AI Paper Atlas

Research map / Video / Video-language understanding

Training-free Video Temporal Grounding using Large-scale Pre-trained Models

Minghang Zheng, Xinhao Cai, Qingchao Chen, Yuxin Peng, Yang Liu

ECCV 2024 · Video › Video-language understanding · approach: Video-language pretraining · 38 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 the VLM localizer with dynamic and static scoring over the naive baseline (ablation)TFVTG · Charades-STAR@0.5: 42.32 -> 48.01Improved
add LLM prompting alone without filtering and integration (ablation)naive baseline · Charades-STAR@0.7: 18.91 -> 18.56No clear effect
add LLM prompting with filtering and integration (ablation)naive baseline · Charades-STAmIoU: 31.61 -> 33.07Improved
add LLM prompting to VLM localizer without filtering (ablation)TFVTG · Charades-STAmIoU: 43.37 -> 42.76Hurt
add filtering and integration on top of LLM + VLM localizer (ablation)TFVTG · Charades-STAR@0.7: 21.94 -> 24.32Improved
add dynamic scoring to the naive baseline (ablation)VLM localizer · Charades-STAmIoU: 31.61 -> 41.68Improved
add static scoring to the naive baseline (ablation)VLM localizer · Charades-STAmIoU: 31.61 -> 41.81Improved
use image-text BLIP-2 instead of video-text VLMs (InterVideo, ViCLIP) (ablation)VLM localizer · Charades-STAmIoU: 40.72 -> 43.37Improved
use stronger LLM (GPT-4 Turbo vs GPT-3.5 Turbo) (ablation)TFVTG · Charades-STAR@0.7: 23.11 -> 24.32Improved
add order and relation constraints from LLM (ablation)Filtering and integration · Charades-STAR@0.5: 42.32 -> 44.12Improved
use training-free method on cross-dataset transfer versus supervised modelsTFVTG · ActivityNet to Charades-STAR@1 R@0.5: 21.45 -> 49.97Improved

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