IEEE

SDCoT++: Improved Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection

Abstract: Deep learning approaches have demonstrated high effectiveness in 3D object detection tasks. However, they often suffer from a notable drop in performance on the previously trained classes ...
GitHub

Awesome Multi-modal Object Tracking

A Comprehensive Survey: Awesome Multi-modal Object Tracking. Chunhui Zhang, Li Liu, Hao Wen, Xi Zhou, Yanfeng Wang. [paper] [homepage][中文解读] Abstract: Multi-modal object tracking (MMOT) is an emerging ...
GitHub

Class-agnostic Object Detection with Multi-modal Transformer (ECCV 2022)

(Nov 25, 2021) Evaluation code along with pre-trained models & pre-computed predictions is released. evaluation/README.md Abstract: What constitutes an object? This has been a long-standing question ...
IEEE

VoPiFNet: Voxel-Pixel Fusion Network for Multi-Class 3D Object Detection

Abstract: Many LiDAR-based methods for detecting large objects, single-class object detection, or under easy situations were claimed to perform well. However, due to their failure to exploit image ...
MarketWatch

What’s an ‘E-shaped’ economy — and where do you fit in it?

Forget the K-shaped economy. The growing gap between the upper, middle and lower classes suggests we’re in what’s being called an E-shaped economy — which could spell trouble ahead. Since 2020, many ...