AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset

Jing Liu, Sihan Chen, Xingjian He, Longteng Guo, Xinxin Zhu, Weining Wang, Jinhui Tang

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 185 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 audio modality and VALOR-1M pretraining (VALOR_B vs vision-only VALOR_B^-)VALOR_B · VALOR-32K retrievalR@1: 43.3 -> 67.9Improved
add audio modality and VALOR-1M pretrainingVALOR_B · MSRVTT retrievalR@1: 36.2 -> 43.0Improved
add audio modality and VALOR-1M pretrainingVALOR_B · VALOR-32K audiovisual captioningCIDEr: 44.3 -> 55.7Improved
use dual softmax (DSL) post-processing at evaluationVALOR_L · VALOR-32K retrievalR@1: 73.2 -> 80.9Improved
pretrain on VALOR-1M instead of WebVid-2.5M (ablation)VALOR (Video Swin-S) · MSRVTT retrievalR@1: 35.7 -> 39.5Improved
pretrain on VALOR-1M instead of HD_VILA_10M (ablation)VALOR (Video Swin-S) · MSRVTT retrievalR@1: 30.4 -> 39.5Improved
add T-AV modality group to T-V only MGA pretraining (ablation)MGA pretraining · VALOR-32K T-AV retrieval (finetune)R@1: 46.9 -> 55.4Improved
use only T-AV group instead of T-V on T-V benchmark (ablation)MGA pretraining · VALOR-32K T-V (finetune)R@1: 42.7 -> 40.1Hurt
add T-V, T-A and T-AV groups together vs T-AV alone (ablation)MGA pretraining · VALOR-32K T-A (finetune)R@1: 12.3 -> 17.0Improved
add V-A, A-TV, V-TA groups on top of T-V/T-A/T-AV (ablation)MGA pretraining · VALOR-32K T-AV (finetune)R@1: 55.6 -> 54.0Hurt
use fine-grained plus weighted average instead of coarse score fusion (ablation)MGA T-AV · AVR VALOR-32KR@1: 53.4 -> 55.4Improved
use concatenated cross attention instead of merge attention (ablation)MGC T-AV decoder · VALOR-32K AVCCIDEr: 48.2 -> 50.0Improved

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