summarization (12 videos)AUC (Pi filter): 9.71 -> 15.29Improved
replace the conditional DPPs of SeqDPP with GDPP to accept an expected summary length (SeqGDPP)SeqDPP · Egocentric video summarization (12 videos)AUC (Gaussian filter): 9.56 -> 14.86Improved
add large-margin training to SeqGDPPSeqGDPP · Egocentric video summarization (12 videos)AUC (Pi filter): 15.29 -> 15.87Improved
add large-margin training to SeqGDPPSeqGDPP · Egocentric video summarization (12 videos)AUC (Gaussian filter): 14.86 -> 15.43Improved
use SeqGDPP (length-aware) instead of large-margin SeqDPPLM-SeqDPP · Egocentric video summarization (12 videos)AUC (Pi filter): 15.05 -> 15.29Improved
remove temporal filter restriction (filter parameters to infinity, original BM metric) when comparing modelsevaluation metric · Egocentric video summarization (12 videos)BM vs filtered F1Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy