AI Paper Atlas

Research map / Video / Video-language understanding

DisTime: Distribution-based Time Representation for Video Large Language Models

Yingsen Zeng, Zepeng Huang, Yujie Zhong, Chengjian Feng, Jie Hu, Lin Ma, Yang Liu

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 10 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
predict timestamps via a distribution decoder instead of direct regression (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.5: 51.9 -> 53.5Improved
predict timestamps via a distribution decoder instead of direct regression (ablation)DisTime (InternVL2.5-1B) · YouCook2F1 Score: 2.2 -> 16.3Improved
add time token re-encoding (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.7: 26.7 -> 29.7Improved
add time token re-encoding (ablation)DisTime (InternVL2.5-1B) · YouCook2CIDEr: 4.0 -> 15.6Improved
add InternVid-TG training data (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.7: 22.9 -> 29.7Improved
add InternVid-TG training data (ablation)DisTime (InternVL2.5-1B) · QVHighlightsmAP@.5: 34.8 -> 47.9Improved
add Momentor data to training (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.7: 22.9 -> 21.6Hurt
expand InternVid-TG from 90k-video subset to full 179k videos (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.5: 55.5 -> 56.3Improved
use 32 bins instead of 64 in time decoder (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.5: 53.7 -> 56.3Improved
use 32 bins instead of 16 in time decoder (ablation)DisTime (InternVL2.5-1B) · YouCook2CIDEr: 12.1 -> 15.6Mixed
use 3 layers in time encoder/decoder instead of 2 (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.5: 52.4 -> 56.3Improved
use 4 layers instead of 3 in time encoder/decoder (ablation)DisTime (InternVL2.5-1B) · Charades-STAR@1 IoU=0.5: 56.3 -> 54.4Hurt

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