AI Paper Atlas

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

XVO: Generalized Visual Odometry via Cross-Modal Self-Training

Lei Lai, Zhongkai Shangguan, Jimuyang Zhang, Eshed Ohn-Bar

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 22 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 semi-supervised self-training on pseudo-labeled YouTube video (student) to nuScenes teacherXVO · KITTI seqs 03-10 averaget_rel / r_rel: 25.27 -> 15.17 t_rel; 8.17 -> 4.08 r_relImproved
add uncertainty-based pseudo-label filtering (ablation)Student · KITTI seqs 03-10 averaget_rel: 18.73 -> 15.17Improved
add uncertainty-based filtering (ablation)Student · nuScenes unseen regionst_err: 9.32 -> 10.54Mixed
add audio prediction auxiliary task (ablation)Student · KITTI 00-10t_err: 17.04 -> 14.37Improved
add audio prediction auxiliary task (ablation)Student · Argoverse 2t_err: 9.16 -> 8.00Improved
add audio prediction auxiliary task (ablation)Student · nuScenes unseen regionst_err: 10.54 -> 9.26Improved
add segmentation auxiliary task (ablation)Student · nuScenes unseen regionst_err: 10.54 -> 11.35Hurt
add depth auxiliary task (ablation)Student · KITTI 00-10 / nuScenest_err: 17.04 -> 17.49 (KITTI); 10.54 -> 11.86 (nuScenes)Mixed
add flow auxiliary task (ablation)Student · KITTI 00-10t_err: 17.04 -> 15.60Improved
combine all four auxiliary tasks instead of audio alone (ablation)Student+Audio · KITTI 00-10t_err: 14.37 -> 16.74Hurt
add noise to camera intrinsics for TartanVOTartanVO · KITTI seqs 03-10 averaget_rel: 5.93 -> 11.72 (10% noise) -> 24.51 (30% noise)Hurt

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