Related papers: GTNet:Guided Transformer Network for Detecting Hum…
Human-object interaction (HOI) detection is a core task in computer vision. The goal is to localize all human-object pairs and recognize their interactions. An interaction defined by a <verb, noun> tuple leads to a long-tailed visual…
Spatial contexts, such as the backgrounds and surroundings, are considered critical in Human-Object Interaction (HOI) recognition, especially when the instance-centric foreground is blurred or occluded. Recent advancements in HOI detectors…
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks. However, most works pursue designing better architectures to…
Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines. While detecting non-temporal HOIs (e.g., sitting on a chair) from static images is feasible, it is unlikely even for…
Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification. Such disentangled transformers,…
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…
Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Recently, Contrastive Language-Image Pre-training (CLIP) has shown great potential in providing interaction prior for HOI…
Object goal navigation aims to steer an agent towards a target object based on observations of the agent. It is of pivotal importance to design effective visual representations of the observed scene in determining navigation actions. In…
The task of Human-Object Interaction~(HOI) detection could be divided into two core problems, i.e., human-object association and interaction understanding. In this paper, we reveal and address the disadvantages of the conventional…
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…
Human-Object Interaction (HOI) detection plays a core role in activity understanding. Though recent two/one-stage methods have achieved impressive results, as an essential step, discovering interactive human-object pairs remains…
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…
We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based methods face the following three major drawbacks; they cannot…
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…
Rapid progress has been witnessed for human-object interaction (HOI) recognition, but most existing models are confined to single-stage reasoning pipelines. Considering the intrinsic complexity of the task, we introduce a cascade…
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…
A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to…
Understanding human intentions during interactions has been a long-lasting theme, that has applications in human-robot interaction, virtual reality and surveillance. In this study, we focus on full-body human interactions with large-sized…
In the field of human-object interaction (HOI), detection and generation are two dual tasks that have traditionally been addressed separately, hindering the development of comprehensive interaction understanding. To address this, we propose…
We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate modality. In…