AI Paper Atlas

Research map / Video / Video-language understanding

Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset

Grant Van Horn, Rui Qian, Kimberly Wilber, Hartwig Adam, Oisin Mac Aodha, Serge Belongie

ECCV 2022 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 19 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
fuse audio and visual modalities (best fusion vs best single modality)ViT-B audiovisual · SSW60 videostop-1 accuracy: 76.2% -> 80.6%Improved
pretrain visual backbone on Images iNat and audio on unpaired audio instead of ImageNetViT-B audiovisual fusion · SSW60 videos (fusion)top-1 accuracy: 59.8% -> 80.6%Improved
use score fusion instead of mid fusion (MBT) (ablation)ViT-B audiovisual · SSW60 (iNat + Unpair Audio pretrain)top-1 accuracy: 73.5% -> 80.6%Improved
use mid fusion instead of late fusion (ImageNet pretrain) (ablation)ViT-B audiovisual · SSW60 (ImageNet/ImageNet pretrain)top-1 accuracy: 59.8% -> 54.3%Hurt
fine-tune iNat-trained backbone on Video FramesResNet50 · SSW60 Video Framestop-1 accuracy: 60.47 -> 71.88Improved
train on Images iNat instead of Video Frames directlyResNet50 · SSW60 Video Framestop-1 accuracy: 54.92 -> 60.47Improved
fine-tune unpaired audio model on Video AudioResNet18 · SSW60 Video Audiotop-1 accuracy: 24.41 -> 15.33Hurt
pretrain on unpaired audio instead of training on Video Audio onlyResNet18 · SSW60 Video Audiotop-1 accuracy: 10.37 -> 24.41Improved
add time crop augmentation (ablation)ViT-B audio · SSW60 unpaired audiotop-1 accuracy: 44.1 -> 60.6Improved
add frequency mask augmentation (ablation)ViT-B audio · SSW60 unpaired audiotop-1 accuracy: 60.6 -> 66.8Improved
use higher-resolution 384 ViT-B pretrainingViT-B audio · SSW60 unpaired audiotop-1 accuracy: 66.8% -> 65.9%Hurt
add AudioSet pretraining to ViT-B 384ViT-B audio · SSW60 unpaired audiotop-1 accuracy: 65.9% -> 67.4%Improved

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