中文
相关论文

相关论文: Human-Object Interaction Prediction in Videos thro…

200 篇论文

Human-object interaction (HOI) detection often faces high levels of ambiguity and indeterminacy, as the same interaction can appear vastly different across different human-object pairs. Additionally, the indeterminacy can be further…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Xiaofei Hui , Haoxuan Qu , Hossein Rahmani , Jun Liu

Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding. We propose PhraseHOI, containing a HOI branch and a novel phrase branch, to leverage language prior and improve relation…

计算机视觉与模式识别 · 计算机科学 2022-01-19 Zhimin Li , Cheng Zou , Yu Zhao , Boxun Li , Sheng Zhong

Humans naturally interact with both others and the surrounding multiple objects, engaging in various social activities. However, recent advances in modeling human-object interactions mostly focus on perceiving isolated individuals and…

计算机视觉与模式识别 · 计算机科学 2024-04-03 Juze Zhang , Jingyan Zhang , Zining Song , Zhanhe Shi , Chengfeng Zhao , Ye Shi , Jingyi Yu , Lan Xu , Jingya Wang

Human-Object Interaction (HOI) detection aims to simultaneously localize human-object pairs and recognize their interactions. While recent two-stage approaches have made significant progress, they still face challenges due to incomplete…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Zhehao Li , Yucheng Qian , Chong Wang , Yinghao Lu , Zhihao Yang , Jiafei Wu

3D human-object interaction (HOI) anticipation aims to predict the future motion of humans and their manipulated objects, conditioned on the historical context. Generally, the articulated humans and rigid objects exhibit different motion…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Xiaotong Lin , Tianming Liang , Jian-Fang Hu , Kun-Yu Lin , Yulei Kang , Chunwei Tian , Jianhuang Lai , Wei-Shi Zheng

Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by…

计算机视觉与模式识别 · 计算机科学 2023-09-19 Yichao Cao , Qingfei Tang , Feng Yang , Xiu Su , Shan You , Xiaobo Lu , Chang Xu

The interaction decoder utilized in prevalent Transformer-based HOI detectors typically accepts pre-composed human-object pairs as inputs. Though achieving remarkable performance, such paradigm lacks feasibility and cannot explore novel…

计算机视觉与模式识别 · 计算机科学 2023-11-17 Liulei Li , Jianan Wei , Wenguan Wang , Yi Yang

In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video. Objects can be indistinctly located inside or outside the…

计算机视觉与模式识别 · 计算机科学 2019-03-01 Benoit Massé , Stéphane Lathuilière , Pablo Mesejo , Radu Horaud

Most existing attention prediction research focuses on salient instances like humans and objects. However, the more complex interaction-oriented attention, arising from the comprehension of interactions between instances by human observers,…

计算机视觉与模式识别 · 计算机科学 2024-05-17 Yuchen Zhou , Linkai Liu , Chao Gou

This paper explores a cross-modality synthesis task that infers 3D human-object interactions (HOIs) from a given text-based instruction. Existing text-to-HOI synthesis methods mainly deploy a direct mapping from texts to object-specific 3D…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Xuehao Gao , Yang Yang , Shaoyi Du , Yang Wu , Yebin Liu , Guo-Jun Qi

Human-Object Interaction (HOI) aims to identify the pairs of humans and objects in images and to recognize their relationships, ultimately forming $\langle human, object, verb \rangle$ triplets. Under default settings, HOI performance is…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Chaoyi Ai

Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them. Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Zhaolin Cai , Huiyu Duan , Zitong Xu , Fan Li , Zhi Liu , Jing Liu , Wei Shen , Xiongkuo Min , Guangtao Zhai

Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, and animation. However, creating high-quality 3D HOIs remains…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Yixuan Zhang , Hui Yang , Chuanchen Luo , Junran Peng , Yuxi Wang , Zhaoxiang Zhang

Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Liulei Li , Wenguan Wang , Yi Yang

Human Object Interaction (HOI) detection aims to localize and infer the relationships between a human and an object. Arguably, training supervised models for this task from scratch presents challenges due to the performance drop over rare…

计算机视觉与模式识别 · 计算机科学 2023-09-08 Ting Lei , Fabian Caba , Qingchao Chen , Hailin Jin , Yuxin Peng , Yang Liu

Rendering realistic human-object interactions (HOIs) from sparse-view inputs is a challenging yet crucial task for various real-world applications. Existing methods often struggle to simultaneously achieve high rendering quality, physical…

图形学 · 计算机科学 2026-04-10 Weiquan Wang , Jun Xiao , Yi Yang , Yueting Zhuang , Long Chen

Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of…

计算机视觉与模式识别 · 计算机科学 2022-06-14 Yong Zhang , Yingwei Pan , Ting Yao , Rui Huang , Tao Mei , Chang-Wen Chen

Human-object interaction(HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene. Since there is an subordination between human and object---human play subjective…

计算机视觉与模式识别 · 计算机科学 2020-10-21 Hai Wang , Wei-Shi Zheng , Ling Yingbiao

We study the problem of detecting human-object interactions (HOI) in static images, defined as predicting a human and an object bounding box with an interaction class label that connects them. HOI detection is a fundamental problem in…

计算机视觉与模式识别 · 计算机科学 2018-03-02 Yu-Wei Chao , Yunfan Liu , Xieyang Liu , Huayi Zeng , Jia Deng

We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions. Our dataset consists of several common articulated objects captured from diverse…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Xiang Xu , Hanbyul Joo , Greg Mori , Manolis Savva