AI Paper Atlas

Research map / Video / Video-language understanding

Query-Focused Extractive Video Summarization

Aidean Sharghi, Boqing Gong, Mubarak Shah

ECCV 2016 · Video › Video-language understanding · approach: Dense video captioning · 135 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
use SH-DPP (query layer plus sequential summary layer) instead of vanilla DPPquery-focused summarizer · TV episodes, patient user, bi-concept queriesF-measure (%): 29.62 -> 37.02Improved
use SH-DPP instead of seqDPPquery-focused summarizer · UTE, patient user, bi-concept queriesF-measure (%): 18.85 -> 21.27Mixed
use SH-DPP instead of seqDPPquery-focused summarizer · UTE, impatient user, bi-concept querieshitting recall (%): 12.68 -> 22.91Improved
use SH-DPP instead of uniform samplingquery-focused summarizer · UTE, impatient user, bi-concept queriesF-measure (%): 25.44 -> 25.56No clear effect
use SH-DPP instead of SubModquery-focused summarizer · UTE, impatient user, bi-concept queriesF-measure (%): 27.10 -> 25.56Hurt
use SH-DPP trained on bi-concept queries for novel three-concept queries (vs DPP)SH-DPP · UTE, patient user, three-concept queriesF-measure (%): 20.7 -> 24.54Improved
use SH-DPP instead of seqDPP on three-concept queriesSH-DPP · UTE, impatient user, three-concept queriesF-measure (%): 19.4 -> 29.59Improved
add dependency between adjacent subsets (seqDPP) vs DPP on long egocentric UTE videos (ablation)DPP · UTE, patient user, bi-concept queriesF-measure (%): 15.7 -> 18.85Improved
add dependency between adjacent subsets (seqDPP) vs DPP on TV episodes (ablation)DPP · TV episodes, patient user, bi-concept queriesF-measure (%): 29.62 -> 27.96No clear effect
vary ground set size from 6 to 10 shots (ablation)SH-DPP · TV episodesF-measureNo clear effect
use very small (4 shots) or large (16 shots) ground set (ablation)SH-DPP · TV episodesF-measureHurt
vary lower-dimension of W and V (ablation)SH-DPP · UTE and TVF-measureNo clear effect

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