scispace - formally typeset
Open accessJournal ArticleDOI: 10.1007/S11263-021-01446-Y

Mimetics: Towards Understanding Human Actions Out of Context

02 Mar 2021-International Journal of Computer Vision (Springer US)-Vol. 129, Iss: 5, pp 1675-1690
Abstract: Recent methods for video action recognition have reached outstanding performances on existing benchmarks. However, they tend to leverage context such as scenes or objects instead of focusing on understanding the human action itself. For instance, a tennis field leads to the prediction playing tennis irrespectively of the actions performed in the video. In contrast, humans have a more complete understanding of actions and can recognize them without context. The best example of out-of-context actions are mimes, that people can typically recognize despite missing relevant objects and scenes. In this paper, we propose to benchmark action recognition methods in such absence of context and introduce a novel dataset, Mimetics, consisting of mimed actions for a subset of 50 classes from the Kinetics benchmark. Our experiments show that (a) state-of-the-art 3D convolutional neural networks obtain disappointing results on such videos, highlighting the lack of true understanding of the human actions and (b) models leveraging body language via human pose are less prone to context biases. In particular, we show that applying a shallow neural network with a single temporal convolution over body pose features transferred to the action recognition problem performs surprisingly well compared to 3D action recognition methods.

... read more

Citations
  More

7 results found


Open accessPosted Content
Abstract: In this paper, we study current and upcoming frontiers across the landscape of skeleton-based human action recognition. To begin with, we benchmark state-of-the-art models on the NTU-120 dataset and provide multi-layered assessment of the results. To examine skeleton action recognition 'in the wild', we introduce Skeletics-152, a curated and 3-D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset. The results from benchmarking the top performers of NTU-120 on Skeletics-152 reveal the challenges and domain gap induced by actions 'in the wild'. We extend our study to include out-of-context actions by introducing Skeleton-Mimetics, a dataset derived from the recently introduced Mimetics dataset. Finally, as a new frontier for action recognition, we introduce Metaphorics, a dataset with caption-style annotated YouTube videos of the popular social game Dumb Charades and interpretative dance performances. Overall, our work characterizes the strengths and limitations of existing approaches and datasets. It also provides an assessment of top-performing approaches across a spectrum of activity settings and via the introduced datasets, proposes new frontiers for human action recognition.

... read more

3 Citations


Open accessJournal ArticleDOI: 10.1007/S11263-021-01470-Y
Abstract: In this paper, we study current and upcoming frontiers across the landscape of skeleton-based human action recognition. To study skeleton-action recognition in the wild, we introduce Skeletics-152, a curated and 3-D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset. We extend our study to include out-of-context actions by introducing Skeleton-Mimetics, a dataset derived from the recently introduced Mimetics dataset. We also introduce Metaphorics, a dataset with caption-style annotated YouTube videos of the popular social game Dumb Charades and interpretative dance performances. We benchmark state-of-the-art models on the NTU-120 dataset and provide multi-layered assessment of the results. The results from benchmarking the top performers of NTU-120 on the newly introduced datasets reveal the challenges and domain gap induced by actions in the wild. Overall, our work characterizes the strengths and limitations of existing approaches and datasets. Via the introduced datasets, our work enables new frontiers for human action recognition.

... read more

2 Citations


Open accessPosted Content
Anshul Shah1, Shlok Kumar Mishra1, Ankan Bansal2, Jun-Cheng Chen2  +2 moreInstitutions (3)
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.

