Improving Action Quality Assessment Using Weighted Aggregation

2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 2019

Can learning to measure the quality of an action help in measuring the quality of other actions? If so, can consolidated samples from multiple actions help improve the performance of current approaches? In this paper, we carry out experiments to see if knowledge transfer is possible in the action quality assessment (AQA) setting. Experiments are carried out on our newly released AQA dataset () consisting of 1106 action samples from seven actions with quality as measured by expert human judges. Our experimental results show that there is utility in learning a single model across multiple actions.

arXiv (Cornell University), 2019

Human actions in videos are 3D signals. However, there are a few methods available for multiple human action recognition. For long videos, it's difficult to search within a video for a specific action and/or person. For that, this paper proposes a new technic for multiple human action recognition and summarization for surveillance videos. The proposed approach proposes a new representation of the data by extracting the sequence of each person from the scene. This is followed by an analysis of each sequence to detect and recognize the corresponding actions using 3D convolutional neural networks (3DCNNs). Action-based video summarization is performed by saving each person's action at each time of the video. Results of this work revealed that the proposed method provides accurate multi human action recognition that easily used for summarization of any action. Further, for other videos that can be collected from the internet, which are complex and not built for surveillance applications, the proposed model was evaluated on some datasets like UCF101 and YouTube without any preprocessing. For this category of videos, the summarization is performed on the video sequences by summarizing the actions in each subsequence. The results obtained demonstrate its efficiency compared to state-of-the-art methods.

Proceedings of the 28th ACM International Conference on Multimedia, 2020

The objective of action quality assessment is to score sports videos. However, most existing works focus only on video dynamic information (i.e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos. In this work, we present a novel hybrid dynAmic-static Context-aware attenTION NETwork (ACTION-NET) for action assessment in long videos. To learn more discriminative representations for videos, we not only learn the video dynamic information but also focus on the static postures of the detected athletes in specific frames, which represent the action quality at certain moments, along with the help of the proposed hybrid dynamic-static architecture. Moreover, we leverage a context-aware attention module consisting of a temporal instancewise graph convolutional network unit and an attention unit for both streams to extract more robust stream features, where the former is for exploring the relations between instances and the latter for assigning a proper weight to each instance. Finally, we combine the features of the two streams to regress the final video score, supervised by ground-truth scores given by experts. Additionally, we have collected and annotated the new Rhythmic Gymnastics dataset, which contains videos of four different types of gymnastics routines, for evaluation of action quality assessment in long videos. Extensive experimental results validate the efficacy of our proposed method, which outperforms related approaches. The codes and dataset are available at https://github.com/lingan1996/ACTION-NET. CCS CONCEPTS • Computing methodologies → Activity recognition and understanding; Scene understanding.

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs can achieve good performance but are computationally intensive. In this work, we tackle this dilemma by designing a generic and effective module that can be embedded into 2D CNNs. To this end, we propose a spAtiotemporal, Channel and moTion excitatION (ACTION) module consisting of three paths: Spatio-Temporal Excitation (STE) path, Channel Excitation (CE) path, and Motion Excitation (ME) path. The STE path employs one channel 3D convolution to characterize spatio-temporal representation. The CE path adaptively recalibrates channel-wise feature responses by explicitly modeling interdependencies between channels in terms of the temporal aspect. The ME path calculates feature-level temporal differences, which is then utilized to excite motion-sensitive channels. We equip 2D CNNs with the proposed ACTION module to form a simple yet effective ACTION-Net with very limited extra computational cost. ACTION-Net is demonstrated by consistently outperforming 2D CNN counterparts on three backbones (i.e., ResNet-50, MobileNet V2 and BNInception) employing three datasets (i.e., Something-Something V2, Jester, and EgoGesture). Codes are available at https: //github.com/V-Sense/ACTION-Net.

arXiv (Cornell University), 2019

Human actions in videos are 3D signals. However, there are a few methods available for multiple human action recognition. For long videos, it's difficult to search within a video for a specific action and/or person. For that, this paper proposes a new technic for multiple human action recognition and summarization for surveillance videos. The proposed approach proposes a new representation of the data by extracting the sequence of each person from the scene. This is followed by an analysis of each sequence to detect and recognize the corresponding actions using 3D convolutional neural networks (3DCNNs). Action-based video summarization is performed by saving each person's action at each time of the video. Results of this work revealed that the proposed method provides accurate multi human action recognition that easily used for summarization of any action. Further, for other videos that can be collected from the internet, which are complex and not built for surveillance applications, the proposed model was evaluated on some datasets like UCF101 and YouTube without any preprocessing. For this category of videos, the summarization is performed on the video sequences by summarizing the actions in each subsequence. The results obtained demonstrate its efficiency compared to state-of-the-art methods.

Proceedings of the International Conference on Computer Vision (ICCV), 2017

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into 'action tubes' in a post-processing step. With this paper we radically depart from current practice, and take a first step towards the design and implementation of a deep network architecture able to classify and regress whole video subsets, so providing a truly optimal solution of the action detection problem. In this work, in particular, we propose a novel deep net framework able to regress and classify 3D region proposals spanning two successive video frames, whose core is an evolution of classical region proposal networks (RPNs). As such, our 3D-RPN net is able to effectively encode the temporal aspect of actions by purely exploiting appearance, as opposed to methods which heavily rely on expensive flow maps. The proposed model is end-to-end trainable and can be jointly optimised for action local-isation and classification in a single step. At test time the network predicts 'micro-tubes' encompassing two successive frames, which are linked up into complete action tubes via a new algorithm which exploits the temporal encoding learned by the network and cuts computation time by 50%. Promising results on the J-HMDB-21 and UCF-101 action detection datasets show that our model does outperform the state-of-the-art when relying purely on appearance.

Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neu-ral Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking videos into fixed length clips and Long Short Term Memory (LSTM) networks. Such architectures are designed to take advantage of both short term and long term temporal contexts, but also requires the accumulation of a predefined number of video frames (e.g., to construct video clips for 3D Con-vNet filters, to generate enough inputs for LSTMs). For applications that require low-latency online predictions of fast-changing action scenes, a new action recognition system is proposed in this paper. Termed " Weighted Multi-Region Con-volutional Neural Network " (WMR ConvNet), the proposed system is LSTM-free, and is based on 2D ConvNet that does not require the accumulation of video frames for 3D ConvNet filtering. Unlike early 2D ConvNets that are based purely on RGB frames and optical flow frames, the WMR ConvNet is designed to simultaneously capture multiple spatial and short term temporal cues (e.g., human poses, occurrences of objects in the background) with both the primary region (foreground) and secondary regions (mostly background). On both the UCF101 and HMDB51 datasets, the proposed WMR Con-vNet achieves the state-of-the-art performance among competing low-latency algorithms. Furthermore, WMR ConvNet even outperforms the 3D ConvNet based C3D algorithm that requires video frame accumulation. In an ablation study with the optical flow ConvNet stream removed, the ablated WMR ConvNet nevertheless outperforms competing algorithms.

2021

In this paper, we propose a repetition-aware augmentation to be applied to an existing loss function to embed an external attribute of a dataset into this value. We test this augmentation by training an R3D-18 [4] model on the Countix [2] dataset for action classification using cross entropy loss both before and after batch-wise mean reduction, achieving a 5.55% and 4.70% increase above baseline, respectively. Additionally, we examine two types of data imbalance in Countix [2], instance imbalance, and repetition imbalance and their effects on classification models.

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Recently, some transfer learning-based methods have been adopted in video quality assessment (VQA) to compensate for the lack of enormous training samples and human annotation labels. But these methods induce a domain gap between source and target domains, resulting in a sub-optimal feature representation that deteriorates the accuracy. This paper proposes the optimized quality feature learning via a multi-channel convolutional neural network (CNN) with the gated recurrent unit (GRU) for no-reference (NR) VQA. First, the multi-channel CNN is pre-trained on the image quality assessment (IQA) domain using non-human annotation labels, which is inspired by self-supervised learning. Then, semi-supervised learning is used to fine-tune CNN and transfer the knowledge from IQA to VQA while considering motion information for optimized quality feature learning. Finally, all frame quality features are extracted as the input of GRU to obtain the final video quality. Experimental results demonstrate that our model achieves better performance than state-of-the-art VQA approaches.

ArXiv, 2018

The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models correlations between channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block ‘Spatio-Temporal Channel Correlation’ (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improve the performance by 2–3% on the Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ign...