atlas

Research map / Video / Video-language understanding

Object Relational Graph With Teacher-Recommended Learning for Video Captioning

CVPR 2020 · Video › Video-language understanding · approach: Encoder-decoder video captioning · 328 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 ORG to the baseline (ablation)Video captioning model · MSR-VTTCIDEr: 47.9 -> 50.1Helped
add TRL using ELM-generated soft targets (ablation)Video captioning model · MSR-VTTCIDEr: 47.9 -> 50.4Helped
add both ORG and TRL (ablation)Video captioning model · MSR-VTTCIDEr: 47.9 -> 50.9Helped
add both ORG and TRL (ablation)Video captioning model · MSVDCIDEr: 91.7 -> 95.2Helped
replace P-ORG with C-ORG using top-5 connections (ablation)Baseline object-relational encoder · MSR-VTTBLEU-4: 43.1 -> 43.3Helped
increase C-ORG connections from top-1 to top-5 (ablation)Baseline+C-ORG · MSR-VTTCIDEr: 49.3 -> 50.1Helped
increase C-ORG connections from top-5 to top-20 (ablation)Baseline+C-ORG · MSR-VTTCIDEr: 50.1 -> 50.0Hurt
connect each C-ORG node to all nodes instead of top-5 (ablation)Baseline+C-ORG · MSR-VTTCIDEr: 50.1 -> 49.3Hurt

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