93 citations · 415 across the 48 of their papers we have counts for
49 papers
Lifelong Robot Learning with Human Assisted Language Planners
Meenal Parakh, Alisha Fong, Anthony Simeonov +3
Large Language Models (LLMs) have been shown to act like planners that can decompose high-level instructions into a sequence of executable instructions. However, current LLM-based…
Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering
Chi Zhang, Wei Yin, Gang Yu +5
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to dire…
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
Yancheng Cai, Bo Zhang, Baopu Li +4
Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applica…
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Sijin Chen, Hongyuan Zhu, Mingsheng Li +6
3D dense captioning requires a model to translate its understanding of an input 3D scene into several captions associated with different object regions. Existing methods adopt a so…
ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
Bo Zhang, Xinyu Cai, Jiakang Yuan +10
Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the prev…
Experts Weights Averaging: A New General Training Scheme for Vision Transformers
Yongqi Huang, Peng Ye, Xiaoshui Huang +4
Structural re-parameterization is a general training scheme for Convolutional Neural Networks (CNNs), which achieves performance improvement without increasing inference cost. As V…
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
Marcel Torne, Max Balsells, Zihan Wang +4
Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration…
MotionGPT: Human Motion as a Foreign Language
Biao Jiang, Xin Chen, Wen Liu +3
Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains ch…
Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
Zibo Zhao, Wen Liu, Xin Chen +7
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional…
AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
Jiakang Yuan, Bo Zhang, Xiangchao Yan +4
It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that c…
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
Chi Zhang, Yiwen Chen, Yijun Fu +7
The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models. Nevertheless, the limited availability of diverse 3D r…
Spectroscopy of momentum state lattices
Sai Naga Manoj Paladugu, Tao Chen, Fangzhao Alex An +2
We explore a technique for probing energy spectra in synthetic lattices that is analogous to scanning tunneling microscopy. Using one-dimensional synthetic lattices of coupled atom…
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization
Chong Yu, Tao Chen, Zhongxue Gan +1
The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision…
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
Peng Ye, Tong He, Shengji Tang +4
Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual ne…
BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
Tao Chen, Chenhui Wang, Hongming Shan
Medical image segmentation is a challenging task with inherent ambiguity and high uncertainty, attributed to factors such as unclear tumor boundaries and multiple plausible annotat…
Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?
Haoyang Peng, Baopu Li, Bo Zhang +3
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural lan…
What Makes for Effective Few-shot Point Cloud Classification?
Chuangguan Ye, Hongyuan Zhu, Yongbin Liao +3
Due to the emergence of powerful computing resources and large-scale annotated datasets, deep learning has seen wide applications in our daily life. However, most current methods r…
A Closer Look at Few-Shot 3D Point Cloud Classification
Chuangguan Ye, Hongyuan Zhu, Bo Zhang +1
In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization f…
TactoFind: A Tactile Only System for Object Retrieval
Sameer Pai, Tao Chen, Megha Tippur +3
We study the problem of object retrieval in scenarios where visual sensing is absent, object shapes are unknown beforehand and objects can move freely, like grabbing objects out of…
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
Jiakang Yuan, Bo Zhang, Xiangchao Yan +4
Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently. Though preliminary progress has been made, the performance gap between the UDA-b…
Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection
Tao Chen, Ruirui Li, Jiafeng Fu +1
Object detection on VHR remote sensing images plays a vital role in applications such as urban planning, land resource management, and rescue missions. The large-scale variation of…
Research on data integration of overseas discrete archives from the perspective of digital humanties
Rina Su, 2. Yumeng Li, Xin Yang +2
The digitization of displaced archives is of great historical and cultural significance. Through the construction of digital humanistic platforms represented by MISS platform, and…
ConceptFusion: Open-set Multimodal 3D Mapping
Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu +14
Building 3D maps of the environment is central to robot navigation, planning, and interaction with objects in a scene. Most existing approaches that integrate semantic concepts wit…
A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction
Chongshan Lu, Fukun Yin, Xin Chen +3
Neural Radiance Fields (NeRF) has achieved impressive results in single object scene reconstruction and novel view synthesis, which have been demonstrated on many single modality a…