Deep learning techniques have led to remarkable breakthroughs in the field of object
detection and have spawned a lot of scene-understanding tasks in recent years. Scene …

Towards building comprehensive real-world visual perception systems, we propose and
study a new problem called panoptic scene graph generation (PVSG). PVSG is related to …

Effectively tackling the problem of temporal action localization (TAL) necessitates a visual
representation that jointly pursues two confounding goals, ie, fine-grained discrimination for …

Video-based visual relation detection tasks such as video scene graph generation play
important roles in fine-grained video understanding. However current video visual relation …

Abstract We propose Continuous Scene Representations (CSR), a scene representation
constructed by an embodied agent navigating within a space, where objects and their …

This paper deals with a challenging task of video scene graph generation (VidSGG), which
could serve as a structured video representation for high-level understanding tasks. We …

Video Visual Relation Detection (VidVRD) aims to semantically describe the dynamic
interactions across visual concepts localized in a video in the form of subject, predicate …

We propose a novel few-shot learning framework that can recognize human–object
interaction (HOI) classes with a few labeled samples. We achieve this by leveraging a meta …

Current multi-object tracking (MOT) aims to predict trajectories of targets (ie,“where”) in
videos. Yet, knowing merely “where” is insufficient in many crucial applications. In …

Training effective embodied AI agents often involves expert imitation, specialized
components such as maps, or leveraging additional sensors for depth and localization …