中文
相关论文

相关论文: Rb-PaStaNet: A Few-Shot Human-Object Interaction D…

200 篇论文

Human-Object Interaction Detection (HOI-DET) aims to localize human-object pairs and identify their interactive relationships. To aggregate contextual cues, existing methods typically propagate information across all detected entities via…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Jiajun Hong , Jianan Wei , Wenguan Wang

The task of Human-Object Interaction (HOI) detection targets fine-grained visual parsing of humans interacting with their environment, enabling a broad range of applications. Prior work has demonstrated the benefits of effective…

计算机视觉与模式识别 · 计算机科学 2022-11-17 Hangjie Yuan , Jianwen Jiang , Samuel Albanie , Tao Feng , Ziyuan Huang , Dong Ni , Mingqian Tang

Interestingness recognition is crucial for decision making in autonomous exploration for mobile robots. Previous methods proposed an unsupervised online learning approach that can adapt to environments and detect interesting scenes quickly,…

机器人学 · 计算机科学 2022-08-03 Seungchan Kim , Chen Wang , Bowen Li , Sebastian Scherer

Learning to detect novel objects from few annotated examples is of great practical importance. A particularly challenging yet common regime occurs when there are extremely limited examples (less than three). One critical factor in improving…

计算机视觉与模式识别 · 计算机科学 2021-05-05 Weilin Zhang , Yu-Xiong Wang

Human-object interaction detection is a relatively new task in the world of computer vision and visual semantic information extraction. With the goal of machines identifying interactions that humans perform on objects, there are many…

计算机视觉与模式识别 · 计算机科学 2020-09-29 Trevor Bergstrom , Humphrey Shi

Reasoning the human-object interactions (HOI) is essential for deeper scene understanding, while object affordances (or functionalities) are of great importance for human to discover unseen HOIs with novel objects. Inspired by this, we…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Zhi Hou , Baosheng Yu , Yu Qiao , Xiaojiang Peng , Dacheng Tao

We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions. Differently…

计算机视觉与模式识别 · 计算机科学 2022-05-27 A S M Iftekhar , Hao Chen , Kaustav Kundu , Xinyu Li , Joseph Tighe , Davide Modolo

In human-object interactions (HOI) recognition, conventional methods consider the human body as a whole and pay a uniform attention to the entire body region. They ignore the fact that normally, human interacts with an object by using some…

计算机视觉与模式识别 · 计算机科学 2018-07-31 Hao-Shu Fang , Jinkun Cao , Yu-Wing Tai , Cewu Lu

In scene understanding, robotics benefit from not only detecting individual scene instances but also from learning their possible interactions. Human-Object Interaction (HOI) Detection infers the action predicate on a <human, predicate,…

机器学习 · 计算机科学 2021-03-09 Zhijun Liang , Juan Rojas , Junfa Liu , Yisheng Guan

We present an approach for detecting human-object interactions (HOIs) in images, based on the idea that humans interact with functionally similar objects in a similar manner. The proposed model is simple and efficiently uses the data,…

计算机视觉与模式识别 · 计算机科学 2020-09-03 Ankan Bansal , Sai Saketh Rambhatla , Abhinav Shrivastava , Rama Chellappa

Human Object Interaction (HOI) detection is a challenging task that requires to distinguish the interaction between a human-object pair. Attention based relation parsing is a popular and effective strategy utilized in HOI. However, current…

计算机视觉与模式识别 · 计算机科学 2022-07-19 Jingjia Huang , Baixiang Yang

Human-Object Interaction (HOI) detection plays a crucial role in activity understanding. Though significant progress has been made, interactiveness learning remains a challenging problem in HOI detection: existing methods usually generate…

计算机视觉与模式识别 · 计算机科学 2022-10-05 Xiaoqian Wu , Yong-Lu Li , Xinpeng Liu , Junyi Zhang , Yuzhe Wu , Cewu Lu

Detecting human interactions is crucial for human behavior analysis. Many methods have been proposed to deal with Human-to-Object Interaction (HOI) detection, i.e., detecting in an image which person and object interact together and…

计算机视觉与模式识别 · 计算机科学 2022-01-27 Astrid Orcesi , Romaric Audigier , Fritz Poka Toukam , Bertrand Luvison

Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Minh Anh Nguyen , Quang Huy Tran , Bao Ngoc Le , SuiYang Guang , Tuan Kiet Pham , Linh Chi Vo

Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully understand a visual scene. Towards a deeper visual understanding,…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Bumsoo Kim , Taeho Choi , Jaewoo Kang , Hyunwoo J. Kim

Human-Object Interaction (HOI) detection is the task of identifying a set of <human, object, interaction> triplets from an image. Recent work proposed transformer encoder-decoder architectures that successfully eliminated the need for many…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Bumsoo Kim , Jonghwan Mun , Kyoung-Woon On , Minchul Shin , Junhyun Lee , Eun-Sol Kim

Human-Object Interaction (HOI) detection aims to localize human-object pairs and comprehend their interactions. Recently, two-stage transformer-based methods have demonstrated competitive performance. However, these methods frequently focus…

计算机视觉与模式识别 · 计算机科学 2024-05-27 Jihao Dong , Renjie Pan , Hua Yang

Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches…

Zero-shot human-object interaction (HOI) detection remains a challenging task, particularly in generalizing to unseen actions. Existing methods address this challenge by tapping Vision-Language Models (VLMs) to access knowledge beyond the…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Qinqian Lei , Bo Wang , Robby T. Tan

Human-Object Interaction (HOI) consists of human, object and implicit interaction/verb. Different from previous methods that directly map pixels to HOI semantics, we propose a novel perspective for HOI learning in an analytical manner. In…

计算机视觉与模式识别 · 计算机科学 2020-11-10 Yong-Lu Li , Xinpeng Liu , Xiaoqian Wu , Yizhuo Li , Cewu Lu