相关论文: Hierarchical Motion Understanding via Motion Progr…

We introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low-level motion and high-level description as motion concepts. This representation enables human motion description,…

We present a novel framework for the automatic discovery and recognition of motion primitives in videos of human activities. Given the 3D pose of a human in a video, human motion primitives are discovered by optimizing the `motion flux', a…

Biological systems exhibit a continuous stream of movements, consisting of sequential segments, that allow them to perform complex tasks in a creative and versatile fashion. This observation has led researchers towards identifying…

Human-centred systems require an understanding of human actions in the physical world. Temporally extended sequences of actions are intentional and structured, yet existing methods for recognising what actions are performed often do not…

This paper introduces a novel approach to enhance existing motion captioning methods, which directly map representations of movement to high-level descriptive captions (e.g., ``a person doing jumping jacks"). The existing methods require…

We introduce MotionScript, a novel framework for generating highly detailed, natural language descriptions of 3D human motions. Unlike existing motion datasets that rely on broad action labels or generic captions, MotionScript provides…

In this work, we propose a motion embedding strategy known as motion codes, which is a vectorized representation of motions based on a manipulation's salient mechanical attributes. These motion codes provide a robust motion representation,…

Videos are more informative than images because they capture the dynamics of the scene. By representing motion in videos, we can capture dynamic activities. In this work, we introduce GPT-4 generated motion descriptions that capture…

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion…

Physical motions are inherently continuous, and higher camera frame rates typically contribute to improved smoothness and temporal coherence. For the first time, we explore continuous representations of human motion sequences, featuring the…

Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to…

In this paper, we introduce a new hierarchical model for human action recognition using body joint locations. Our model can categorize complex actions in videos, and perform spatio-temporal annotations of the atomic actions that compose the…

Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing…

We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion…

Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we…

Human motion prediction is an essential component for enabling closer human-robot collaboration. The task of accurately predicting human motion is non-trivial. It is compounded by the variability of human motion, both at a skeletal level…

Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms…

Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing…

In this paper, we propose H-MoRe, a novel pipeline for learning precise human-centric motion representation. Our approach dynamically preserves relevant human motion while filtering out background movement. Notably, unlike previous methods…

Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and…