AI Paper Atlas

Research map / Video / Video-language understanding

Vid-Group: Temporal Video Grounding Pretraining from Unlabeled Videos in the Wild

Peijun Bao, Chenqi Kong, Siyuan Yang, Zihao Shao, Xinghao Jiang, Boon Poh Ng, Meng Hwa Er, Alex Kot

ICCV 2025 · Video › Video-language understanding · approach: Temporal video grounding · 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 ReCorrect cleaning, adjustment and memory-consensus correction to GPT-4o pretraining (ablation)GPT-4o Pretraining · Charades-STA (zero-shot)mIoU: 41.43 -> 45.63Improved
add ReCorrect cleaning, adjustment and correction in pretraining plus finetuning (ablation)GPT-4o Pretraining + Finetuning · Charades-STA (unsupervised)mIoU: 40.91 -> 48.66Improved
add SPL pseudo-label refinement to GPT-4o pretrainingGPT-4o Pretraining · Charades-STA (zero-shot)mIoU: 41.43 -> 42.47Improved
add VTG-GPT boundary refinement to GPT-4o pretrainingGPT-4o Pretraining · ActivityNet Captions (zero-shot)mIoU: 33.21 -> 34.47Improved
use ReCorrect instead of SPL refinement in pretrainingGPT-4o Pretraining · Charades-STA (zero-shot)mIoU: 42.47 -> 45.63Improved
add pretraining on Vid-Group before unsupervised finetuning with ReCorrectReCorrect Finetuning · Charades-STA (unsupervised)mIoU: 44.48 -> 48.66Improved
add pretraining on Vid-Group before finetuning with GPT-4o labelsGPT-4o Finetuning · Charades-STA (unsupervised)mIoU: 40.91 -> 44.22Improved
increase pretraining data from 6.3K to 200.3K samples (ablation)ReCorrect · Charades-STA (zero-shot)Avg R@m: 29.14 -> 48.74Improved
concatenate frames into a composite image instead of separate images for GPT-4o (ablation)GPT-4o labeling · Charades-STA (pilot)mIoU: 27.53 -> 28.11No 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