45 citations · 163 across the 21 of their papers we have counts for
21 papers
UniDet: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
Yubin Wang, Zhikang Zou, Xiaoqing Ye +3
We present UniDet, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization…
Exploring the Causality of End-to-End Autonomous Driving
Jiankun Li, Hao Li, Jiangjiang Liu +6
Deep learning-based models are widely deployed in autonomous driving areas, especially the increasingly noticed end-to-end solutions. However, the black-box property of these model…
PointMamba: A Simple State Space Model for Point Cloud Analysis
Dingkang Liang, Xin Zhou, Wei Xu +5
Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has qu…
Diffusion-based 3D Object Detection with Random Boxes
Xin Zhou, Jinghua Hou, Tingting Yao +6
3D object detection is an essential task for achieving autonomous driving. Existing anchor-based detection methods rely on empirical heuristics setting of anchors, which makes the…
CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching
Jincheng Lu, Xipeng Yang, Jin Ye +4
Multi-Camera Multi-Target Tracking (MCMT) is a computer vision technique that involves tracking multiple targets simultaneously across multiple cameras. MCMT in urban traffic visua…
Understanding Depth Map Progressively: Adaptive Distance Interval Separation for Monocular 3d Object Detection
Xianhui Cheng, Shoumeng Qiu, Zhikang Zou +2
Monocular 3D object detection aims to locate objects in different scenes with just a single image. Due to the absence of depth information, several monocular 3D detection technique…
SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
Dingyuan Zhang, Dingkang Liang, Hongcheng Yang +4
With the development of large language models, many remarkable linguistic systems like ChatGPT have thrived and achieved astonishing success on many tasks, showing the incredible p…
Multi-Modal 3D Object Detection by Box Matching
Zhe Liu, Xiaoqing Ye, Zhikang Zou +5
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detect…
SOOD: Towards Semi-Supervised Oriented Object Detection
Wei Hua, Dingkang Liang, Jingyu Li +4
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approache…
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
Dingkang Liang, Jiahao Xie, Zhikang Zou +3
Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsup…
Repainting and Imitating Learning for Lane Detection
Yue He, Minyue Jiang, Xiaoqing Ye +5
Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows, severe road mark degradation, and serious vehicle occlusion. As a result, di…
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network
Bo Ju, Zhikang Zou, Xiaoqing Ye +4
3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with r…
The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection
Zhikang Zou, Xiaoqing Ye, Liang Du +6
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory. In this paper, we dig into the 3D object…
SGM3D: Stereo Guided Monocular 3D Object Detection
Zheyuan Zhou, Liang Du, Xiaoqing Ye +5
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a grea…
Self-Adaptive Partial Domain Adaptation
Jian Hu, Hongya Tuo, Shizhao Zhang +6
Partial Domain adaptation (PDA) aims to solve a more practical cross-domain learning problem that assumes target label space is a subset of source label space. However, the mismatc…
Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network
Zhikang Zou, Xiaoye Qu, Pan Zhou +4
Recent deep networks have convincingly demonstrated high capability in crowd counting, which is a critical task attracting widespread attention due to its various industrial applic…
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Wenhao Wu, Yuxiang Zhao, Yanwu Xu +8
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal mode…
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting
Qiming Wu, Zhikang Zou, Pan Zhou +3
Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced esti…
Crowd Counting via Hierarchical Scale Recalibration Network
Zhikang Zou, Yifan Liu, Shuangjie Xu +3
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenati…
Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
Zhikang Zou, Yu Cheng, Xiaoye Qu +3
Crowd counting is a challenging task due to the large variations in crowd distributions. Previous methods tend to tackle the whole image with a single fixed structure, which is una…
Enhanced 3D convolutional networks for crowd counting
Zhikang Zou, Huiliang Shao, Xiaoye Qu +2
Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting. However, when dealing with video datasets, CNN-based methods still process each vi…