paper-with-me

Papers

Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition

2021-10-28 · Liang Xu, Cuiling Lan, Wenjun Zeng, Cewu Lu

Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the action of persons. In this paper, we propose a joint learning framework for mutually assisted "interacted object localization" and "human action recognition" based on skeleton data. The two tasks are serialized together and collaborate to promote each other, where preliminary action type derived from skeleton alone helps improve interacted object localization, which in turn provides valuable cues for the final human action recognition. Besides, we explore the temporal consistency of interacted object as constraint to better localize the interacted object with the absence of ground-truth labels. Extensive experiments on the datasets of SYSU-3D, NTU60 RGB+D, Northwestern-UCLA and UAV-Human show that our method achieves the best or competitive performance with the state-of-the-art methods for human action recognition. Visualization results show that our method can also provide reasonable interacted object localization results.

📄 PDF Abstract BibTeX arXiv:2110.14994

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionObjectObject LocalizationTemporal Action Localization

Similar Papers 제목 키워드 기반

Reasoning About Human-Object Interactions Through Dual Attention Networks

2019-09-10 · ICCV 2019 10 · Tete Xiao, Quanfu Fan, Dan Gutfreund, Mathew Monfort 외

Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reasons about human-object interactions. The d…

Human-Object Interaction DetectionObject

SALC: Skeleton-Assisted Learning-Based Clustering for Time-Varying Indoor Localization

2023-07-14 · An-Hung Hsiao, Li-Hsiang Shen, Chen-Yi Chang, Chun-Jie Chiu 외

Wireless indoor localization has attracted significant amount of attention in recent years. Using received signal strength (RSS) obtained from WiFi access points (APs) for establishing fingerprinting database is a widely…

ClusteringIndoor Localization

LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints

2022-03-31 · CVPR 2022 1 · Junshu Tang, Zhijun Gong, Ran Yi, Yuan Xie 외

Point cloud completion aims at completing geometric and topological shapes from a partial observation. However, some topology of the original shape is missing, existing methods directly predict the location of complete p…

Point Cloud Completion

Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation

2019-03-15 · Wei Feng, Wentao Liu, Tong Li, Jing Peng 외

Human-object interactions (HOI) recognition and pose estimation are two closely related tasks. Human pose is an essential cue for recognizing actions and localizing the interacted objects. Meanwhile, human action and the…

Human-Object Interaction DetectionPose Estimation

DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images

2016-09-13 · Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang 외

Object skeletons are useful for object representation and object detection. They are complementary to the object contour, and provide extra information, such as how object scale (thickness) varies among object parts. But…

Multi-Task LearningObjectobject-detectionObject Detection+1