We introduce a new benchmark “Humans Interacting with Common Objects ” (HICO) for recognizing human-object interactions (HOI). We demonstrate the key features of HICO: a diverse set of interactions with common ob-ject categories, a list of well-defined, sense-based HOI cat-egories, and an exhaustive labeling of co-occurring inter-actions with an object category in each image. We perform an in-depth analysis of representative current approaches and show that DNNs enjoy a significant edge. In addition, we show that semantic knowledge can significantly improve HOI recognition, especially for uncommon categories. 1
Human-Object Interaction (HOI) recognition in videos is important for analysing human activity. Mos...
Most existing Human-Object Interaction~(HOI) Detection methods rely heavily on full annotations with...
Human-Object Interaction (HOI) detection aims to infer different interactions, which occur between h...
Extreme instance imbalance among categories and combinatorial explosion make the recognition of Huma...
We present an approach for detecting human-object interactions (HOIs) in images, based on the idea t...
Human-object interaction (HOI) detection aims to detect and recognise how people interact with the o...
Human-object interaction (HOI) detection has been a trending topic in computer vision and image unde...
International audienceDetecting human interactions is crucial for human behavior analysis. Many meth...
Human-Object Interactions (HOI) detection, which aims to localize a human and a relevant object whil...
This paper describes the Trento Universal Human Object Interaction dataset, TUHOI, which is dedicate...
This paper describes the Trento Universal Human Object Interaction dataset, TUHOI, which is dedicate...
Recognizing human-object interaction (HOI) is an important research topic in computer vision. With t...
The study of human-object interaction (HOI) aims at modeling the geometric relationship between a hu...
The Human Interaction Image (HII) dataset is a new dataset containing Web images from Commercial Sea...
International audienceHuman object interaction (HOI) detection is an important task in image underst...
Human-Object Interaction (HOI) recognition in videos is important for analysing human activity. Mos...
Most existing Human-Object Interaction~(HOI) Detection methods rely heavily on full annotations with...
Human-Object Interaction (HOI) detection aims to infer different interactions, which occur between h...
Extreme instance imbalance among categories and combinatorial explosion make the recognition of Huma...
We present an approach for detecting human-object interactions (HOIs) in images, based on the idea t...
Human-object interaction (HOI) detection aims to detect and recognise how people interact with the o...
Human-object interaction (HOI) detection has been a trending topic in computer vision and image unde...
International audienceDetecting human interactions is crucial for human behavior analysis. Many meth...
Human-Object Interactions (HOI) detection, which aims to localize a human and a relevant object whil...
This paper describes the Trento Universal Human Object Interaction dataset, TUHOI, which is dedicate...
This paper describes the Trento Universal Human Object Interaction dataset, TUHOI, which is dedicate...
Recognizing human-object interaction (HOI) is an important research topic in computer vision. With t...
The study of human-object interaction (HOI) aims at modeling the geometric relationship between a hu...
The Human Interaction Image (HII) dataset is a new dataset containing Web images from Commercial Sea...
International audienceHuman object interaction (HOI) detection is an important task in image underst...
Human-Object Interaction (HOI) recognition in videos is important for analysing human activity. Mos...
Most existing Human-Object Interaction~(HOI) Detection methods rely heavily on full annotations with...
Human-Object Interaction (HOI) detection aims to infer different interactions, which occur between h...