An official website of the United States government
In this paper, we aim at synthesizing a free-viewpoint video of an arbitrary human performance using sparse multi-view cameras. Recently, several works have addressed this problem by learning person-specific neural radiance fields (NeRF) to capture the appearance of a particular human. In parallel, some work proposed to use pixel-aligned features to generalize radiance fields to arbitrary new scenes and objects. Adopting such generalization approaches to humans, however, is highly challenging due to the heavy occlusions and dynamic articulations of body parts. To tackle this, we propose Neural Human Performer, a novel approach that learns generalizable neural radiance fields based on a parametric human body model for robust performance capture. Specifically, we first introduce a temporal transformer that aggregates tracked visual features based on the skeletal body motion over time. Moreover, a multi-view transformer is proposed to perform cross-attention between the temporally-fused features and the pixel-aligned features at each time step to integrate observations on the fly from multiple views. Experiments on the ZJU-MoCap and AIST datasets show that our method significantly outperforms recent generalizable NeRF methods on unseen identities and poses. The video results and code are available at https://youngjoongunc.github.io/nhp.
more »
« less
Dynamic Motion Representation for Human Action Recognition
Despite the advances in Human Activity Recognition, the ability to exploit the dynamics of human body motion in videos has yet to be achieved. In numerous recent works, re- searchers have used appearance and motion as independent inputs to infer the action that is taking place in a specific video. In this paper, we highlight that while using a novel representation of human body motion, we can benefit from appearance and motion simultaneously. As a result, bet- ter performance of action recognition can be achieved. We start with a pose estimator to extract the location and heat- map of body joints in each frame. We use a dynamic encoder to generate a fixed size representation from these body joint heat-maps. Our experimental results show that training a convolutional neural network with the dynamic motion representation outperforms state-of-the-art action recognition models. By modeling distinguishable activities as distinct dynamical systems and with the help of two stream net- works, we obtain the best performance on HMDB, JHMDB, UCF-101, and AVA datasets.
more »
« less
- PAR ID:
- 10186508
- Date Published:
- Journal Name:
- 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Page Range / eLocation ID:
- 546 to 555
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Spatiotemporal graph convolutional networks (STGCNs) have emerged as a desirable model for skeleton -based human action recognition. Despite achieving state-of-the-art performance, there is a limited understanding of the representations learned by these models, which hinders their application in critical and real-world settings. While layerwise analysis of CNN models has been studied in the literature, to the best of our knowledge, there exists no study on the layerwise explainability of the embeddings learned on spatiotemporal data using STGCNs. In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN. To do so, we develop a window-based dynamic time warping (DTW) method to compute the distance between data sequences with varying temporal lengths. To validate our findings, we have developed a layer-specific Spatiotemporal Graph Gradient-weighted Class Activation Mapping (L-STG-GradCAM) technique tailored for spatiotemporal data. This approach enables us to visually analyze and interpret each layer within the STGCN network. We characterize the functions learned by each layer of the STGCN using the label smoothness of the representation and visualize them using our L-STG-GradCAM approach. Our proposed method is generic and can yield valuable insights for STGCN architectures in different applications. However, this paper focuses on the human activity recognition task as a representative application. Our experiments show that STGCN models learn representations that capture general human motion in their initial layers while discriminating different actions only in later layers. This justifies experimental observations showing that fine-tuning deeper layers works well for transfer between related tasks. We provide experimental evidence for different human activity datasets and advanced spatiotemporal graph networks to validate that the proposed method is general enough to analyze any STGCN model and can be useful for drawing insight into networks in various scenarios. We also show that noise at the input has a limited effect on label smoothness, which can help justify the robustness of STGCNs to noise.more » « less
-
Human-Robot Collaboration (HRC), which envisions a workspace in which human and robot can dynamically collaborate, has been identified as a key element in smart manufacturing. Human action recognition plays a key role in the realization of HRC as it helps identify current human action and provides the basis for future action prediction and robot planning. Despite recent development of Deep Learning (DL) that has demonstrated great potential in advancing human action recognition, one of the key issues remains as how to effectively leverage the temporal information of human motion to improve the performance of action recognition. Furthermore, large volume of training data is often difficult to obtain due to manufacturing constraints, which poses challenge for the optimization of DL models. This paper presents an integrated method based on optical flow and convolutional neural network (CNN)-based transfer learning to tackle these two issues. First, optical flow images, which encode the temporal information of human motion, are extracted and serve as the input to a two-stream CNN structure for simultaneous parsing of spatial-temporal information of human motion. Then, transfer learning is investigated to transfer the feature extraction capability of a pretrained CNN to manufacturing scenarios. Evaluation using engine block assembly confirmed the effectiveness of the developed method.more » « less
-
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represented by local body parts, such as legs or hands, which are advantageous for skeleton-based action recognition. This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations. To achieve this, a multi-head attention mask module is employed to learn the soft attention mask features from the skeletons, suppressing non-salient local features while accentuating local salient features, thereby bringing similar local features closer in the feature space. Additionally, ample contrastive pairs are generated by expanding contrastive pairs based on salient and non-salient features with global features, which guide the network to learn the semantic representations of the entire skeleton. Therefore, with the attention mask mechanism, SkeAttnCLR learns local features under different data augmentation views. The experiment results demonstrate that the inclusion of local feature similarity significantly enhances skeleton-based action representation. Our proposed SkeAttnCLR outperforms state-of-the-art methods on NTURGB+D, NTU120-RGB+D, and PKU-MMD datasets. The code and settings are available at this repository: https://github.com/GitHubOfHyl97/SkeAttnCLR.more » « less
-
In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition. Its parameters for iterative flow optimization are learned in an end-to-end fashion together with the other CNN model parameters, maximizing the action recognition performance. Furthermore, we newly introduce the concept of learning `flow of flow' representations by stacking multiple representation flow layers. We conducted extensive experimental evaluations, confirming its advantages over previous recognition models using traditional optical flows in both computational speed and performance. The code is publicly available.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/WACV45572.2020.9093500
