Posted Content•
Pose And Joint-Aware Action Recognition.
TL;DR: A new model for joint-based action recognition is presented, which first extracts motion features from each joint separately through a shared motion encoder before performing collective reasoning, and which outperforms the existing baseline on Mimetics, a dataset with out-of-context actions.
Abstract: Most human action recognition systems typically consider static appearances and motion as independent streams of information. In this paper, we consider the evolution of human pose and propose a method to better capture interdependence among skeleton joints. Our model extracts motion information from each joint independently, reweighs the information and finally performs inter-joint reasoning. The effectiveness of pose and joint-based representations is strengthened using a geometry-aware data augmentation technique which jitters pose heatmaps while retaining the dynamics of the action. Our best model gives an absolute improvement of 8.19% on JHMDB, 4.31% on HMDB and 1.55 mAP on Charades datasets over state-of-the-art methods using pose heat-maps alone. Fusing with RGB and flow streams leads to improvement over state-of-the-art. Our model also outperforms the baseline on Mimetics, a dataset with out-of-context videos by 1.14% while using only pose heatmaps. Further, to filter out clips irrelevant for action recognition, we re-purpose our model for clip selection guided by pose information and show improved performance using fewer clips.
Citations
More filters
Posted Content•
TL;DR: In this paper, the authors propose to represent videos as space-time region graphs which capture temporal shape dynamics and functional relationships between humans and objects, and perform reasoning on this graph representation via Graph Convolutional Networks.
Abstract: How do humans recognize the action "opening a book" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations capturing the interactions between nearby objects. We perform reasoning on this graph representation via Graph Convolutional Networks. We achieve state-of-the-art results on both Charades and Something-Something datasets. Especially for Charades, we obtain a huge 4.4% gain when our model is applied in complex environments.
278 citations
TL;DR: Zhang et al. as mentioned in this paper proposed a Pose-Appearance Relational Network (PARNet), which combines the benefits of appearance and pose to improve the robustness of real-world videos.
Abstract: Recent studies of video action recognition can be classified into two categories: the appearance-based methods and the pose-based methods. The appearance-based methods generally cannot model temporal dynamics of large motion well by virtue of optical flow estimation, while the pose-based methods ignore the visual context information such as typical scenes and objects, which are also important cues for action understanding. In this paper, we tackle these problems by proposing a Pose-Appearance Relational Network (PARNet), which models the correlation between human pose and image appearance, and combines the benefits of these two modalities to improve the robustness towards unconstrained real-world videos. There are three network streams in our model, namely pose stream, appearance stream and relation stream. For the pose stream, a Temporal Multi-Pose RNN module is constructed to obtain the dynamic representations through temporal modeling of 2D poses. For the appearance stream, a Spatial Appearance CNN module is employed to extract the global appearance representation of the video sequence. For the relation stream, a Pose-Aware RNN module is built to connect pose and appearance streams by modeling action-sensitive visual context information. Through jointly optimizing the three modules, PARNet achieves superior performances compared with the state-of-the-arts on both the pose-complete datasets (KTH, Penn-Action, UCF11) and the challenging pose-incomplete datasets (UCF101, HMDB51, JHMDB), demonstrating its robustness towards complex environments and noisy skeletons. Its effectiveness on NTU-RGBD dataset is also validated even compared with 3D skeleton-based methods. Furthermore, an appearance-enhanced PARNet equipped with a RGB-based I3D stream is proposed, which outperforms the Kinetics pre-trained competitors on UCF101 and HMDB51. The better experimental results verify the potentials of our framework by integrating various modules.
2 citations
TL;DR: Goel et al. as discussed by the authors proposed a fully transformable version of HMR 2.0 to deal with multiple people and maintain identities through occlusion events, achieving state-of-the-art results for tracking people from monocular video.
Abstract: We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully"transformerized"version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.
2 citations
DOI•
TL;DR: Zhang et al. as mentioned in this paper proposed a multifeatures and multistream network (MM-Net) for real-time skeleton-based action recognition, which used a 1-D convolutional neural network (1DCNN) to reduce the number of parameters of the model and fully extract the three pairs of features.
