activity
20242026
collaborators

17 papers

cs.CV2026

SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition

Shunpeng Chen, Changwei Wang, Rongtao Xu +7

Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fin…

cs.CV2026

DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval

Xingtian Pei, Yukun Song, Changwei Wang +4

Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification t…

cs.AI2026

DialogueVPR: Towards Conversational Visual Place Recognition

Yukun Song, Changwei Wang, Xingtian Pei +8

Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progres…

cs.CV2026

Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition

Shunpeng Chen, Yukun Song, Changwei Wang +6

Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasin…

eess.SP2026

SE-EE Tradeoff in Pinching-Antenna Systems: Waveguide Multiplexing or Waveguide Switching?

Guangyu Zhu, Xidong Mu, Li Guo +3

The spectral and energy efficiency (SE-EE) trade-off in pinching-antenna systems (PASS) is investigated in this paper. In particular, two practical operating protocols, namely wave…

cs.CV2025

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion

Rongtao Xu, Jinzhou Lin, Jialei Zhou +6

Camera-based occupancy prediction is a mainstream approach for 3D perception in autonomous driving, aiming to infer complete 3D scene geometry and semantics from 2D images. Almost…