Search results for: Cewu Lu

Items from 1 to 20 out of 24 results

article

Fast Abnormal Event Detection

Cewu Lu, Jianping Shi, Weiming Wang, Jiaya Jia

International Journal of Computer Vision > 2019 > 127 > 8 > 993-1011

Fast abnormal event detection meets the growing demand to process an enormous number of surveillance videos. Based on the inherent redundancy of video structures, we propose an efficient sparse combination learning framework with both batch and online solvers. It achieves decent performance in the detection phase without compromising result quality. The extremely fast execution speed is guaranteed...

article

Two-Class Weather Classification

Cewu Lu, Di Lin, Jiaya Jia, Chi-Keung Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2017 > 39 > 12 > 2510 - 2524

Given a single outdoor image, we propose a collaborative learning approach using novel weather features to label the image as either sunny or cloudy. Though limited, this two-class classification problem is by no means trivial given the great variety of outdoor images captured by different cameras where the images may have been edited after capture. Our overall weather feature combines the data-driven...

chapter

RMPE: Regional Multi-person Pose Estimation

Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

2017 IEEE International Conference on Computer Vision (ICCV) > 2353 - 2362

2017 IEEE International Conference on Computer Vision (ICCV)

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose...

chapter

Online Video Object Detection Using Association LSTM

Yongyi Lu, Cewu Lu, Chi-Keung Tang

2017 IEEE International Conference on Computer Vision (ICCV) > 2363 - 2371

2017 IEEE International Conference on Computer Vision (ICCV)

Video object detection is a fundamental tool for many applications. Since direct application of image-based object detection cannot leverage the rich temporal information inherent in video data, we advocate to the detection of long-range video object pattern. While the Long Short-Term Memory (LSTM) has been the de facto choice for such detection, currently LSTM cannot fundamentally model object association...

article

RSCM: Region Selection and Concurrency Model for Multi-Class Weather Recognition

Di Lin, Cewu Lu, Hui Huang, Jiaya Jia

IEEE Transactions on Image Processing > 2017 > 26 > 9 > 4154 - 4167

Toward weather condition recognition, we emphasize the importance of regional cues in this paper and address a few important problems regarding appropriate representation, its differentiation among regions, and weather-condition feature construction. Our major contribution is, first, to construct a multi-class benchmark data set containing 65 000 images from six common categories for sunny, cloudy,...

article

$L_0$ Regularized Stationary-Time Estimation for Crowd Analysis

Shuai Yi, Xiaogang Wang, Cewu Lu, Jiaya Jia, more

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2017 > 39 > 5 > 981 - 994

In this paper, we tackle the problem of stationary crowd analysis which is as important as modeling mobile groups in crowd scenes and finds many important applications in crowd surveillance. Our key contribution is to propose a robust algorithm for estimating how long a foreground pixel becomes stationary. It is much more challenging than only subtracting background because failure at a single frame...

article

Improving object recognition with the ℓ-channel

Cewu Lu, Efstratios Tsougenis, Chi-Keung Tang

Pattern Recognition > 2016 > 49 > Complete > 187-197

We augment a new channel called the ℓ-channel to conventional RGB images, and propose its application in multiple classification and recognition tasks. The new RGB-ℓ image records the same scene using the color and frosted light channel, which are simultaneously captured using a binocular camera with a low-cost frosted glass placed in front of one of the cameras. Due to the light scattering property...

article

Personal object discovery in first-person videos

Cewu Lu, Renjie Liao, Jiaya Jia

IEEE Transactions on Image Processing > 2015 > 24 > 12 > 5789 - 5799

People know and care for personal objects, which can be different for individuals. Automatically discovering personal objects is thus of great practical importance. We, in this paper, pursue this task with wearable cameras based on the common sense that personal objects generally company us in various scenes. With this clue, we exploit a new object-scene distribution for robust detection. Two technical...

chapter

Box Aggregation for Proposal Decimation: Last Mile of Object Detection

Shu Liu, Cewu Lu, Jiaya Jia

2015 IEEE International Conference on Computer Vision (ICCV) > 2569 - 2577

2015 IEEE International Conference on Computer Vision (ICCV)

Regions-with-convolutional-neural-network (RCNN) is now a commonly employed object detection pipeline. Its main steps, i.e., proposal generation and convolutional neural network (CNN) feature extraction, have been intensively investigated. We focus on the last step of the system to aggregate thousands of scored box proposals into final object prediction, which we call proposal decimation. We show...

chapter

Square Localization for Efficient and Accurate Object Detection

Cewu Lu, Yongyi Lu, Hao Chen, Chi-Keung Tang

2015 IEEE International Conference on Computer Vision (ICCV) > 2560 - 2568

2015 IEEE International Conference on Computer Vision (ICCV)

The key contribution of this paper is the compact square object localization, which relaxes the exhaustive sliding window from testing all windows of different combinations of aspect ratios. Square object localization is category scalable. By using a binary search strategy, the number of scales to test is further reduced empirically to only O(log(min{H, W})) rounds of sliding CNNs, where H and W are...

chapter

Contour Box: Rejecting Object Proposals without Explicit Closed Contours

Cewu Lu, Shu Liu, Jiaya Jia, Chi-Keung Tang

2015 IEEE International Conference on Computer Vision (ICCV) > 2021 - 2029

2015 IEEE International Conference on Computer Vision (ICCV)

Closed contour is an important objectness indicator. We propose a new measure subject to the completeness and tightness constraints, where the optimized closed contour should be tightly bounded within an object proposal. The closed contour measure is defined using closed path integral, and we solve the optimization problem efficiently in polar coordinate system with a global optimum guaranteed. Extensive...

chapter

Deep LAC: Deep localization, alignment and classification for fine-grained recognition

Di Lin, Xiaoyong Shen, Cewu Lu, Jiaya Jia

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 1666 - 1674

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major contribution is to propose a valve linkage function (VLF) for back-propagation chaining and form our...

chapter

Complexity-adaptive distance metric for object proposals generation

Yao Xiao, Cewu Lu, Efstratios Tsougenis, Yongyi Lu, more

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 778 - 786

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Distance metric plays a key role in grouping superpixels to produce object proposals for object detection. We observe that existing distance metrics work primarily for low complexity cases. In this paper, we develop a novel distance metric for grouping two superpixels in high-complexity scenarios. Combining them, a complexity-adaptive distance measure is produced that achieves improved grouping in...

chapter

Learning Important Spatial Pooling Regions for Scene Classification

Di Lin, Cewu Lu, Renjie Liao, Jiaya Jia

2014 IEEE Conference on Computer Vision and Pattern Recognition > 3726 - 3733

2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

We address the false response influence problem when learning and applying discriminative parts to construct the mid-level representation in scene classification. It is often caused by the complexity of latent image structure when convolving part filters with input images. This problem makes mid-level representation, even after pooling, not distinct enough to classify input data correctly to categories...

chapter

L0 Regularized Stationary Time Estimation for Crowd Group Analysis

Shuai Yi, Xiaogang Wang, Cewu Lu, Jiaya Jia

2014 IEEE Conference on Computer Vision and Pattern Recognition > 2219 - 2226

2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance. Our key contribution is to propose a robust algorithm of estimating how long a foreground pixel becomes stationary. It is much more challenging than only subtracting background because failure at a single frame due to local movement...

chapter

Range-Sample Depth Feature for Action Recognition

Cewu Lu, Jiaya Jia, Chi-Keung Tang

2014 IEEE Conference on Computer Vision and Pattern Recognition > 772 - 779

2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

We propose binary range-sample feature in depth. It is based on &tau; tests and achieves reasonable invariance with respect to possible change in scale, viewpoint, and background. It is robust to occlusion and data corruption as well. The descriptor works in a high speed thanks to its binary property. Working together with standard learning algorithms, the proposed descriptor achieves state-of-theart...

chapter

Two-Class Weather Classification

Cewu Lu, Di Lin, Jiaya Jia, Chi-Keung Tang

2014 IEEE Conference on Computer Vision and Pattern Recognition > 3718 - 3725

2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy. Never adequately addressed, this twoclass classification problem is by no means trivial given the great variety of outdoor images. Our weather feature combines special cues after properly encoding them into feature vectors. They then work collaboratively in synergy under a...

article

Scale Adaptive Dictionary Learning

Cewu Lu, Jianping Shi, Jiaya Jia

IEEE Transactions on Image Processing > 2014 > 23 > 2 > 837 - 847

Dictionary learning has been widely used in many image processing tasks. In most of these methods, the number of basis vectors is either set by experience or coarsely evaluated empirically. In this paper, we propose a new scale adaptive dictionary learning framework, which jointly estimates suitable scales and corresponding atoms in an adaptive fashion according to the training data, without the need...

article

Contrast Preserving Decolorization with Perception-Based Quality Metrics

Cewu Lu, Li Xu, Jiaya Jia

International Journal of Computer Vision > 2014 > 110 > 2 > 222-239

Converting color images into grayscale ones suffer from information loss. In the meantime, it is one fundamental tool indispensable for single channel image processing, digital printing, and monotone e-ink display. In this paper, we propose an optimization framework aiming at maximally preserving color contrast. Our main contribution is threefold. First, we employ a bimodal objective function to alleviate...

chapter

Abnormal Event Detection at 150 FPS in MATLAB

Cewu Lu, Jianping Shi, Jiaya Jia

2013 IEEE International Conference on Computer Vision > 2720 - 2727

2013 IEEE International Conference on Computer Vision (ICCV)

Speedy abnormal event detection meets the growing demand to process an enormous number of surveillance videos. Based on inherent redundancy of video structures, we propose an efficient sparse combination learning framework. It achieves decent performance in the detection phase without compromising result quality. The short running time is guaranteed because the new method effectively turns the original...

Publication date

Set your own date range

Publication type

book (14)
article (10)

Keywords

DICTIONARY LEARNING (3)
FEATURE EXTRACTION (3)
OBJECT DETECTION (3)
CAMERAS (2)
CLOUDS (2)
COMPUTER SCIENCE (2)
DETECTORS (2)
DICTIONARIES (2)
IMAGE CLASSIFICATION (2)
IMAGE COLOR ANALYSIS (2)
METEOROLOGY (2)
OPTIMIZATION (2)
PROPOSALS (2)
TRAINING (2)
VISUALIZATION (2)
ABNORMAL EVENT (1)
ABNORMAL EVENT DETECTION (1)
ACTION RECOGNITION (1)
ADAPTATION MODELS (1)
ALGORITHM DESIGN AND ANALYSIS (1)
ANALYTICAL MODELS (1)
ATTRIBUTE RECOGNITION (1)
BAYES METHODS (1)
BINARY FEATURE (1)
BRIGHTNESS (1)
BUILDINGS (1)
CLASSIFICATION (1)
CLUSTERING (1)
CLUTTER SUPPRESSION (1)
COLOR (1)
COLOR2GRAY (1)
COMPUTATIONAL MODELING (1)
COMPUTER VISION (1)
CONCURRENT COMPUTING (1)
CONTRAST PRESERVATION (1)
CONVERSION (1)
CROWD VIDEO SURVEILLANCE (1)
DECOLORIZATION (1)
DEEP LEARNING (1)
DEPTH (1)
ENCODING (1)
ESTIMATION (1)
EVENT DETECTION (1)
FEATURE (1)
FIRST-PERSON VISION AND WEARABLE CAMERA (1)
FREQUENCY SYNCHRONIZATION (1)
GENERATORS (1)
GRAY-SCALE (1)
GROUND PENETRATING RADAR (GPR) (1)
HUMANS (1)
IMAGE FORMAT (1)
IMAGE PROCESSING (1)
IMAGE RECOGNITION (1)
IMAGE RESTORATION (1)
INFORMATION FUSION (1)
MAXIMUM LIKELIHOOD (ML) (1)
MULTI-CLASS WEATHER RECOGNITION (1)
NEURAL NETWORKS (1)
OBJECT DISCOVERY (1)
ONLINE LEARNING (1)
ORTHOGONAL FREQUENCY DIVISION MULTIPLEXING (OFDM) (1)
PERCEPTUAL-BASED (1)
PIPELINES (1)
POLYNOMIALS (1)
POSE ESTIMATION (1)
QUALITY METRICS (1)
REAL-TIME (1)
REALTIME DETECTION (1)
ROBUST STATISTICS (1)
ROBUSTNESS (1)
SAMPLING (1)
SCENE (1)
SCENE CLASSIFICATION (1)
SCENE UNDERSTANDING (1)
SPARSE CODING (1)
SPARSE REPRESENTATION (1)
STATIONARY CROWD ANALYSIS (1)
STATIONARY-TIME ESTIMATION (1)
STATISTICAL APPROXIMATION (1)
STRUCTURE SVM (1)
SUPPORT VECTOR MACHINES (1)
SURVEILLANCE VIDEO (1)
TENSILE STRESS (1)
THREE-DIMENSIONAL DISPLAYS (1)
TOOLS (1)
VECTORS (1)
VIDEO ANALYSIS (1)
VIDEOS (1)
WEATHER (1)
WEATHER UNDERSTANDING (1)
more

Data set

ieee (19)
Springer (4)
Elsevier (1)

INFONA - science communication portal

Search results for: Cewu Lu

Fast Abnormal Event Detection

Two-Class Weather Classification

RMPE: Regional Multi-person Pose Estimation

Online Video Object Detection Using Association LSTM

RSCM: Region Selection and Concurrency Model for Multi-Class Weather Recognition

$L_0$ Regularized Stationary-Time Estimation for Crowd Analysis

Improving object recognition with the ℓ-channel

Personal object discovery in first-person videos

Box Aggregation for Proposal Decimation: Last Mile of Object Detection

Square Localization for Efficient and Accurate Object Detection

Contour Box: Rejecting Object Proposals without Explicit Closed Contours

Deep LAC: Deep localization, alignment and classification for fine-grained recognition

Complexity-adaptive distance metric for object proposals generation

Learning Important Spatial Pooling Regions for Scene Classification

L0 Regularized Stationary Time Estimation for Crowd Group Analysis

Range-Sample Depth Feature for Action Recognition

Two-Class Weather Classification

Scale Adaptive Dictionary Learning

Contrast Preserving Decolorization with Perception-Based Quality Metrics

Abnormal Event Detection at 150 FPS in MATLAB

Filter options

Publication date

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Cewu Lu

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options