40 citations · 101 across the 28 of their papers we have counts for
28 papers
Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation
Lee En-Yi Hannah, Haozhi Cao, Yuecong Xu
Federated Video Domain Adaptation (FVDA) enables collaborative learning across distributed and non-IID video datasets while preserving privacy, but is under-explored due to challen…
When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
Tao Wu, Chuhao Zhou, Guangyu Zhao +3
Embodied Question Answering (EQA) requires an agent to interpret language, perceive its environment, and navigate within 3D scenes to produce responses. Existing EQA benchmarks ass…
TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
Rui Qian, Haozhi Cao, Tianchen Deng +4
Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initial…
Gaussian Semantic Field for One-shot LiDAR Global Localization
Pengyu Yin, Shenghai Yuan, Haozhi Cao +4
We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registra…
SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion
Rui Qian, Haozhi Cao, Tianchen Deng +2
Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While…
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information
Kuan Xu, Zeyu Jiang, Haozhi Cao +3
Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation.…
UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration
Geng Li, Haozhi Cao, Mingyang Liu +2
Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance w…
Enhancing Dataset Distillation via Label Inconsistency Elimination and Learning Pattern Refinement
Chuhao Zhou, Chenxi Jiang, Yi Xie +2
Dataset Distillation (DD) seeks to create a condensed dataset that, when used to train a model, enables the model to achieve performance similar to that of a model trained on the e…
SGBA: Semantic Gaussian Mixture Model-Based LiDAR Bundle Adjustment
Xingyu Ji, Shenghai Yuan, Jianping Li +3
LiDAR bundle adjustment (BA) is an effective approach to reduce the drifts in pose estimation from the front-end. Existing works on LiDAR BA usually rely on predefined geometric fe…
GERA: Geometric Embedding for Efficient Point Registration Analysis
Geng Li, Haozhi Cao, Mingyang Liu +2
Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgi…
AIR-Embodied: An Efficient Active 3DGS-based Interaction and Reconstruction Framework with Embodied Large Language Model
Zhenghao Qi, Shenghai Yuan, Fen Liu +4
Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying…
MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception
Thien-Minh Nguyen, Shenghai Yuan, Thien Hoang Nguyen +8
Perception plays a crucial role in various robot applications. However, existing well-annotated datasets are biased towards autonomous driving scenarios, while unlabelled SLAM data…
Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation
Haozhi Cao, Yuecong Xu, Pengyu Yin +4
Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA…
MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation
Haozhi Cao, Yuecong Xu, Jianfei Yang +3
Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a practical solution to embed semantic understanding in autonomous systems without expensive poi…
Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning
Pengyu Yin, Haozhi Cao, Thien-Minh Nguyen +4
One-shot LiDAR localization refers to the ability to estimate the robot pose from one single point cloud, which yields significant advantages in initialization and relocalization p…
Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation
Haozhi Cao, Yuecong Xu, Jianfei Yang +3
Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this pa…
Segregator: Global Point Cloud Registration with Semantic and Geometric Cues
Pengyu Yin, Shenghai Yuan, Haozhi Cao +3
This paper presents Segregator, a global point cloud registration framework that exploits both semantic information and geometric distribution to efficiently build up outlier-robus…
Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
Yuecong Xu, Haozhi Cao, Zhenghua Chen +3
Video analysis tasks such as action recognition have received increasing research interest with growing applications in fields such as smart healthcare, thanks to the introduction…
Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation
Yuecong Xu, Jianfei Yang, Haozhi Cao +4
To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to impr…
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
Yuecong Xu, Jianfei Yang, Haozhi Cao +3
Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environme…
Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study
Yuecong Xu, Jianfei Yang, Haozhi Cao +5
While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to cha…
Self-Supervised Video Representation Learning by Video Incoherence Detection
Haozhi Cao, Yuecong Xu, Jianfei Yang +4
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of hu…
Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
Yuecong Xu, Jianfei Yang, Haozhi Cao +4
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios. It relaxes the assumption in conventional Unsupervised Domain Adaptati…
Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network
Yuecong Xu, Jianfei Yang, Haozhi Cao +3
Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsum…