9 papers
All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping
Yang Li, Aming Wu, Zihao Zhang +3
To advance the development of embodied intelligence, Open-Environment Active 3D Mapping has attracted increasing attention, aiming to perform a long-horizon and shortest trajectory…
Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection
Zihao Zhang, Aming Wu, Yang Li +1
In this paper, we study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains. Ex…
Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation
Zihao Zhang, Aming Wu, Yang Li +2
Novel class discovery in point cloud segmentation aims to transfer knowledge from known classes to automatically identify and segment unlabeled novel classes in point clouds. Exist…
Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation
Xitie Zhang, Aming Wu, Yahong Han
Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-cont…
PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis
Dexiang Li, Zhenning Che, Haijun Zhang +3
Pavement condition assessment is essential for road safety and maintenance. Existing research has made significant progress. However, most studies focus on conventional computer vi…
Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning
Yang Li, Aming Wu, Zihao Zhang +1
Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e.,…
Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection
Zihao Zhang, Yang Li, Aming Wu +1
In this paper, we focus on Single-Domain Generalized Object Detection (Single-DGOD), aiming to transfer a detector trained on one source domain to multiple unknown domains. Existin…
Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
Yang Li, Aming Wu, Zihao Zhang +1
In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervi…
Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios
Deng Li, Aming Wu, Yang Li +2
In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and tes…