AI Paper Atlas

Research map / Video / Video-language understanding

Grounded Video Situation Recognition

Zeeshan Khan, C.V. Jawahar, Makarand Tapaswi

NeurIPS 2022 · Video › Video-language understanding · approach: Dense video captioning · 6 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 role-object decoder instead of role-video decoder (ablation)VideoWhisperer · VidSitu SRLCIDEr: 47.91 -> 70.48Improved
add video-object encoder before role-object decoder (ablation)VideoWhisperer · VidSitu groundingIoU@0.3: 0.14 -> 0.29Improved
add video-object encoder before role-object decoder (ablation)VideoWhisperer · VidSitu groundingIoU@0.5: 0.06 -> 0.12Improved
add video-object encoder before role-object decoder (ablation)VideoWhisperer · VidSitu SRLCIDEr: 70.48 -> 68.54No clear effect
contextualize objects with events (VO instead of V) (ablation)VideoWhisperer · VidSitu groundingIoU@0.3: 0.23 -> 0.29Improved
use joint VOR encoder instead of staged RO decoder (ablation)VideoWhisperer · VidSitu SRLCIDEr: 70.48 -> 67.4Hurt
use event embedding instead of GT-verb in role query (ablation)VideoWhisperer · VidSitu groundingIoU@0.3: 0.25 -> 0.29Improved
use event embedding instead of GT-verb in role query (ablation)VideoWhisperer · VidSitu SRLCIDEr: 68.71 -> 68.54No clear effect
role embedding alone as query (ablation)VideoWhisperer · VidSitu SRLCIDEr: 68.61 -> 68.54No clear effect
add masking in RO decoder cross-attention (ablation)VideoWhisperer · VidSitu SRLCIDEr: 67.02 -> 68.54Improved
add masking in RO decoder cross-attention (ablation)VideoWhisperer · VidSitu groundingIoU@0.3: 0.25 -> 0.29Improved
replace independent clip prediction with video-only transformer encoder (ablation)verb predictor · VidSituAcc@1: 46.79 -> 48.82Improved

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