AI Paper Atlas

Research map / Video / Video-language understanding

OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding

Minghang Zheng, Zihao Yin, Yi Yang, Yuxin Peng, Yang Liu

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 2 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 multi-task SFT on OmniVTG (ablation)Qwen2.5-VL-7B · OmniVTG test set (Full)R1@0.5: 34.5 -> 62.3Improved
add multi-task SFT on OmniVTG (ablation)Qwen2.5-VL-7B · ActivityNet CaptionsR1@0.5: 13.6 -> 25.6Improved
add self-correction CoT finetuning after SFT (ablation)SFT model · OmniVTG test set (Rare)R1@0.5: 59.6 -> 61.3Improved
add self-correction CoT finetuning after SFT (ablation)SFT model · ActivityNet CaptionsR1@0.5: 25.6 -> 32.5Improved
add self-correction CoT finetuning after SFT (ablation)SFT model · OmniVTG test set (Full)R1@0.5: 62.3 -> 62.4No clear effect
add RL on top of SFT + CoT (ablation)SFT + CoT model · ActivityNet CaptionsR1@0.5: 32.5 -> 39.8Improved
add RL on top of SFT + CoT (ablation)SFT + CoT model · OmniVTG test set (Full)R1@0.5: 62.4 -> 63.3Improved
add CoT finetuning before RL (ablation)SFT + RL model · ActivityNet CaptionsR1@0.5: 37.2 -> 39.8Improved
increase SFT data from 10% to 100% (ablation)SFT model · OmniVTG test set (Full)R1@0.5: 41.9 -> 62.3Improved
add content-aware reflection instead of no reasoning (ablation)SFT model · ActivityNet CaptionsR1@0.5: 25.6 -> 39.8Improved
use content-aware rather than rule-based reflection (ablation)OmniVTG CoT · ActivityNet CaptionsR1@0.5: 37.9 -> 39.8Improved
use content-aware rather than rule-based reflection (ablation)OmniVTG CoT · OmniVTG test set (Rare)R1@0.5: 61.0 -> 62.4Improved

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