80 citations · 186 across the 25 of their papers we have counts for
25 papers
Instance-free Text to Point Cloud Localization with Relative Position Awareness
Lichao Wang, Zhihao Yuan, Jinke Ren +2
Text-to-point-cloud cross-modal localization is an emerging vision-language task critical for future robot-human collaboration. It seeks to localize a position from a city-scale po…
Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding
Zhihao Yuan, Jinke Ren, Chun-Mei Feng +3
3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predef…
LATR: 3D Lane Detection from Monocular Images with Transformer
Yueru Luo, Chaoda Zheng, Xu Yan +4
3D lane detection from monocular images is a fundamental yet challenging task in autonomous driving. Recent advances primarily rely on structural 3D surrogates (e.g., bird's eye vi…
WeakPolyp: You Only Look Bounding Box for Polyp Segmentation
Jun Wei, Yiwen Hu, Shuguang Cui +2
Limited by expensive pixel-level labels, polyp segmentation models are plagued by data shortage and suffer from impaired generalization. In contrast, polyp bounding box annotations…
An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
Chaoda Zheng, Xu Yan, Haiming Zhang +4
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance match…
Benchmarking the Robustness of LiDAR Semantic Segmentation Models
Xu Yan, Chaoda Zheng, Ying Xue +3
When using LiDAR semantic segmentation models for safety-critical applications such as autonomous driving, it is essential to understand and improve their robustness with respect t…
Geometry-Aware Network for Domain Adaptive Semantic Segmentation
Yinghong Liao, Wending Zhou, Xu Yan +3
Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) data is the core issue for domain adaptive semantic segmentation. Though recent w…
Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis
Xu Yan, Heshen Zhan, Chaoda Zheng +4
Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we t…
M-3DLaneNet: Exploring Multi-Modal 3D Lane Detection
Yueru Luo, Xu Yan, Chaoda Zheng +5
Estimating accurate lane lines in 3D space remains challenging due to their sparse and slim nature. Previous works mainly focused on using images for 3D lane detection, leading to…
Composable Text Controls in Latent Space with ODEs
Guangyi Liu, Zeyu Feng, Yuan Gao +7
Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and…
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
Xu Yan, Jiantao Gao, Chaoda Zheng +4
As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-mod…
Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases
Zhihao Yuan, Xu Yan, Zhuo Li +4
Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description. However, existing methods only consider t…
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
Zhihao Yuan, Xu Yan, Yinghong Liao +4
3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only expl…
Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
Chaoda Zheng, Xu Yan, Haiming Zhang +4
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching…
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation
Xu Yan, Zhihao Yuan, Yuhao Du +4
Visual Question Answering on 3D Point Cloud (VQA-3D) is an emerging yet challenging field that aims at answering various types of textual questions given an entire point cloud scen…
Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Guangyi Liu, Yinghong Liao, Fuyu Wang +8
Medical imaging technologies, including computed tomography (CT) or chest X-Ray (CXR), are largely employed to facilitate the diagnosis of the COVID-19. Since manual report writing…
Adaptive Residue-wise Profile Fusion for Low Homologous Protein SecondaryStructure Prediction Using External Knowledge
Qin Wang, Jun Wei, Boyuan Wang +3
Protein secondary structure prediction (PSSP) is essential for protein function analysis. However, for low homologous proteins, the PSSP suffers from insufficient input features. I…
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment
Qin Wang, Hui Che, Weizhen Ding +4
Differentiation of colorectal polyps is an important clinical examination. A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images. Most…
Shallow Attention Network for Polyp Segmentation
Jun Wei, Yiwen Hu, Ruimao Zhang +3
Accurate polyp segmentation is of great importance for colorectal cancer diagnosis. However, even with a powerful deep neural network, there still exists three big challenges that…
Shallow Feature Matters for Weakly Supervised Object Localization
Jun Wei, Qin Wang, Zhen Li +3
Weakly supervised object localization (WSOL) aims to localize objects by only utilizing image-level labels. Class activation maps (CAMs) are the commonly used features to achieve W…
Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds
Chaoda Zheng, Xu Yan, Jiantao Gao +4
Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area. However, due to the common occlusion in…
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Guangyi Liu, Zichao Yang, Tianhua Tao +6
Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss, which encourages an exact token-by-token match between a…
PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery
Weibing Zhao, Xu Yan, Jiantao Gao +5
Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing since raw data usually requires large storage and computation. In t…
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
Zhihao Yuan, Xu Yan, Yinghong Liao +4
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, name…