AI Paper Atlas

Research map / Video / Video segmentation and tracking

Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-Wise Pseudo Labeling

Jinxing Zhou, Dan Guo, Yiran Zhong, Meng Wang

IJCV 2024 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 38 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
add PLG video-level visual pseudo labels to HAN (ablation)HAN · LLP test, visual segment-levelV F-score: 52.9 -> 64.1Improved
add PLG video-level pseudo labels to HAN, audio effect (ablation)HAN · LLP test, audio segment-levelA F-score: 60.1 -> 59.8No clear effect
add naive segment-level BCE loss (PLE) on PLG labels (ablation)HAN + PLG · LLP test, segment-levelType@AV F-score: 60.5 -> 61.6Improved
use richness-aware loss instead of naive BCE segment loss (ablation)HAN + PLG · LLP test, segment-levelType@AV F-score: 61.6 -> 62.0Improved
add category-richness alignment to the richness-aware loss (ablation)HAN + PLG · LLP test, segment-levelEvent@AV F-score: 58.3 -> 60.2Improved
add segment-richness alignment to the richness-aware loss (ablation)HAN + PLG · LLP test, segment-levelType@AV F-score: 60.5 -> 61.3Improved
add PLD denoising of visual pseudo labels (ablation)HAN + PLG + PLE · LLP test, segment-levelType@AV F-score: 62.0 -> 63.1Improved
add PLD to visual pseudo labels (K=5, alpha=30) (ablation)PLG visual pseudo labels · LLP val, pseudo-label qualityaverage F-score: 67.95 -> 70.63Improved
add PLD to audio pseudo labels (K=6, alpha=400) (ablation)PLG audio pseudo labels · LLP val, pseudo-label qualityaverage F-score: 75.93 -> 76.06No clear effect
raise visual threshold tau_v from 0.041 to 0.042 (ablation)PLG visual pseudo labels · LLP valsegment-level V F-score: 71.08 -> 51.51Hurt
use prompt VP1 rather than VP3 for CLIP (ablation)PLG visual pseudo labels · LLP valsegment-level V F-score: 67.60 -> 71.08Improved
use PLG pseudo labels instead of assigning video labels to the visual modality (ablation)visual pseudo labels · LLP valvideo-level precision: 66.96 -> 86.88Improved

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