AI Paper Atlas

Research map / Video / Video-language understanding

SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval

Ruixiang Zhao, Zhihao Xu, Bangxiang Lan, Zijie Xin, Jingyu Liu, Xirong Li

CVPR 2026 · Video › Video-language understanding · approach: Text-video retrieval · 0 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 dedicated speech branch (Whisper ASR + CLIP text encoder) (ablation)SAVE · MSRVTT-9kSumR: 211.9 -> 216.2Improved
add audio (sound) branch (ablation)SAVE · MSRVTT-9kSumR: 207.5 -> 216.2Improved
add soft-ALBEF early vision-audio alignment (ablation)SAVE · MSRVTT-9kSumR: 213.8 -> 216.2Improved
use hard-label ALBEF instead of no alignment (ablation)SAVE · MSRVTT-9kSumR: 213.8 -> 211.2Hurt
use soft labels instead of hard labels in ALBEF (ablation)SAVE · MSRVTT-9kSumR: 211.2 -> 216.2Improved
use Pearson distance instead of MSE (ablation)soft-ALBEF · MSRVTT-9kSumR: 215.0 -> 216.2Improved
use ImageBind instead of AudioCLIP as soft-label teacher (ablation)soft-ALBEF · MSRVTT-9kSumR: 215.8 -> 216.2Improved
use early fusion instead of late fusion for speech (ablation)SAVE · MSRVTT-9kSumR: 206.5 -> 216.2Improved
use parameter-free fusion instead of learnable weights (ablation)SAVE · MSRVTT-9kSumR: 215.5 -> 216.2No clear effect
share CLIP text encoder between speech and query (ablation)SAVE · MSRVTT-9kSumR: 214.8 -> 216.2Improved
use Whisper instead of SenseVoice for ASR (ablation)SAVE · MSRVTT-9kSumR: 215.4 -> 216.2Improved
add speech branch and soft-ALBEF to AVIGATEAVIGATE · CharadesSumR: 110.6 -> 121.4Improved

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