arXiv subjects

Guodong Guo

Publications and source records attributed to Guodong Guo.

83 records · Page 5Linked to original sources

arXiv2019

ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of $8.1\%$ (from $0.8917$ to $0.9639$) of CSR.

cs.CV↗

arXiv2019

A database for face presentation attack using wax figure faces

Compared to 2D face presentation attacks (e.g. printed photos and video replays), 3D type attacks are more challenging to face recognition systems (FRS) by presenting 3D characteristics or materials similar to real faces. Existing 3D face spoofing databases, however, mostly based on 3D masks, are restricted to small data size or poor authenticity due to the production difficulty and high cost. In this work, we introduce the first wax figure face database, WFFD, as one type of super-realistic 3D presentation attacks to spoof the FRS. This database consists of 2200 images with both real and wax figure faces (totally 4400 faces) with a high diversity from online collections. Experiments on this database first investigate the vulnerability of three popular FRS to this kind of new attack. Further, we evaluate the performance of several face presentation attack detection methods to show the attack abilities of this super-realistic face spoofing database.

cs.CV↗

arXiv2019

Supervised Online Hashing via Similarity Distribution Learning

Online hashing has attracted extensive research attention when facing streaming data. Most online hashing methods, learning binary codes based on pairwise similarities of training instances, fail to capture the semantic relationship, and suffer from a poor generalization in large-scale applications due to large variations. In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space. Specifically, we first transform the discrete similarity matrix into a probability matrix via a Gaussian-based normalization to address the extremely imbalanced distribution issue. And then, we introduce a scaling Student t-distribution to solve the challenging initialization problem, and efficiently bridge the gap between the known and unknown distributions. Lastly, we align the two distributions via minimizing the Kullback-Leibler divergence (KL-diverence) with stochastic gradient descent (SGD), by which an intuitive similarity constraint is imposed to update hashing model on the new streaming data with a powerful generalizing ability to the past data. Extensive experiments on three widely-used benchmarks validate the superiority of the proposed SDOH over the state-of-the-art methods in the online retrieval task.

cs.CV↗

arXiv2019

Adversarial Attacks against Deep Saliency Models

Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet been studied. In this paper, we propose a sparse feature-space adversarial attack method against deep saliency models for the first time. The proposed attack only requires a part of the model information, and is able to generate a sparser and more insidious adversarial perturbation, compared to traditional image-space attacks. These adversarial perturbations are so subtle that a human observer cannot notice their presences, but the model outputs will be revolutionized. This phenomenon raises security threats to deep saliency models in practical applications. We also explore some intriguing properties of the feature-space attack, e.g. 1) the hidden layers with bigger receptive fields generate sparser perturbations, 2) the deeper hidden layers achieve higher attack success rates, and 3) different loss functions and different attacked layers will result in diverse perturbations. Experiments indicate that the proposed method is able to successfully attack different model architectures across various image scenes.

cs.CV↗

arXiv2019

Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition

We propose a new deep network structure for unconstrained face recognition. The proposed network integrates several key components together in order to characterize complex data distributions, such as in unconstrained face images. Inspired by recent progress in deep networks, we consider some important concepts, including multi-scale feature learning, dense connections of network layers, and weighting different network flows, for building our deep network structure. The developed network is evaluated in unconstrained face matching, showing the capability of learning complex data distributions caused by face images with various qualities.

cs.CV↗

arXiv2018

Unconstrained Face Detection and Open-Set Face Recognition Challenge

Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance cameras. While face detection has shown remarkable success in images collected from the web, surveillance cameras include more diverse occlusions, poses, weather conditions and image blur. Although face verification or closed-set face identification have surpassed human capabilities on some datasets, open-set identification is much more complex as it needs to reject both unknown identities and false accepts from the face detector. We show that unconstrained face detection can approach high detection rates albeit with moderate false accept rates. By contrast, open-set face recognition is currently weak and requires much more attention.

cs.CV↗

arXiv2018

Attributes in Multiple Facial Images

Facial attribute recognition is conventionally computed from a single image. In practice, each subject may have multiple face images. Taking the eye size as an example, it should not change, but it may have different estimation in multiple images, which would make a negative impact on face recognition. Thus, how to compute these attributes corresponding to each subject rather than each single image is a profound work. To address this question, we deploy deep training for facial attributes prediction, and we explore the inconsistency issue among the attributes computed from each single image. Then, we develop two approaches to address the inconsistency issue. Experimental results show that the proposed methods can handle facial attribute estimation on either multiple still images or video frames, and can correct the incorrectly annotated labels. The experiments are conducted on two large public databases with annotations of facial attributes.

cs.CV↗

arXiv2016

From Graph Isoperimetric Inequality to Network Connectivity -- A New Approach

We present a new, novel approach to obtaining a network's connectivity. More specifically, we show that there exists a relationship between a network's graph isoperimetric properties and its conditional connectivity. A network's connectivity is the minimum number of nodes, whose removal will cause the network disconnected. It is a basic and important measure for the network's reliability, hence its overall robustness. Several conditional connectivities have been proposed in the past for the purpose of accurately reflecting various realistic network situations, with extra connectivity being one such conditional connectivity. In this paper, we will use isoperimetric properties of the hypercube network to obtain its extra connectivity. The result of the paper for the first time establishes a relationship between the age-old isoperimetric problem and network connectivity.

cs.DC↗

arXiv2016

Performance of Photosensors in the PandaX-I Experiment

We report the long term performance of the photosensors, 143 one-inch R8520-406 and 37 three-inch R11410-MOD photomultipliers from Hamamatsu, in the first phase of the PandaX dual-phase xenon dark matter experiment. This is the first time that a significant number of R11410 photomultiplier tubes were operated in liquid xenon for an extended period, providing important guidance to the future large xenon-based dark matter experiments.

physics.ins-det↗

arXiv2015

Low-mass dark matter search results from full exposure of PandaX-I experiment

We report the results of a weakly-interacting massive particle (WIMP) dark matter search using the full 80.1\;live-day exposure of the first stage of the PandaX experiment (PandaX-I) located in the China Jin-Ping Underground Laboratory. The PandaX-I detector has been optimized for detecting low-mass WIMPs, achieving a photon detection efficiency of 9.6\%. With a fiducial liquid xenon target mass of 54.0\,kg, no significant excess event were found above the expected background. A profile likelihood analysis confirms our earlier finding that the PandaX-I data disfavor all positive low-mass WIMP signals reported in the literature under standard assumptions. A stringent bound on the low mass WIMP is set at WIMP mass below 10\,GeV/c$^2$, demonstrating that liquid xenon detectors can be competitive for low-mass WIMP searches.

hep-ex↗

arXiv2014

First dark matter search results from the PandaX-I experiment

We report on the first dark-matter (DM) search results from PandaX-I, a low threshold dual-phase xenon experiment operating at the China Jinping Underground Laboratory. In the 37-kg liquid xenon target with 17.4 live-days of exposure, no DM particle candidate event was found. This result sets a stringent limit for low-mass DM particles and disfavors the interpretation of previously-reported positive experimental results. The minimum upper limit, $3.7\times10^{-44}$\,cm$^2$, for the spin-independent isoscalar DM-particle-nucleon scattering cross section is obtained at a DM-particle mass of 49\,GeV/c$^2$ at 90\% confidence level.

hep-ex↗