122 citations · 289 across the 21 of their papers we have counts for
21 papers
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
Ke Wu, Yanan Zhang, Yingjie Gao +5
Object detection for Unmanned Aerial Vehicles (UAVs) working in open and dynamic environments is a highly challenging task. While Vision-Language Models (VLMs) have offered a power…
TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding
Jingbin You, Zehao Li, Hao Jiang +8
3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hi…
Towards Unbiased Source-Free Object Detection via Vision Foundation Models
Zhi Cai, Yingjie Gao, Yanan Zhang +2
Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffe…
Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition
Baoli Sun, Yihan Wang, Xinzhu Ma +3
Fine-grained action recognition (FGAR) aims to identify subtle and distinctive differences among fine-grained action categories. However, current recognition methods often capture…
Referring Video Object Segmentation with Cross-Modality Proxy Queries
Baoli Sun, Xinzhu Ma, Ning Wang +2
Referring video object segmentation (RVOS) is an emerging cross-modality task that aims to generate pixel-level maps of the target objects referred by given textual expressions. Th…
Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion
Shenglun Chen, Xinzhu Ma, Hong Zhang +2
Depth completion is a pivotal challenge in computer vision, aiming at reconstructing the dense depth map from a sparse one, typically with a paired RGB image. Existing learning bas…
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
Yuchen Ren, Zhiyuan Chen, Lifeng Qiao +10
RNA plays a pivotal role in translating genetic instructions into functional outcomes, underscoring its importance in biological processes and disease mechanisms. Despite the emerg…
Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completion
Chen Shenglun, Zhang Hong, Ma XinZhu +2
Depth completion is a long-standing challenge in computer vision, where classification-based methods have made tremendous progress in recent years. However, most existing classific…
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection
Xinzhu Ma, Yongtao Wang, Yinmin Zhang +5
In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object dete…
GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
Yan Lu, Xinzhu Ma, Lei Yang +6
Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2…
Toward Understanding BERT-Like Pre-Training for DNA Foundation Models
Chaoqi Liang, Lifeng Qiao, Peng Ye +9
With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods base…
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection
Xinzhu Ma, Yuan Meng, Yinmin Zhang +4
Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main…
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation
Zengyu Qiu, Xinzhu Ma, Kunlin Yang +4
Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the…
3D Object Detection from Images for Autonomous Driving: A Survey
Xinzhu Ma, Wanli Ouyang, Andrea Simonelli +1
3D object detection from images, one of the fundamental and challenging problems in autonomous driving, has received increasing attention from both industry and academia in recent…
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Zhiyu Chong, Xinzhu Ma, Hong Zhang +4
3D object detection is a fundamental and challenging task for 3D scene understanding, and the monocular-based methods can serve as an economical alternative to the stereo-based or…
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Yan Lu, Xinzhu Ma, Lei Yang +5
Geometry Projection is a powerful depth estimation method in monocular 3D object detection. It estimates depth dependent on heights, which introduces mathematical priors into the d…
Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
Yinmin Zhang, Xinzhu Ma, Shuai Yi +4
As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to th…
Delving into Localization Errors for Monocular 3D Object Detection
Xinzhu Ma, Yinmin Zhang, Dan Xu +4
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. I…
Rethinking Pseudo-LiDAR Representation
Xinzhu Ma, Shinan Liu, Zhiyi Xia +3
The recently proposed pseudo-LiDAR based 3D detectors greatly improve the benchmark of monocular/stereo 3D detection task. However, the underlying mechanism remains obscure to the…
Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Xinzhu Ma, Zhihui Wang, Haojie Li +3
In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted fr…
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Yuanzheng Ci, Xinzhu Ma, Zhihui Wang +2
Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack…