Top Cited Papers: CVPR 2013

Curated Papers:

Fast Image Super-Resolution Based on In-Place Example Regression

We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches- learning from an external database and learning from self-examples. Our in-place self-similarity refines the recently proposed local self-similarity by proving that a patch in the upper scale image have good matches around its origin location in the lower scale image. Based on the in-place examples, a first-order approximation of the nonlinear mapping function from low-to high-resolution image patches is learned. Extensive experiments on benchmark and real-world images demonstrate that our algorithm can produce natural-looking results with sharp edges and preserved fine details, while the current state-of-the-art algorithms are prone to visual artifacts. Furthermore, our model can easily extend to deal with noise by combining the regression results on multiple in-place examples for robust estimation. The algorithm runs fast and is particularly useful for practical applications, where the input images typically contain diverse textures and they are potentially contaminated by noise or compression artifacts.

Learning without Human Scores for Blind Image Quality Assessment

General purpose blind image quality assessment (BIQA) has been recently attracting significant attention in the fields of image processing, vision and machine learning. State-of-the-art BIQA methods usually learn to evaluate the image quality by regression from human subjective scores of the training samples. However, these methods need a large number of human scored images for training, and lack an explicit explanation of how the image quality is affected by image local features. An interesting question is then: can we learn for effective BIQA without using human scored images? This paper makes a good effort to answer this question. We partition the distorted images into overlapped patches, and use a percentile pooling strategy to estimate the local quality of each patch. Then a quality-aware clustering (QAC) method is proposed to learn a set of centroids on each quality level. These centroids are then used as a codebook to infer the quality of each patch in a given image, and subsequently a perceptual quality score of the whole image can be obtained. The proposed QAC based BIQA method is simple yet effective. It not only has comparable accuracy to those methods using human scored images in learning, but also has merits such as high linearity to human perception of image quality, real-time implementation and availability of image local quality map.

All About VLAD

The objective of this paper is large scale object instance retrieval, given a query image. A starting point of such systems is feature detection and description, for example using SIFT. The focus of this paper, however, is towards very large scale retrieval where, due to storage requirements, very compact image descriptors are required and no information about the original SIFT descriptors can be accessed directly at run time. We start from VLAD, the state-of-the art compact descriptor introduced by Jegou et al. for this purpose, and make three novel contributions: first, we show that a simple change to the normalization method significantly improves retrieval performance, second, we show that vocabulary adaptation can substantially alleviate problems caused when images are added to the dataset after initial vocabulary learning. These two methods set a new state-of-the-art over all benchmarks investigated here for both mid-dimensional (20k-D to 30k-D) and small (128-D) descriptors. Our third contribution is a multiple spatial VLAD representation, MultiVLAD, that allows the retrieval and localization of objects that only extend over a small part of an image (again without requiring use of the original image SIFT descriptors).

What Makes a Patch Distinct?

What makes an object salient? Most previous work assert that distinctness is the dominating factor. The difference between the various algorithms is in the way they compute distinctness. Some focus on the patterns, others on the colors, and several add high-level cues and priors. We propose a simple, yet powerful, algorithm that integrates these three factors. Our key contribution is a novel and fast approach to compute pattern distinctness. We rely on the inner statistics of the patches in the image for identifying unique patterns. We provide an extensive evaluation and show that our approach outperforms all state-of-the-art methods on the five most commonly-used datasets.

Hierarchical Saliency Detection

When dealing with objects with complex structures, saliency detection confronts a critical problem – namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns. This issue is common in natural images and forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. The final saliency map is produced in a hierarchical model. Different from varying patch sizes or downsizing images, our scale-based region handling is by finding saliency values optimally in a tree model. Our approach improves saliency detection on many images that cannot be handled well traditionally. A new dataset is also constructed.

Full list:

