AI Paper Atlas

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

Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition

Di Hu, Xuhong Li, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiaoxiang Zhu, Dejing Dou

ECCV 2020 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 47 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
concatenate sound representation with image without extra lossaudiovisual ResNet-101 + ResNet-50 · ADVANCE (audiovisual)F-score: 72.85 vs. 72.71No clear effect
add sound event knowledge transfer losses (L_SQ, L_KL, L_E) to multimodal trainingaudiovisual ResNet-101 + ResNet-50 · ADVANCE (audiovisual)F-scoreImproved
add L_E (scene-to-event posterior transfer) rather than multitask L_SQ/L_KLaudiovisual ResNet-101 + ResNet-50 · ADVANCE (audiovisual)F-scoreImproved
add pre-trained weight initialization (image) (ablation)audiovisual ResNet-101 + ResNet-50 · ADVANCE (image only)F-score: 64.04 -> 72.85Improved
add pre-trained weight initialization (sound) (ablation)audiovisual ResNet-101 + ResNet-50 · ADVANCE (sound only)F-score: 21.32 -> 28.99Improved
add L_SQ|Nv+a to image-only networkaudiovisual ResNet-101 + ResNet-50 · ADVANCE (image only)F-score: 72.85 -> 73.98Improved
add L_E to image-only networkaudiovisual ResNet-101 + ResNet-50 · ADVANCE (image only)F-score: 72.85 -> 73.44Improved
add L_E to sound-only networkaudiovisual ResNet-101 + ResNet-50 · ADVANCE (sound only)F-score: 28.99 -> 29.66Improved
add L_KL|Nv+a to sound-only networkaudiovisual ResNet-101 + ResNet-50 · ADVANCE (sound only)F-score: 28.99 -> 28.51Hurt
add event relevance term beta*L_E2 to L_E1 (no Ls) (ablation)audiovisual ResNet-101 + ResNet-50 · ADVANCE (no scene loss Ls)F-score: 42.50 -> 48.65Improved
multitask L_KL|Nv+a instead of L_E when no scene lossaudiovisual ResNet-101 + ResNet-50 · ADVANCE (no scene loss Ls)F-score: 4.46 vs. 48.65Hurt

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