ineffectual
发表于 2025-3-28 17:19:17
http://reply.papertrans.cn/25/2424/242336/242336_41.png
critic
发表于 2025-3-28 21:33:51
http://reply.papertrans.cn/25/2424/242336/242336_42.png
卜闻
发表于 2025-3-28 23:08:16
,Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs,es of all videos, and instance IDs to associate them through time. To this end, we introduce Walker, the first self-supervised tracker that learns from videos with sparse bounding box annotations, and no tracking labels. First, we design a quasi-dense temporal object appearance graph, and propose a
drusen
发表于 2025-3-29 05:04:09
http://reply.papertrans.cn/25/2424/242336/242336_44.png
CRAMP
发表于 2025-3-29 11:15:33
http://reply.papertrans.cn/25/2424/242336/242336_45.png
令人悲伤
发表于 2025-3-29 15:05:49
http://reply.papertrans.cn/25/2424/242336/242336_46.png
咯咯笑
发表于 2025-3-29 17:50:36
,GPSFormer: A Global Perception and Local Structure Fitting-Based Transformer for Point Cloud Underslar point clouds without reliance on external data remains a formidable challenge. To address this problem, we propose ., an innovative .lobal .erception and Local .tructure .itting-based Transf., which learns detailed shape information from point clouds with remarkable precision. The core of GPSFor
烦躁的女人
发表于 2025-3-29 22:20:18
http://reply.papertrans.cn/25/2424/242336/242336_48.png
falsehood
发表于 2025-3-30 03:20:12
,FSD-BEV: Foreground Self-distillation for Multi-view 3D Object Detection,friendly perception solution for autonomous driving, there is still a performance gap compared to LiDAR-based methods. In recent years, several cross-modal distillation methods have been proposed to transfer beneficial information from teacher models to student models, with the aim of enhancing perf
Granular
发表于 2025-3-30 05:26:52
,SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs,hs comprise multiple modalities, including object-level point clouds, images, attributes, and relationships between objects, offering a lightweight and efficient alternative to conventional methods that rely on extensive image databases. Given these modalities, the proposed method SceneGraphLoc lear