7 citations · 12 across the 19 of their papers we have counts for
20 papers
ControlRadio: Prompt-Driven Controllable Diffusion for Cross-Modal Radio Map Generation
Kangjun Liu, Xiying Pan, Shuhang Zhang +3
Radio maps describe how wireless signals propagate across space and are essential for wireless communication, sensing, and network planning. However, constructing accurate radio ma…
RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modeling
Zheng Fang, Junjie Liu, Kangjun Liu +3
With the emergence of wireless applications in three-dimensional environments, such as the low-altitude airspace and 3D heterogeneous networks, radio map estimation is increasingly…
CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception
Liupeng Li, Haoqian Kang, Zhenyu Lu +4
High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods stru…
SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation
Zhenyu Lu, Liupeng Li, Jinpeng Wang +4
While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Cur…
C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models
Junhao Li, Xinhao Zhong, Yi sun +4
Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation, yet their personalization capabilities remain largely limited to sta…
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
Haoyu Zhang, Qiaohui Chu, Yisen Feng +4
This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participants must answer 185 closed-for…
Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
Jun Li, Peifeng Lai, Xuhang Lou +5
Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries an…
DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
Yuqing Chen, Lin Liu, Haisu Wu +4
Video object removal frequently struggles to eliminate target objects and their associated complex physical effects (e.g., smoke and light) in real-world scenes. We attribute this…
UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data
Longkun Zou, Jiale Wang, Rongqin Liang +3
Accurate perception of UAVs in complex low-altitude environments is critical for airspace security and related intelligent systems. Developing reliable solutions requires large-sca…
LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space
Hai Wu, Shuai Tang, Jiale Wang +5
Perception of Low-Altitude Aircraft (LAA) in 3D space enables precise 3D object localization and behavior understanding. However, datasets tailored for 3D LAA perception remain sca…
RadioDUN: A Physics-Inspired Deep Unfolding Network for Radio Map Estimation
Taiqin Chen, Zikun Zhou, Zheng Fang +5
The radio map represents the spatial distribution of spectrum resources within a region, supporting efficient resource allocation and interference mitigation. However, it is diffic…
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Longkun Zou, Kangjun Liu, Ke Chen +3
Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition meth…
RadioFormer: A Multiple-Granularity Radio Map Estimation Transformer with 1\textpertenthousand Spatial Sampling
Zheng Fang, Kangjun Liu, Ke Chen +4
The task of radio map estimation aims to generate a dense representation of electromagnetic spectrum quantities, such as the received signal strength at each grid point within a ge…
OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensing
Xiang Xiang, Zhuo Xu, Yao Deng +7
The advancement of remote sensing, including satellite systems, facilitates the continuous acquisition of remote sensing imagery globally, introducing novel challenges for achievin…
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
Longkun Zou, Wanru Zhu, Ke Chen +4
Semantic pattern of an object point cloud is determined by its topological configuration of local geometries. Learning discriminative representations can be challenging due to larg…
MixBCT: Towards Self-Adapting Backward-Compatible Training
Yu Liang, Yufeng Zhang, Shiliang Zhang +4
Backward-compatible training circumvents the need for expensive updates to the old gallery database when deploying an advanced new model in the retrieval system. Previous methods a…
ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States
Kangjun Liu, Ke Chen, Lihua Guo +2
Mixup style data augmentation algorithms have been widely adopted in various tasks as implicit network regularization on representation learning to improve model generalization, wh…
Improving Deep Representation Learning via Auxiliary Learnable Target Coding
Kangjun Liu, Ke Chen, Kui Jia +1
Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existin…
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
Yichen Zhang, Jiehong Lin, Ke Chen +3
Domain gap between synthetic and real data in visual regression (e.g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse c…
Classification of Single-View Object Point Clouds
Zelin Xu, Ke Chen, Kangjun Liu +3
Object point cloud classification has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet. These benchmarks assume poin…