相关论文: A Training Method For VideoPose3D With Ideology of…

Egocentric action recognition is essential for healthcare and assistive technology that relies on egocentric cameras because it allows for the automatic and continuous monitoring of activities of daily living (ADLs) without requiring any…

Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously…

The goal of human action recognition is to temporally or spatially localize the human action of interest in video sequences. Temporal localization (i.e. indicating the start and end frames of the action in a video) is referred to as…

Recently, much progress has been made for self-supervised action recognition. Most existing approaches emphasize the contrastive relations among videos, including appearance and motion consistency. However, two main issues remain for…

We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial…

Accurate 3D human pose estimation remains a critical yet unresolved challenge, requiring both temporal coherence across frames and fine-grained modeling of joint relationships. However, most existing methods rely solely on geometric cues…

We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos. The method learns directly from unsegmented egocentric videos…

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction…

In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning…

This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction. It stems from the observation that human visual system is sensitive to video pace, e.g., slow motion, a…

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by…

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective…

Action recognition is essential for egocentric video understanding, allowing automatic and continuous monitoring of Activities of Daily Living (ADLs) without user effort. Existing literature focuses on 3D hand pose input, which requires…

Video predictive understanding encompasses a wide range of efforts that are concerned with the anticipation of the unobserved future from the current as well as historical video observations. Action prediction is a major sub-area of video…

Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…

We investigate a human-like interpretable model of video understanding. Humans recognise complex activities in video by recognising critical spatio-temporal relations among explicitly recognised objects and parts, for example, an object…

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation,…

In 3D Human Motion Prediction (HMP), conventional methods train HMP models with expensive motion capture data. However, the data collection cost of such motion capture data limits the data diversity, which leads to poor generalizability to…

Online test-time adaptation for 3D human pose estimation is used for video streams that differ from training data. Ground truth 2D poses are used for adaptation, but only estimated 2D poses are available in practice. This paper addresses…

Despite progress in human motion capture, existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. This difficulty arises from reliance on accurate 2D joint estimations,…