Semisupervised Discriminant Multimanifold Analysis for Action Recognition

Xu, Zengmin; Hu, Ruimin; Chen, Chen; Jiang, Junjun; Li, Jiao‐fen; Li, Hongyang

doi:10.1109/tnnls.2018.2886008

Cited by 25 publications

(11 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Top-1 Acc Parameters MFLOPs Visual Attention (2016) [33] 85.0 108M -TT-LSTM (2017) [11] 79.6 0.268M 37.1 TT-GRU (2017) [11] 81.3 0.203M 31.2 BT-LSTM (2018) [12] 85.3 0.268M 100.6 TR-LSTM (2019) [13] 86.9 0.267M 118.9 HT-LSTM (2020) [22] 79.7 7.4M -5th-order HT-LSTM (2020) [14] [34] 78.5 0.1M -RRNN (2016) [35] 86.6 38M 381 TT-LSTM (2017) [11] 75.5 0.278M 50.5 TT-GRU (2017) [11] 80.0 0.212M 44.5 5th-order HT-LSTM (2020) [14] [36] 78.0 74M 724 SDMA-TDD (2019) [37] 89.0 59M -Fusion Feature (2019) [38] 91.1 111M -HT-LSTM (2020) [22] 76.6 7.4M -Ours (6,4,4)…”

Section: Ucf11 Methodsmentioning

confidence: 99%

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

Wang,

Wu,

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, including long-short term memory (LSTM) and gated recurrent unit (GRU) networks, have complex topologies and expensive space/computation complexity, compressing them becomes a hot and promising topic in recent years. Among plenty of compression methods, tensor decomposition, e.g., tensor train (TT), block term (BT), tensor ring (TR) and hierarchical Tucker (HT), appears to be the most amazing approach since a very high compression ratio might be obtained. Nevertheless, none of these tensor decomposition formats can provide both the space and computation efficiency. In this paper, we consider to compress RNNs based on a novel Kronecker CANDECOMP/PARAFAC (KCP) decomposition, which is derived from Kronecker tensor (KT) decomposition, by proposing two fast algorithms of multiplication between the input and the tensor-decomposed weight. According to our experiments based on UCF11, Youtube Celebrities Face and UCF50 datasets, it can be verified that the proposed KCP-RNNs have comparable performance of accuracy with those in other tensor-decomposed formats, and even 278,219× compression ratio could be obtained by the low rank KCP. More importantly, KCP-RNNs are efficient in both space and computation complexity compared with other tensor-decomposed ones under similar ranks. Besides, we find KCP has the best potential for parallel computing to accelerate the calculations in neural networks.

show abstract

Section: Ucf11 Methodsmentioning

confidence: 99%

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

Wang,

Wu,

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The closed-set methods were: iDT [18], Two-stream [31], FstCN [71], MoFAP [72], MIFS [8], LTC [34], R-STAN [73], ST-Pyramid Network [74], ATW [75], DOVF [76], Four-Stream [77], TLE [78], and DTPP [79]. The open-set methods were: ODN [43], P-ODN [44], SDMM [48], and Mishra et al [47].…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…Thus, these existing works will often fail to give a correct prediction in the real-world situation since some actions have not been trained. Furthermore, it is difficult to define every Among the various approaches recently proposed for the open-set condition [41]- [48], the meta-learning method by [42] discriminates an untrained class from a trained class and learns it as a new class (unknown class), making the model learn a new class (unknown class) without re-training the model. Bendale and Boult [41] proposed SVM-based recognition by extending Nearest Class Mean type algorithms [9], [15] to a Nearest Non-Outlier(NNO) algorithm to learn new classes continuously.…”

Section: Open-set Action Recognitionmentioning

confidence: 99%

Spatio-Temporal Representation Matching-Based Open-Set Action Recognition by Joint Learning of Motion and Appearance

Yoon

Jeon

2019

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose the spatio-temporal representation matching (STRM) for video-based action recognition under the open-set condition. Open-set action recognition is a more challenging problem than closed-set action recognition since samples of the untrained action class need to be recognized and most of the conventional frameworks are likely to give a false prediction. To handle the untrained action classes, we propose STRM, which involves jointly learning both motion and appearance. STRM extracts spatio-temporal representations from video clips through a joint learning pipeline with both motion and appearance information. Then, STRM computes the similarities between the ST-representations to find the one with highest similarity. We set the experimental protocol for open-set action recognition and carried out experiments on UCF101 and HMDB51 to evaluate STRM. We first investigated the effects of different hyperparameter settings on STRM, and then compared its performance with existing state-of-the-art methods. The experimental results showed that the proposed method not only outperformed existing methods under the open-set condition, but also provided comparable performance to the state-of-the-art methods under the closed-set condition.

show abstract

“…All images come from about 5400 real video clips, collected by 156 surveillance cameras in the coastline video surveillance system. Some research uses this dataset to train their model or improve the model's performance [139,140]. Some other datasets need to be highlighted.…”

Section: Marine Datasets Comparison Moosbauer Et Al [144]mentioning

confidence: 99%

Survey on Deep Learning-Based Marine Object Detection

Zhang

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

We present a survey on marine object detection based on deep neural network approaches, which are state-of-the-art approaches for the development of autonomous ship navigation, maritime surveillance, shipping management, and other intelligent transportation system applications in the future. The fundamental task of maritime transportation surveillance and autonomous ship navigation is to construct a reachable visual perception system that requires high efficiency and high accuracy of marine object detection. Therefore, high-performance deep learning-based algorithms and high-quality marine-related datasets need to be summarized. This survey focuses on summarizing the methods and application scenarios of maritime object detection, analyzes the characteristics of different marine-related datasets, highlights the marine detection application of the YOLO series model, and also discusses the current limitations of object detection based on deep learning and possible breakthrough directions. The large-scale, multiscenario industrialized neural network training is an indispensable link to solve the practical application of marine object detection. A widely accepted and standardized large-scale marine object verification dataset should be proposed.

show abstract

Semisupervised Discriminant Multimanifold Analysis for Action Recognition

Cited by 25 publications

References 70 publications

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

Spatio-Temporal Representation Matching-Based Open-Set Action Recognition by Joint Learning of Motion and Appearance

Survey on Deep Learning-Based Marine Object Detection

Contact Info

Product

Resources

About