9 accepted papers
Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and inference costs, as well as challenges in extracting visual det
Point cloud instance segmentation is crucial for 3D scene understanding in robotics. However, existing methods heavily rely on learning-based approaches that require large amounts of annotated 3D data, resulting in high annotation costs. Therefore, developing cost-effective and data-efficient soluti
Open-vocabulary 3D instance segmentation (OV-3DIS), which aims to segment and classify objects beyond predefined categories, is a critical capability for embodied AI applications. Existing methods rely on pre-trained 2D foundation models, focusing on instance-level features while overlooking context…
Text-based person retrieval aims at retrieving a specific pedestrian image from a gallery based on textual descriptions. The primary challenge is how to overcome the inherent heterogeneous modality gap in the situation of significant intra-class variation and minimal inter-class variation. Existing…
This paper investigates the coverage performance of millimeter wave (mmWave) unmanned aerial vehicle (UAV) networks. Due to the sensitivity of mmWave to both static and moving obstacles, we aim to improve generality and gain more in-depth insights by simultaneously considering the effects of static…
Acting as dynamic base stations, unmanned aerial vehicles have a significant advantage over conventional base stations for dynamic object localization and tracking. In practice, however, the localization and tracking performance highly depends on the observation sequence of time-variant received sig…
In this paper, we aim to implement outdoor-to-indoor communication with the aid of an active reconfigurable intelligent surface (active-RIS), where the active-RIS allows the incoming signal from an outdoor base station (BS) to pass through the surface and be received by indoor users (UEs) after shif…
Acting as the dynamic base stations, the unmanned aerial vehicles has a significant advantage over the conventional base station for target localization. When localizing a target, UAV can move toward the estimated target location after each estimation, making the received signals stronger after each…
This paper considers the Base Station (BS) clustering in a downlink heterogeneous network with finite backhaul capacity. We consider a tree structure network where each BS has only one incoming link and several outgoing links. The objective is to maximize the minimum rate among all users while satis…