AI Paper Atlas

Research map / Video / Video segmentation and tracking

PAC-Net: Highlight Your Video via History Preference Modeling

Hang Wang, Penghao Zhou, Chong Zhou, Zhao Zhang, Xing Sun

ECCV 2022 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 1 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 DBC (user-level adaptive classifier) to the generic baseline (ablation)PAC-NetG · PHD-GIFs (Dv3)mAP: 15.28 -> 15.89Improved
add Mi-Hi mechanism with a shared classifier to the baseline (ablation)PAC-NetG · PHD-GIFs (Dv3)mAP: 15.28 -> 16.23Improved
use fine-grained Mi-Hi samples instead of concatenating averaged history (ablation)PAC-NetAgg · PHD-GIFs (Dv3)mAP: 15.67 -> 16.23Improved
concatenate averaged user history feature to the input feature (ablation)PAC-NetG · PHD-GIFs (Dv3)mAP: 15.28 -> 15.67Improved
combine DBC with Mi-Hi (full model) (ablation)PAC-NetG · PHD-GIFs (Dv3)mAP: 15.28 -> 17.51Improved
add non-highlighted history as DBC input (ablation)PAC-Net · PHD-GIFs (Dv3)mAP: 15.66 -> 17.51Improved
allow more user history videos (0 to all M) (ablation)PAC-Net · PHD-GIFs (Dv3)mAP: 15.28 -> 17.51Improved
increase allowed history videos from 3 to 5 (ablation)PAC-Net · PHD-GIFs (Dv3)mAP: 16.38 -> 17.02Improved
use PAC-Net instead of Adaptive-H-FCSNpersonalized highlight detector · PHD-GIFs (Dv3)mAP: 16.04 -> 17.51Improved
use PAC-Net with 5.89M parameters instead of Adaptive-H-FCSN with 197.36Mpersonalized highlight detector · PHD-GIFs (Dv3)parameters (M): 197.36 -> 5.89Improved
use Adaptive-H-FCSN instead of FCSN on the harder Dv3 dataFCSN · PHD-GIFs (Dv3)mAP: 15.09 -> 16.04Improved
transfer generic PAC-NetG trained on PHD-GIFs to SumMe without fine-tuningPAC-NetG · SumMeF-score: 44.4 -> 44.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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