AI Paper Atlas

Research map / Video / Video-language understanding

Learning Streaming Video Representation via Multitask Training

Yibin Yan, Jilan Xu, Shangzhe Di, Yikun Liu, Yudi Shi, Qirui Chen, Zeqian Li, Yifei Huang, Weidi Xie

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 5 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 global and temporal tasks (ablation)StreamFormer spatial-only · THUMOS-14 OAD (w/o flow)mAP: 51.5 -> 69.1Improved
add spatial-level tasks to global+temporal (ablation)StreamFormer · YouTube-VIS 2019AP: 41.9 -> 45.1Improved
add spatial-level tasks to global+temporal (ablation)StreamFormer · THUMOS-14 OAD (w/o flow)mAP: 69.1 -> 68.4Hurt
add spatial-level tasks to global+temporal (ablation)StreamFormer · VideoMMEaccuracy: 43.1 -> 45.0Improved
add multitask video training over SigLIP image encoderStreamFormer · THUMOS-14 OAD (w/o flow)mAP: 58.9 -> 68.4Improved
add temporal attention (causal) to image model (ablation)StreamFormer · THUMOS-14 OAD (w/o flow, 10% data)mAP: 61.7 -> 62.5Improved
use bidirectional instead of causal temporal attention (ablation)StreamFormer · THUMOS-14 OAD (w/o flow, 10% data)mAP: 62.5 -> 62.8Mixed
use multitask annotated data instead of WebVid-1M contrastive (ablation)StreamFormer · THUMOS-14 OAD (w/o flow)mAP: 57.2 -> 62.5Improved
increase multitask pre-training data from 0.1M to 1M (ablation)StreamFormer · THUMOS-14 OAD (w/o flow)mAP: 62.5 -> 68.4Improved
increase multitask pre-training data from 0.1M to 1M (ablation)StreamFormer · MLVUaccuracy: 49.6 -> 48.4Hurt
add spatial-only tasks to SigLIP baseline (ablation)StreamFormer spatial-only · VideoMMEaccuracy: 40.8 -> 30.0Hurt
replace SigLIP with StreamFormer in CTVISCTVIS · YouTube-VIS 2019AP: 40.9 -> 45.1Improved

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