Abstract: Action recognition is a hot topic in the field of computer vision. It has been widely used in human–computer/robot interaction, abnormal behavior monitoring, and medical assistive. Because of the excellent robustness of skeleton data, it has attracted many scholars to research skeleton-based action recognition. Most of the current skeleton-based action recognition methods suffer from the incomplete and poor generalization of the input features, inadequate feature extraction by the network model, and an imbalance between recognition accuracy and model size. We analyze the critical skeleton features for action recognition to solve these problems and propose a multifeatures and multistream network (MM-Net) for real-time action recognition. First, three pairs of features are proposed, which are the joint distance (JD) and JD velocity (JDV), joint angle (JA) and JA velocity (JAV), and fast-action joint position (FJP) and slow-action joint position (SJP). Second, an MM-Net is proposed by using a 1-D convolutional neural network (1DCNN) to reduce the number of parameters of the model and fully extract the three pairs of features. As a result, MM-Net achieves the highest accuracies on both JHMDB (86.5%) and SHREC (96.4% on coarse and 93.3% on fine datasets). In addition, MM-Net is applied to a human–robot interaction (HRI) platform, which proves the practicality of MM-Net.
1 citations
TL;DR: This paper presents a computationally efficient yet generic spatial-temporal cascaded framework that exploits the deep discriminative spatial and temporal features for human activity recognition and attains an improvement in execution time up to 167 × in terms of frames per second.
Abstract: Vision-based human activity recognition (HAR) has emerged as one of the essential research areas in video analytics. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize complex human actions from video streams. These deep learning algorithms have shown impressive performance for the video analytics task. However, these newly introduced methods either exclusively focus on model performance or the effectiveness of these models in terms of computational efficiency, resulting in a biased trade-off between robustness and computational efficiency in their proposed methods to deal with challenging HAR problem. To enhance both the accuracy and computational efficiency, this paper presents a computationally efficient yet generic spatial–temporal cascaded framework that exploits the deep discriminative spatial and temporal features for HAR. For efficient representation of human actions, we propose an efficient dual attentional convolutional neural network (DA-CNN) architecture that leverages a unified channel–spatial attention mechanism to extract human-centric salient features in video frames. The dual channel–spatial attention layers together with the convolutional layers learn to be more selective in the spatial receptive fields having objects within the feature maps. The extracted discriminative salient features are then forwarded to a stacked bi-directional gated recurrent unit (Bi-GRU) for long-term temporal modeling and recognition of human actions using both forward and backward pass gradient learning. Extensive experiments are conducted on three publicly available human action datasets, where the obtained results verify the effectiveness of our proposed framework (DA-CNN+Bi-GRU) over the state-of-the-art methods in terms of model accuracy and inference runtime across each dataset. Experimental results show that the DA-CNN+Bi-GRU framework attains an improvement in execution time up to 167× in terms of frames per second as compared to most of the contemporary action-recognition methods.
1 citations
References
More filters
18 Jun 2018
TL;DR: This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.
Abstract: The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .
14,807 citations
18 Jun 2018
TL;DR: In this article, the non-local operation computes the response at a position as a weighted sum of the features at all positions, which can be used to capture long-range dependencies.
Abstract: Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method [4] in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our nonlocal models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code will be made available.
8,059 citations
Posted Content•
TL;DR: It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.
Abstract: This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.
7,951 citations
"Pose And Joint-Aware Action Recogni..." refers background or methods in this paper
...We enforce this constraint by employing contrastive learning loss [35, 7, 23]....
[...]
...Different from the usual contrastive learning setup [7, 23] where the loss is applied to the last layer features, the proposed loss operates on the ‘mid-level’ joint features....
[...]
Proceedings Article•
08 Dec 2014TL;DR: This work proposes a two-stream ConvNet architecture which incorporates spatial and temporal networks and demonstrates that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data.
Abstract: We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework.
Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multitask learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.
6,397 citations
"Pose And Joint-Aware Action Recogni..." refers background in this paper
...[42] was amongst the first to successfully apply deep networks for action recognition that relied on RGB and optical flow....
[...]
Posted Content•
TL;DR: This work proposes a universal unsupervised learning approach to extract useful representations from high-dimensional data, which it calls Contrastive Predictive Coding, and demonstrates that the approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
Abstract: While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsupervised learning approach to extract useful representations from high-dimensional data, which we call Contrastive Predictive Coding. The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models. We use a probabilistic contrastive loss which induces the latent space to capture information that is maximally useful to predict future samples. It also makes the model tractable by using negative sampling. While most prior work has focused on evaluating representations for a particular modality, we demonstrate that our approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
5,444 citations
"Pose And Joint-Aware Action Recogni..." refers methods in this paper
...We enforce this constraint by employing contrastive learning loss [35, 7, 23]....
[...]