... read more

1 Citations


Open accessPosted Content
06 Oct 2021-arXiv: Learning
Abstract: Deep neural networks (DNNs) often rely on easy-to-learn discriminatory features, or cues, that are not necessarily essential to the problem at hand. For example, ducks in an image may be recognized based on their typical background scenery, such as lakes or streams. This phenomenon, also known as shortcut learning, is emerging as a key limitation of the current generation of machine learning models. In this work, we introduce a set of experiments to deepen our understanding of shortcut learning and its implications. We design a training setup with several shortcut cues, named WCST-ML, where each cue is equally conducive to the visual recognition problem at hand. Even under equal opportunities, we observe that (1) certain cues are preferred to others, (2) solutions biased to the easy-to-learn cues tend to converge to relatively flat minima on the loss surface, and (3) the solutions focusing on those preferred cues are far more abundant in the parameter space. We explain the abundance of certain cues via their Kolmogorov (descriptional) complexity: solutions corresponding to Kolmogorov-simple cues are abundant in the parameter space and are thus preferred by DNNs. Our studies are based on the synthetic dataset DSprites and the face dataset UTKFace. In our WCST-ML, we observe that the inborn bias of models leans toward simple cues, such as color and ethnicity. Our findings emphasize the importance of active human intervention to remove the inborn model biases that may cause negative societal impacts.

... read more

1 Citations


Proceedings ArticleDOI: 10.1109/UR52253.2021.9494666
Hyung-Min Kim1, Do Hyung Kim1, Jaehong Kim2Institutions (2)
12 Jul 2021-
Abstract: This paper addresses a practical action recognition method for elderly-care robots. Multi-stream based models are one of the promising approaches for solving the complexity of real-world environments. While multi-modal action recognition have been actively studied, there is a lack of research on models that effectively combine features of different modalities. This paper proposes a new mid-level feature fusion method for two-stream based action recognition network. In multi-modal approaches, extracting complementary information between different modalities is an essential task. Our network model is designed to fuse features at an intermediate level of feature extraction, which leverages a whole feature map from each modality. Consensus feature map and consensus attention mechanism are proposed as effective ways to extract information from two different modalities: RGB data and motion features. We also introduce ETRI-Activity3D-LivingLab, a real-world RGB-D dataset for robots to recognize daily activities of the elderly. It is the first 3D action recognition dataset obtained in a variety of home environments where the elderly actually reside. We expect our new dataset to contribute to the practical study of action recognition with the previously released ETRI-Activity3D dataset. To prove the effectiveness of the method, extensive experiments are performed on NTU RGB+D, ETRI-Activity3D and, ETRI-Activity3D-LivingLab dataset. Our mid-level fusion method achieves competitive performance in various experimental settings, especially for domain-changing situations.

... read more


References
  More

57 results found


Open accessProceedings ArticleDOI: 10.1109/CVPR.2016.90
Kaiming He1, Xiangyu Zhang1, Shaoqing Ren1, Jian Sun1Institutions (1)
27 Jun 2016-
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

... read more

Topics: Deep learning (53%), Residual (53%), Convolutional neural network (53%) ... read more

93,356 Citations


Open accessProceedings ArticleDOI: 10.1109/CVPR.2015.7298594
Christian Szegedy1, Wei Liu2, Yangqing Jia1, Pierre Sermanet1  +5 moreInstitutions (3)
07 Jun 2015-
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

... read more

29,453 Citations


Open accessPosted Content
Shaoqing Ren1, Kaiming He2, Ross Girshick3, Jian Sun2Institutions (3)
Abstract: State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

... read more

Topics: Object detection (58%)

23,121 Citations


Open accessProceedings ArticleDOI: 10.1109/CVPR.2017.634
Saining Xie1, Ross Girshick2, Piotr Dollár2, Zhuowen Tu1  +1 moreInstitutions (2)
21 Jul 2017-
Abstract: We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call cardinality (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.

... read more

Topics: Cardinality (61%), Dimension (vector space) (54%), Set (abstract data type) (53%) ... read more

5,343 Citations


Open accessProceedings ArticleDOI: 10.1109/ICCV.2015.510
Du Tran1, Du Tran2, Lubomir Bourdev2, Rob Fergus2  +2 moreInstitutions (2)
07 Dec 2015-
Abstract: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.

... read more

Topics: Feature learning (54%), Linear classifier (53%), Feature extraction (50%)

4,858 Citations


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20215
20202
Network Information
Related Papers (5)
A Grid-based Representation for Human Action Recognition10 Jan 2021

Soufiane Lamghari, Guillaume-Alexandre Bilodeau +1 more

Exploiting language models to recognize unseen actions16 Apr 2013

Dieu Thu Le, Raffaella Bernardi +1 more