  1. Online Object Tracking: A Benchmark Yi Wu;Jongwoo Lim;Ming-Hsuan Yang Publication Year: 2013,Page(s):2411 – 2418 Cited by: Papers (1822) | Patents (3)
  2. Supervised Descent Method and Its Applications to Face Alignment Xuehan Xiong;Fernando De la Torre Publication Year: 2013,Page(s):532 – 539 Cited by: Papers (1052) | Patents (18)
  3. Saliency Detection via Graph-Based Manifold Ranking Chuan Yang;Lihe Zhang;Huchuan Lu;Xiang Ruan;Ming-Hsuan Yang Publication Year: 2013,Page(s):3166 – 3173 Cited by: Papers (1001) | Patents (2)
  4. Hierarchical Saliency Detection Qiong Yan;Li Xu;Jianping Shi;Jiaya Jia Publication Year: 2013,Page(s):1155 – 1162 Cited by: Papers (732) | Patents (3)
  5. Deep Convolutional Network Cascade for Facial Point Detection Yi Sun;Xiaogang Wang;Xiaoou Tang Publication Year: 2013,Page(s):3476 – 3483 Cited by: Papers (632) | Patents (9)
  6. Unsupervised Salience Learning for Person Re-identification Rui Zhao;Wanli Ouyang;Xiaogang Wang Publication Year: 2013,Page(s):3586 – 3593 Cited by: Papers (578) | Patents (3)
  7. Salient Object Detection: A Discriminative Regional Feature Integration Approach Huaizu Jiang;Jingdong Wang;Zejian Yuan;Yang Wu;Nanning Zheng;Shipeng Li Publication Year: 2013,Page(s):2083 – 2090 Cited by: Papers (553)
  8. HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Omar Oreifej;Zicheng Liu Publication Year: 2013,Page(s):716 – 723 Cited by: Papers (487)
  9. Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification Dong Chen;Xudong Cao;Fang Wen;Jian Sun Publication Year: 2013,Page(s):3025 – 3032 Cited by: Papers (364) | Patents (9)
  10. Pedestrian Detection with Unsupervised Multi-stage Feature Learning Pierre Sermanet;Koray Kavukcuoglu;Soumith Chintala;Yann Lecun Publication Year: 2013,Page(s):3626 – 3633 Cited by: Papers (363) | Patents (7)
  11. Local Fisher Discriminant Analysis for Pedestrian Re-identification Sateesh Pedagadi;James Orwell;Sergio Velastin;Boghos Boghossian Publication Year: 2013,Page(s):3318 – 3325 Cited by: Papers (325)
  12. Unnatural L0 Sparse Representation for Natural Image Deblurring Li Xu;Shicheng Zheng;Jiaya Jia Publication Year: 2013,Page(s):1107 – 1114 Cited by: Papers (317)
  13. SLAM++: Simultaneous Localisation and Mapping at the Level of Objects Renato F. Salas-Moreno;Richard A. Newcombe;Hauke Strasdat;Paul H.J. Kelly;Andrew J. Davison Publication Year: 2013,Page(s):1352 – 1359 Cited by: Papers (313) | Patents (4)
  14. What Makes a Patch Distinct? Ran Margolin;Ayellet Tal;Lihi Zelnik-Manor Publication Year: 2013,Page(s):1139 – 1146 Cited by: Papers (300) | Patents (3)
  15. All About VLAD Relja Arandjelovic;Andrew Zisserman Publication Year: 2013,Page(s):1578 – 1585 Cited by: Papers (296) | Patents (7)
  16. Robust Discriminative Response Map Fitting with Constrained Local Models Akshay Asthana;Stefanos Zafeiriou;Shiyang Cheng;Maja Pantic Publication Year: 2013,Page(s):3444 – 3451 Cited by: Papers (291) | Patents (1)
  17. Learning Locally-Adaptive Decision Functions for Person Verification Zhen Li;Shiyu Chang;Feng Liang;Thomas S. Huang;Liangliang Cao;John R. Smith Publication Year: 2013,Page(s):3610 – 3617 Cited by: Papers (287)
  18. Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras Donald G. Dansereau;Oscar Pizarro;Stefan B. Williams Publication Year: 2013,Page(s):1027 – 1034 Cited by: Papers (280) | Patents (12)
  19. Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images Saurabh Gupta;Pablo Arbeláez;Jitendra Malik Publication Year: 2013,Page(s):564 – 571 Cited by: Papers (273) | Patents (38)
  20. Locally Aligned Feature Transforms across Views Wei Li;Xiaogang Wang Publication Year: 2013,Page(s):3594 – 3601 Cited by: Papers (270)
  21. Multi-source Multi-scale Counting in Extremely Dense Crowd Images Haroon Idrees;Imran Saleemi;Cody Seibert;Mubarak Shah Publication Year: 2013,Page(s):2547 – 2554 Cited by: Papers (258)
  22. Blocks That Shout: Distinctive Parts for Scene Classification Mayank Juneja;Andrea Vedaldi;C.V. Jawahar;Andrew Zisserman Publication Year: 2013,Page(s):923 – 930 Cited by: Papers (246) | Patents (4)
  23. Story-Driven Summarization for Egocentric Video Zheng Lu;Kristen Grauman Publication Year: 2013,Page(s):2714 – 2721 Cited by: Papers (243) | Patents (11)
  24. Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera Lu Xia;J.K. Aggarwal Publication Year: 2013,Page(s):2834 – 2841 Cited by: Papers (233)
  25. Better Exploiting Motion for Better Action Recognition Mihir Jain;Hervé Jégou;Patrick Bouthemy Publication Year: 2013,Page(s):2555 – 2562 Cited by: Papers (220) | Patents (1)
