Recently, the DETR framework has emerged as the dominant approach for human--object
interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are …

Abstract Human-Object Interaction (HOI) detection is a challenging computer vision task that
requires visual models to address the complex interactive relationship between humans and …

Human-object interaction (HOI) detection aims to comprehend the intricate relationships
between humans and objects, predicting triplets, and serving as the foundation for …

Abstract Human-Object Interaction (HOI) detection, which localizes and infers relationships
between human and objects, plays an important role in scene understanding. Although two …

We propose an agglomerative Transformer (AGER) that enables Transformer-based human-
object interaction (HOI) detectors to flexibly exploit extra instance-level cues in a single …

Abstract Human Object Interaction (HOI) detection aims to localize and infer the
relationships between a human and an object. Arguably, training supervised models for this …

Traditional video action detectors typically adopt the two-stage pipeline, where a person
detector is first employed to yield actor boxes and then 3D RoIAlign is used to extract actor …

Unlike most previous HOI methods that focus on learning better human-object features, we
propose a novel and complementary approach called category query learning. Such queries …

Learning based 6D object pose estimation methods rely on computing large intermediate
pose representations and/or iteratively refining an initial estimation with a slow render …

The interaction decoder utilized in prevalent Transformer-based HOI detectors typically
accepts pre-composed human-object pairs as inputs. Though achieving remarkable …