AI Paper Atlas

Research map / Video / Video-language understanding

ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning

Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Patras, Ioannis Kompatsiaris

ICCV 2019 · Video › Video-language understanding · approach: Dense video captioning · 86 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 whitening (ablation)ViSiL_f · FIVR-5K DSVRmAP: 0.838 -> 0.844Improved
add whitening (ablation)ViSiL_f · FIVR-5K ISVRmAP: 0.739 -> 0.750Improved
add attention mechanism (ablation)ViSiL_f+W · FIVR-5K ISVRmAP: 0.750 -> 0.768Improved
add attention mechanism (ablation)ViSiL_f+W · FIVR-5K DSVRmAP: 0.844 -> 0.856Improved
add video-level CNN for refined similarity (ablation)ViSiL_f+W+A · FIVR-5K DSVRmAP: 0.856 -> 0.880Improved
add video-level CNN for refined similarity (ablation)ViSiL_f+W+A · FIVR-5K CSVRmAP: 0.848 -> 0.869Improved
add similarity regularization loss (ablation)ViSiL_v · FIVR-5K DSVRmAP: 0.859 -> 0.880Improved
add similarity regularization loss (ablation)ViSiL_v · FIVR-5K ISVRmAP: 0.756 -> 0.777Improved
use asymmetric Chamfer similarity instead of symmetric (ablation)ViSiL · FIVR-5K DSVRmAP: 0.830 -> 0.880Improved
use multi-level regions (L3-iMAC) instead of iMAC (ablation)frame features · FIVR-5K DSVRmAP: 0.755 -> 0.838Improved
use max-pooling in frame-to-frame similarity instead of average pooling (ablation)ViSiL_v · FIVR-5K DSVRmAP: 0.769 -> 0.880Improved
use Chamfer (max then average) in video-to-video similarity instead of two average poolings (ablation)ViSiL_v · FIVR-5K DSVRmAP: 0.640 -> 0.880Improved

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