  26. Label-Embedding for Attribute-Based Classification Zeynep Akata;Florent Perronnin;Zaid Harchaoui;Cordelia Schmid Publication Year: 2013,Page(s):819 – 826 Cited by: Papers (219) | Patents (1)
  27. Cumulative Attribute Space for Age and Crowd Density Estimation Ke Chen;Shaogang Gong;Tao Xiang;Chen Change Loy Publication Year: 2013,Page(s):2467 – 2474 Cited by: Papers (214)
  28. Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images Jamie Shotton;Ben Glocker;Christopher Zach;Shahram Izadi;Antonio Criminisi;Andrew Fitzgibbon Publication Year: 2013,Page(s):2930 – 2937 Cited by: Papers (214) | Patents (6)
  29. Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection Joseph J. Lim;C. Lawrence Zitnick;Piotr Dollár Publication Year: 2013,Page(s):3158 – 3165 Cited by: Papers (213) | Patents (2)
  30. K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes Kaiming He;Fang Wen;Jian Sun Publication Year: 2013,Page(s):2938 – 2945 Cited by: Papers (207) | Patents (1)
  31. Learning without Human Scores for Blind Image Quality Assessment Wufeng Xue;Lei Zhang;Xuanqin Mou Publication Year: 2013,Page(s):995 – 1002 Cited by: Papers (205)
  32. Voxel Cloud Connectivity Segmentation – Supervoxels for Point Clouds Jeremie Papon;Alexey Abramov;Markus Schoeler;Florentin Wörgötter Publication Year: 2013,Page(s):2027 – 2034 Cited by: Papers (196) | Patents (1)
  33. Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions Dong Zhang;Omar Javed;Mubarak Shah Publication Year: 2013,Page(s):628 – 635 Cited by: Papers (195) | Patents (4)
  34. Detecting Pulse from Head Motions in Video Guha Balakrishnan;Fredo Durand;John Guttag Publication Year: 2013,Page(s):3430 – 3437 Cited by: Papers (186) | Patents (77)
  35. Unsupervised Joint Object Discovery and Segmentation in Internet Images Michael Rubinstein;Armand Joulin;Johannes Kopf;Ce Liu Publication Year: 2013,Page(s):1939 – 1946 Cited by: Papers (184) | Patents (3)
  36. POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation Thomas Berg;Peter N. Belhumeur Publication Year: 2013,Page(s):955 – 962 Cited by: Papers (183)
  37. Visual Tracking via Locality Sensitive Histograms Shengfeng He;Qingxiong Yang;Rynson W.H. Lau;Jiang Wang;Ming-Hsuan Yang Publication Year: 2013,Page(s):2427 – 2434 Cited by: Papers (182) | Patents (2)
  38. MODEC: Multimodal Decomposable Models for Human Pose Estimation Ben Sapp;Ben Taskar Publication Year: 2013,Page(s):3674 – 3681 Cited by: Papers (177)
  39. Least Soft-Threshold Squares Tracking Dong Wang;Huchuan Lu;Ming-Hsuan Yang Publication Year: 2013,Page(s):2371 – 2378 Cited by: Papers (174)
  40. An Approach to Pose-Based Action Recognition Chunyu Wang;Yizhou Wang;Alan L. Yuille Publication Year: 2013,Page(s):915 – 922 Cited by: Papers (170) | Patents (2)
  41. Fast Image Super-Resolution Based on In-Place Example Regression Jianchao Yang;Zhe Lin;Scott Cohen Publication Year: 2013,Page(s):1059 – 1066 Cited by: Papers (167) | Patents (10)
  42. Cartesian K-Means Mohammad Norouzi;David J. Fleet Publication Year: 2013,Page(s):3017 – 3024 Cited by: Papers (158) | Patents (1)
  43. Learning Structured Low-Rank Representations for Image Classification Yangmuzi Zhang;Zhuolin Jiang;Larry S. Davis Publication Year: 2013,Page(s):676 – 683 Cited by: Papers (158) | Patents (1)
  44. Seeking the Strongest Rigid Detector Rodrigo Benenson;Markus Mathias;Tinne Tuytelaars;Luc Van Gool Publication Year: 2013,Page(s):3666 – 3673 Cited by: Papers (152) | Patents (1)
  45. Fast, Accurate Detection of 100,000 Object Classes on a Single Machine Thomas Dean;Mark A. Ruzon;Mark Segal;Jonathon Shlens;Sudheendra Vijayanarasimhan;Jay Yagnik Publication Year: 2013,Page(s):1814 – 1821 Cited by: Papers (148) | Patents (6)
  46. Deformable Spatial Pyramid Matching for Fast Dense Correspondences Jaechul Kim;Ce Liu;Fei Sha;Kristen Grauman Publication Year: 2013,Page(s):2307 – 2314 Cited by: Papers (147) | Patents (1)
  47. As-Projective-As-Possible Image Stitching with Moving DLT Julio Zaragoza;Tat-Jun Chin;Michael S. Brown;David Suter Publication Year: 2013,Page(s):2339 – 2346 Cited by: Papers (146)
  48. Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow Asad A. Butt;Robert T. Collins Publication Year: 2013,Page(s):1846 – 1853 Cited by: Papers (146)
  49. Fine-Grained Crowdsourcing for Fine-Grained Recognition Jia Deng;Jonathan Krause;Li Fei-Fei Publication Year: 2013,Page(s):580 – 587 Cited by: Papers (143) | Patents (1)
  50. Large-Scale Video Summarization Using Web-Image Priors Aditya Khosla;Raffay Hamid;Chih-Jen Lin;Neel Sundaresan Publication Year: 2013,Page(s):2698 – 2705 Cited by: Papers (143) | Patents (1)

https://ieeexplore.ieee.org/xpl/conhome/6596161/proceeding?rowsPerPage=50&sortType=paper-citations

Leave a Reply Cancel reply