English
Related papers

Related papers: Self-Supervised Class-Agnostic Motion Prediction w…

200 papers

Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…

Machine Learning · Computer Science 2021-01-05 Todor Davchev , Michael Burke , Subramanian Ramamoorthy

Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Qingwen Zhang , Yi Yang , Peizheng Li , Olov Andersson , Patric Jensfelt

Recent advancements in deep-learning methods for object detection in point-cloud data have enabled numerous roadside applications, fostering improvements in transportation safety and management. However, the intricate nature of point-cloud…

Computer Vision and Pattern Recognition · Computer Science 2025-01-29 Muhammad Shahbaz , Shaurya Agarwal

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

Machine Learning · Computer Science 2020-06-30 Hankook Lee , Sung Ju Hwang , Jinwoo Shin

Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Chaokang Jiang , Guangming Wang , Jiuming Liu , Hesheng Wang , Zhuang Ma , Zhenqiang Liu , Zhujin Liang , Yi Shan , Dalong Du

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Yaozong Zheng , Qihua Liang , Bineng Zhong , Shuimu Zeng , Yuanliang Xue , Ning Li , Shuxiang Song

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Jiacheng Wei , Guosheng Lin , Kim-Hui Yap , Tzu-Yi Hung , Lihua Xie

The task of action-driven human motion prediction aims to forecast future human motion based on the observed sequence while respecting the given action label. It requires modeling not only the stochasticity within human motion but the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Chunzhi Gu , Chao Zhang , Shigeru Kuriyama

Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Sangyun Shin , Stuart Golodetz , Madhu Vankadari , Kaichen Zhou , Andrew Markham , Niki Trigoni

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Zhonghua Wu , Yicheng Wu , Guosheng Lin , Jianfei Cai , Chen Qian

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Yunchuan Ma , Laiyun Qing , Guorong Li , Yuqing Liu , Yuankai Qi , Qingming Huang

Predicting the future can significantly improve the safety of intelligent vehicles, which is a key component in autonomous driving. 3D point clouds accurately model 3D information of surrounding environment and are crucial for intelligent…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Fan Lu , Guang Chen , Yinlong Liu , Zhijun Li , Sanqing Qu , Tianpei Zou

In the task of Autonomous aerial filming of a moving actor (e.g. a person or a vehicle), it is crucial to have a good heading direction estimation for the actor from the visual input. However, the models obtained in other similar tasks,…

Computer Vision and Pattern Recognition · Computer Science 2019-03-28 Wenshan Wang , Aayush Ahuja , Yanfu Zhang , Rogerio Bonatti , Sebastian Scherer

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Mahyar Najibi , Jingwei Ji , Yin Zhou , Charles R. Qi , Xinchen Yan , Scott Ettinger , Dragomir Anguelov

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Ruijie Xu , Chuyu Zhang , Hui Ren , Xuming He

Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of large-scale driving datasets has hindered the development…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Yang Zhou , Hao Shao , Letian Wang , Steven L. Waslander , Hongsheng Li , Yu Liu

LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate the imbalance between static and dynamic points, deriving…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Youngdong Jang , Gyeongrok Oh , Jong Wook Kim , Hyunju Ryu , Hyung-gun Chi , SeungHyeon Kim , Seungryong Kim , Jonghyun Choi , Sangpil Kim

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…

Machine Learning · Computer Science 2020-11-25 Qun Liu , Matthew Shreve , Raja Bala

To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required, the sizes of which directly affect the rate of successful grasps. To…

Robotics · Computer Science 2021-02-02 Gang Peng , Zhenyu Ren , Hao Wang , Xinde Li
‹ Prev 1 4 5 6 7 8 10 Next ›