Video Action Recognition Via Neural Architecture Searching

Peng, Wei; Hong, Xiaopeng; Zhao, Guoying

doi:10.1109/icip.2019.8802919

Cited by 43 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of NAS approaches search networks on a small proxy task and transfer the found architecture to another large target task. For the perspective of computer vision applications, NAS has been developed for face recognition [67], action recognition [46], person ReID [50], object detection [21] and segmentation [65] tasks. To the best of our knowledge, no NAS based method has ever been proposed for face anti-spoofing task.…”

Section: Related Workmentioning

confidence: 99%

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

Zhao

Wang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

440

300

View full text Add to dashboard Cite

Face anti-spoofing (FAS) plays a vital role in face recognition systems. Most state-of-the-art FAS methods 1) rely on stacked convolutions and expert-designed network, which is weak in describing detailed fine-grained information and easily being ineffective when the environment varies (e.g., different illumination), and 2) prefer to use long sequence as input to extract dynamic features, making them difficult to deploy into scenarios which need quick response. Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information. A network built with CDC, called the Central Difference Convolutional Network (CDCN), is able to provide more robust modeling capacity than its counterpart built with vanilla convolution. Furthermore, over a specifically designed CDC search space, Neural Architecture Search (NAS) is utilized to discover a more powerful network structure (CDCN++), which can be assembled with Multiscale Attention Fusion Module (MAFM) for further boosting performance. Comprehensive experiments are performed on six benchmark datasets to show that 1) the proposed method not only achieves superior performance on intra-dataset testing (especially 0.2% ACER in Protocol-1 of OULU-NPU dataset), 2) it also generalizes well on cross-dataset testing (particularly 6.5% HTER from CASIA-MFSD to Replay-Attack datasets). The codes are available at https://github.com/ZitongYu/CDCN.

show abstract

Section: Related Workmentioning

confidence: 99%

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

Zhao

Wang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

440

300

View full text Add to dashboard Cite

show abstract

“…Since the neural networks are still hard to design a priori , Neural Architecture Search (NAS) has been proposed to design the neural networks automatically based on reinforcement learning [ 165 , 166 ], evolution algorithm [ 167 , 168 ] or gradient-based methods [ 169 , 170 ]. Recently, NAS has been applied to several challenging computer vision tasks, such as face recognition [ 171 ], action recognition [ 172 ], person reidentification [ 173 ], object detection [ 174 ] and segmentation [ 175 ]. However, NAS has just started being applied to facial PAD.…”

Section: Overview Of Facial Pad Methods Using Only Rgb Cameras From Gcdsmentioning

confidence: 99%

A Survey on Anti-Spoofing Methods for Facial Recognition with RGB Cameras of Generic Consumer Devices

et al. 2020

View full text Add to dashboard Cite

The widespread deployment of facial recognition-based biometric systems has made facial presentation attack detection (face anti-spoofing) an increasingly critical issue. This survey thoroughly investigates facial Presentation Attack Detection (PAD) methods that only require RGB cameras of generic consumer devices over the past two decades. We present an attack scenario-oriented typology of the existing facial PAD methods, and we provide a review of over 50 of the most influenced facial PAD methods over the past two decades till today and their related issues. We adopt a comprehensive presentation of the reviewed facial PAD methods following the proposed typology and in chronological order. By doing so, we depict the main challenges, evolutions and current trends in the field of facial PAD and provide insights on its future research. From an experimental point of view, this survey paper provides a summarized overview of the available public databases and an extensive comparison of the results reported in PAD-reviewed papers.

show abstract

“…Action recognition (Yan, Xiong, and Lin 2018;Peng, Hong, and Zhao 2019;Peng et al 2020) is one of the most important areas in both industry and academia. We can find numbers of previous action recognition works based on RGB images or videos as the RGB data is available everywhere in real life.…”

Section: Human Action Recognitionmentioning

confidence: 99%

Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition

Peng

Shi

Xia

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Graph Convolutional Networks (GCNs) have already demonstrated their powerful ability to model the irregular data, e.g., skeletal data in human action recognition, providing an exciting new way to fuse rich structural information for nodes residing in different parts of a graph. In human action recognition, current works introduce a dynamic graph generation mechanism to better capture the underlying semantic skeleton connections and thus improves the performance. In this paper, we provide an orthogonal way to explore the underlying connections. Instead of introducing an expensive dynamic graph generation paradigm, we build a more efficient GCN on a Riemann manifold, which we think is a more suitable space to model the graph data, to make the extracted representations fit the embedding matrix. Specifically, we present a novel spatial-temporal GCN (ST-GCN) architecture which is defined via the Poincaré geometry such that it is able to better model the latent anatomy of the structure data. To further explore the optimal projection dimension in the Riemann space, we mix different dimensions on the manifold and provide an efficient way to explore the dimension for each ST-GCN layer. With the final resulted architecture, we evaluate our method on two current largest scale 3D datasets, i.e., NTU RGB+D and NTU RGB+D 120. The comparison results show that the model could achieve a superior performance under any given evaluation metrics with only 40% model size when compared with the previous best GCN method, which proves the effectiveness of our model.

show abstract

Video Action Recognition Via Neural Architecture Searching

Cited by 43 publications

References 22 publications

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

A Survey on Anti-Spoofing Methods for Facial Recognition with RGB Cameras of Generic Consumer Devices

Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition

Contact Info

Product

Resources

About