arXiv subjects

Yu Qiao

Publications and source records attributed to Yu Qiao.

660 records · Page 37Linked to original sources

arXiv2015

Better Exploiting OS-CNNs for Better Event Recognition in Images

Event recognition from still images is one of the most important problems for image understanding. However, compared with object recognition and scene recognition, event recognition has received much less research attention in computer vision community. This paper addresses the problem of cultural event recognition in still images and focuses on applying deep learning methods on this problem. In particular, we utilize the successful architecture of Object-Scene Convolutional Neural Networks (OS-CNNs) to perform event recognition. OS-CNNs are composed of object nets and scene nets, which transfer the learned representations from the pre-trained models on large-scale object and scene recognition datasets, respectively. We propose four types of scenarios to explore OS-CNNs for event recognition by treating them as either "end-to-end event predictors" or "generic feature extractors". Our experimental results demonstrate that the global and local representations of OS-CNNs are complementary to each other. Finally, based on our investigation of OS-CNNs, we come up with a solution for the cultural event recognition track at the ICCV ChaLearn Looking at People (LAP) challenge 2015. Our team secures the third place at this challenge and our result is very close to the best performance.

cs.CV↗

arXiv2015

Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization

Local binary descriptors are attracting increasingly attention due to their great advantages in computational speed, which are able to achieve real-time performance in numerous image/vision applications. Various methods have been proposed to learn data-dependent binary descriptors. However, most existing binary descriptors aim overly at computational simplicity at the expense of significant information loss which causes ambiguity in similarity measure using Hamming distance. In this paper, by considering multiple features might share complementary information, we present a novel local binary descriptor, referred as Ring-based Multi-Grouped Descriptor (RMGD), to successfully bridge the performance gap between current binary and floated-point descriptors. Our contributions are two-fold. Firstly, we introduce a new pooling configuration based on spatial ring-region sampling, allowing for involving binary tests on the full set of pairwise regions with different shapes, scales and distances. This leads to a more meaningful description than existing methods which normally apply a limited set of pooling configurations. Then, an extended Adaboost is proposed for efficient bit selection by emphasizing high variance and low correlation, achieving a highly compact representation. Secondly, the RMGD is computed from multiple image properties where binary strings are extracted. We cast multi-grouped features integration as rankSVM or sparse SVM learning problem, so that different features can compensate strongly for each other, which is the key to discriminativeness and robustness. The performance of RMGD was evaluated on a number of publicly available benchmarks, where the RMGD outperforms the state-of-the-art binary descriptors significantly.

cs.CV↗

arXiv2015

Places205-VGGNet Models for Scene Recognition

VGGNets have turned out to be effective for object recognition in still images. However, it is unable to yield good performance by directly adapting the VGGNet models trained on the ImageNet dataset for scene recognition. This report describes our implementation of training the VGGNets on the large-scale Places205 dataset. Specifically, we train three VGGNet models, namely VGGNet-11, VGGNet-13, and VGGNet-16, by using a Multi-GPU extension of Caffe toolbox with high computational efficiency. We verify the performance of trained Places205-VGGNet models on three datasets: MIT67, SUN397, and Places205. Our trained models achieve the state-of-the-art performance on these datasets and are made public available.

cs.CV↗

arXiv2015

Local Color Contrastive Descriptor for Image Classification

Image representation and classification are two fundamental tasks towards multimedia content retrieval and understanding. The idea that shape and texture information (e.g. edge or orientation) are the key features for visual representation is ingrained and dominated in current multimedia and computer vision communities. A number of low-level features have been proposed by computing local gradients (e.g. SIFT, LBP and HOG), and have achieved great successes on numerous multimedia applications. In this paper, we present a simple yet efficient local descriptor for image classification, referred as Local Color Contrastive Descriptor (LCCD), by leveraging the neural mechanisms of color contrast. The idea originates from the observation in neural science that color and shape information are linked inextricably in visual cortical processing. The color contrast yields key information for visual color perception and provides strong linkage between color and shape. We propose a novel contrastive mechanism to compute the color contrast in both spatial location and multiple channels. The color contrast is computed by measuring \emph{f}-divergence between the color distributions of two regions. Our descriptor enriches local image representation with both color and contrast information. We verified experimentally that it can compensate strongly for the shape based descriptor (e.g. SIFT), while keeping computationally simple. Extensive experimental results on image classification show that our descriptor improves the performance of SIFT substantially by combinations, and achieves the state-of-the-art performance on three challenging benchmark datasets. It improves recent Deep Learning model (DeCAF) [1] largely from the accuracy of 40.94% to 49.68% in the large scale SUN397 database. Codes for the LCCD will be available.

cs.CV↗

arXiv2015

Towards Good Practices for Very Deep Two-Stream ConvNets

Deep convolutional networks have achieved great success for object recognition in still images. However, for action recognition in videos, the improvement of deep convolutional networks is not so evident. We argue that there are two reasons that could probably explain this result. First the current network architectures (e.g. Two-stream ConvNets) are relatively shallow compared with those very deep models in image domain (e.g. VGGNet, GoogLeNet), and therefore their modeling capacity is constrained by their depth. Second, probably more importantly, the training dataset of action recognition is extremely small compared with the ImageNet dataset, and thus it will be easy to over-fit on the training dataset. To address these issues, this report presents very deep two-stream ConvNets for action recognition, by adapting recent very deep architectures into video domain. However, this extension is not easy as the size of action recognition is quite small. We design several good practices for the training of very deep two-stream ConvNets, namely (i) pre-training for both spatial and temporal nets, (ii) smaller learning rates, (iii) more data augmentation techniques, (iv) high drop out ratio. Meanwhile, we extend the Caffe toolbox into Multi-GPU implementation with high computational efficiency and low memory consumption. We verify the performance of very deep two-stream ConvNets on the dataset of UCF101 and it achieves the recognition accuracy of $91.4\%$.

cs.CV↗

arXiv2015

Boosting Optical Character Recognition: A Super-Resolution Approach

Text image super-resolution is a challenging yet open research problem in the computer vision community. In particular, low-resolution images hamper the performance of typical optical character recognition (OCR) systems. In this article, we summarize our entry to the ICDAR2015 Competition on Text Image Super-Resolution. Experiments are based on the provided ICDAR2015 TextSR dataset and the released Tesseract-OCR 3.02 system. We report that our winning entry of text image super-resolution framework has largely improved the OCR performance with low-resolution images used as input, reaching an OCR accuracy score of 77.19%, which is comparable with that of using the original high-resolution images 78.80%.

cs.CV↗

arXiv2015

Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features. Specifically, we utilize deep architectures to learn discriminative convolutional feature maps, and conduct trajectory-constrained pooling to aggregate these convolutional features into effective descriptors. To enhance the robustness of TDDs, we design two normalization methods to transform convolutional feature maps, namely spatiotemporal normalization and channel normalization. The advantages of our features come from (i) TDDs are automatically learned and contain high discriminative capacity compared with those hand-crafted features; (ii) TDDs take account of the intrinsic characteristics of temporal dimension and introduce the strategies of trajectory-constrained sampling and pooling for aggregating deep-learned features. We conduct experiments on two challenging datasets: HMDB51 and UCF101. Experimental results show that TDDs outperform previous hand-crafted features and deep-learned features. Our method also achieves superior performance to the state of the art on these datasets (HMDB51 65.9%, UCF101 91.5%).

cs.CV↗

arXiv2015

Object-Scene Convolutional Neural Networks for Event Recognition in Images

Event recognition from still images is of great importance for image understanding. However, compared with event recognition in videos, there are much fewer research works on event recognition in images. This paper addresses the issue of event recognition from images and proposes an effective method with deep neural networks. Specifically, we design a new architecture, called Object-Scene Convolutional Neural Network (OS-CNN). This architecture is decomposed into object net and scene net, which extract useful information for event understanding from the perspective of objects and scene context, respectively. Meanwhile, we investigate different network architectures for OS-CNN design, and adapt the deep (AlexNet) and very-deep (GoogLeNet) networks to the task of event recognition. Furthermore, we find that the deep and very-deep networks are complementary to each other. Finally, based on the proposed OS-CNN and comparative study of different network architectures, we come up with a solution of five-stream CNN for the track of cultural event recognition at the ChaLearn Looking at People (LAP) challenge 2015. Our method obtains the performance of 85.5% and ranks the $1^{st}$ place in this challenge.

cs.CV↗

arXiv2014

Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice

Video based action recognition is one of the important and challenging problems in computer vision research. Bag of Visual Words model (BoVW) with local features has become the most popular method and obtained the state-of-the-art performance on several realistic datasets, such as the HMDB51, UCF50, and UCF101. BoVW is a general pipeline to construct a global representation from a set of local features, which is mainly composed of five steps: (i) feature extraction, (ii) feature pre-processing, (iii) codebook generation, (iv) feature encoding, and (v) pooling and normalization. Many efforts have been made in each step independently in different scenarios and their effect on action recognition is still unknown. Meanwhile, video data exhibits different views of visual pattern, such as static appearance and motion dynamics. Multiple descriptors are usually extracted to represent these different views. Many feature fusion methods have been developed in other areas and their influence on action recognition has never been investigated before. This paper aims to provide a comprehensive study of all steps in BoVW and different fusion methods, and uncover some good practice to produce a state-of-the-art action recognition system. Specifically, we explore two kinds of local features, ten kinds of encoding methods, eight kinds of pooling and normalization strategies, and three kinds of fusion methods. We conclude that every step is crucial for contributing to the final recognition rate. Furthermore, based on our comprehensive study, we propose a simple yet effective representation, called hybrid representation, by exploring the complementarity of different BoVW frameworks and local descriptors. Using this representation, we obtain the state-of-the-art on the three challenging datasets: HMDB51 (61.1%), UCF50 (92.3%), and UCF101 (87.9%).

cs.CV↗

arXiv2013

A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification

Many efforts have been devoted to develop alternative methods to traditional vector quantization in image domain such as sparse coding and soft-assignment. These approaches can be split into a dictionary learning phase and a feature encoding phase which are often closely connected. In this paper, we investigate the effects of these phases by separating them for video-based action classification. We compare several dictionary learning methods and feature encoding schemes through extensive experiments on KTH and HMDB51 datasets. Experimental results indicate that sparse coding performs consistently better than the other encoding methods in large complex dataset (i.e., HMDB51), and it is robust to different dictionaries. For small simple dataset (i.e., KTH) with less variation, however, all the encoding strategies perform competitively. In addition, we note that the strength of sophisticated encoding approaches comes not from their corresponding dictionaries but the encoding mechanisms, and we can just use randomly selected exemplars as dictionaries for video-based action classification.

cs.CV↗

arXiv2012

Uniform shift estimates for transmission problems and optimal rates of convergence for the parametric Finite Element Method

Let $Ω\subset \RR^d$, $d \geqslant 1$, be a bounded domain with piecewise smooth boundary $\partial Ω$ and let $U$ be an open subset of a Banach space $Y$. Motivated by questions in "Uncertainty Quantification," we consider a parametric family $P = (P_y)_{y \in U}$ of uniformly strongly elliptic, second order partial differential operators $P_y$ on $Ω$. We allow jump discontinuities in the coefficients. We establish a regularity result for the solution $u: Ω\times U \to \RR$ of the parametric, elliptic boundary value/transmission problem $P_y u_y = f_y$, $y \in U$, with mixed Dirichlet-Neumann boundary conditions in the case when the boundary and the interface are smooth and in the general case for $d=2$. Our regularity and well-posedness results are formulated in a scale of broken weighted Sobolev spaces $\hat\maK^{m+1}_{a+1}(Ω)$ of Babuška-Kondrat'ev type in $Ω$, possibly augmented by some locally constant functions. This implies that the parametric, elliptic PDEs $(P_y)_{y \in U}$ admit a shift theorem that is uniform in the parameter $y\in U$. In turn, this then leads to $h^m$-quasi-optimal rates of convergence (i.e. algebraic orders of convergence) for the Galerkin approximations of the solution $u$, where the approximation spaces are defined using the "polynomial chaos expansion" of $u$ with respect to a suitable family of tensorized Lagrange polynomials, following the method developed by Cohen, Devore, and Schwab (2010).

math.NA↗

arXiv2011

Layer potentials C*-algebras of domains with conical points

To a domain with conical points Ω, we associate a natural C*-algebra that is motivated by the study of boundary value problems on Ω, especially using the method of layer potentials. In two dimensions, we allow Ωto be a domain with ramified cracks. We construct an explicit groupoid associated to the boundary of Ωand use the theory of pseudodifferential operators on groupoids and its representations to obtain our layer potentials C*-algebra. We study its structure, compute the associated K-groups, and prove Fredholm conditions for the natural pseudodifferential operators affiliated to this C*-algebra.

math.OA↗