AI Paper Atlas

Research map / Video / Action recognition

Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability

Chenzhaoyu, Hongnan Lin, Yongwei Nie, Fei Ma, Xuemiao Xu, Fei Yu, Chengjiang Long

ICLR 2026 · Video › Action recognition · approach: Fully supervised temporal action detection · 0 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 Invert-TVG auxiliary tasks to Time-R1* training (3B)Qwen2.5-VL-3B RL · Charades-STAR1@0.7: 36.9 -> 44.0Improved
add Invert-TVG auxiliary tasks (7B)Qwen2.5-VL-7B RL · Charades-STAR1@0.7: 50.1 -> 51.4Improved
add all three inversion tasks versus only video description (ablation)Invert4TVG · Charades-STAR1@0.7: 39.4 -> 44.0Improved
add all three inversion tasks versus only action recognition (ablation)Invert4TVG · Charades-STAR1@0.7: 43.8 -> 44.0Improved
add all three inversion tasks versus only verb completion (ablation)Invert4TVG · Charades-STAR1@0.5: 68.0 -> 69.0Improved
add video description to VC+AR (ablation)Invert4TVG · Charades-STAR1@0.7: 43.8 -> 44.0Improved
add action recognition to VC+VD (ablation)Invert4TVG · Charades-STAR1@0.7: 42.1 -> 44.0Improved
add verb completion to AR+VD (ablation)Invert4TVG · Charades-STAR1@0.7: 43.6 -> 44.0Improved
add only inversion task VD to TVG-only training (ablation)Time-R1* 3B · Charades-STAR1@0.7: 36.9 -> 39.4Improved
use binary 0/1 Invert-TVG reward instead of cosine similarity (ablation)Invert4TVG · Charades-STAR1@0.7: 39.8 -> 44.0Improved
use binary reward instead of cosine similarity (ablation)Invert4TVG · Charades-STAR1@0.5: 62.2 -> 69.0Improved
add Invert-TVG tasks within same training time budgetInvert4TVG · Charades-STAtraining time: 80 hours -> 80 hoursNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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