Deep Learning, Computer Vision, PyTorch, OpenCV, and more
Top Cited Papers: CVPR 2015
Longuet-Higgins Prize(Test-of-Time)
2015
“Histograms of oriented gradients for human detection”
N. Dalal, B. Triggs
Best Paper Award
2015
“DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time”
R. A. Newcombe, D. Fox, S. M. Seitz
Honorable Mention
2015
“Efficient Globally Optimal Consensus Maximisation with Tree Search”
T.-J. Chin, P. Purkait, A. Eriksson, D. Suter
2015
“Fully Convolutional Networks for Semantic Segmentation”
J. Long, E. Shelhamer, T. Darrell
2015
“Picture: A Probabilistic Programming Language for Scene Perception”
T. D. Kulkarni, P. Kohli, J. B. Tenenbaum, V. Mansinghka
Best Student Paper Award
2015
“Category-Specific Object Reconstruction from a Single Image”
A. Kar, S. Tulsiani, J. Carreira, J. Malik
Curated Papers:
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
Single image super-resolution from transformed self-exemplars
Self-similarity based super-resolution (SR) algorithms are able to produce visually pleasing results without extensive training on external databases. Such algorithms exploit the statistical prior that patches in a natural image tend to recur within and across scales of the same image. However, the internal dictionary obtained from the given image may not always be sufficiently expressive to cover the textural appearance variations in the scene. In this paper, we extend self-similarity based SR to overcome this drawback. We expand the internal patch search space by allowing geometric variations. We do so by explicitly localizing planes in the scene and using the detected perspective geometry to guide the patch search process. We also incorporate additional affine transformations to accommodate local shape variations. We propose a compositional model to simultaneously handle both types of transformations. We extensively evaluate the performance in both urban and natural scenes. Even without using any external training databases, we achieve significantly superior results on urban scenes, while maintaining comparable performance on natural scenes as other state-of-the-art SR algorithms.
Learning to compare image patches via convolutional neural networks
In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this task. We show that such an approach can significantly outperform the state-of-the-art on several problems and benchmark datasets.
FaceNet: A unified embedding for face recognition and clustering Florian Schroff;Dmitry Kalenichenko;James Philbin Publication Year: 2015,Page(s):815 – 823 Cited by: Papers (2780) | Patents (66)
Long-term recurrent convolutional networks for visual recognition and description Jeff Donahue;Lisa Anne Hendricks;Sergio Guadarrama;Marcus Rohrbach;Subhashini Venugopalan;Trevor Darrell;Kate Saenko Publication Year: 2015,Page(s):2625 – 2634 Cited by: Papers (1332) | Patents (24)
Show and tell: A neural image caption generator Oriol Vinyals;Alexander Toshev;Samy Bengio;Dumitru Erhan Publication Year: 2015,Page(s):3156 – 3164 Cited by: Papers (1314) | Patents (15)
Deep visual-semantic alignments for generating image descriptions Andrej Karpathy;Li Fei-Fei Publication Year: 2015,Page(s):3128 – 3137 Cited by: Papers (1166) | Patents (19)
Person re-identification by Local Maximal Occurrence representation and metric learning Shengcai Liao;Yang Hu;Xiangyu Zhu;Stan Z. Li Publication Year: 2015,Page(s):2197 – 2206 Cited by: Papers (850) | Patents (2)
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images Anh Nguyen;Jason Yosinski;Jeff Clune Publication Year: 2015,Page(s):427 – 436 Cited by: Papers (576) | Patents (4)
An improved deep learning architecture for person re-identification Ejaz Ahmed;Michael Jones;Tim K. Marks Publication Year: 2015,Page(s):3908 – 3916 Cited by: Papers (560) | Patents (2)
Object scene flow for autonomous vehicles Moritz Menze;Andreas Geiger Publication Year: 2015,Page(s):3061 – 3070 Cited by: Papers (547) | Patents (2)
Understanding deep image representations by inverting them Aravindh Mahendran;Andrea Vedaldi Publication Year: 2015,Page(s):5188 – 5196 Cited by: Papers (421) | Patents (4)
From captions to visual concepts and back Hao Fang;Saurabh Gupta;Forrest Iandola;Rupesh K. Srivastava;Li Deng;Piotr Dollár;Jianfeng Gao;Xiaodong He;Margaret Mitchell;John C. Platt;C. Lawrence Zitnick;Geoffrey Zweig Publication Year: 2015,Page(s):1473 – 1482 Cited by: Papers (416) | Patents (8)
Saliency detection by multi-context deep learning Rui Zhao;Wanli Ouyang;Hongsheng Li;Xiaogang Wang Publication Year: 2015,Page(s):1265 – 1274 Cited by: Papers (400) | Patents (3)
Beyond short snippets: Deep networks for video classification Joe Yue-Hei Ng;Matthew Hausknecht;Sudheendra Vijayanarasimhan;Oriol Vinyals;Rajat Monga;George Toderici Publication Year: 2015,Page(s):4694 – 4702 Cited by: Papers (362) | Patents (2)
SUN RGB-D: A RGB-D scene understanding benchmark suite Shuran Song;Samuel P. Lichtenberg;Jianxiong Xiao Publication Year: 2015,Page(s):567 – 576 Cited by: Papers (359) | Patents (5)
Deeply learned face representations are sparse, selective, and robust Yi Sun;Xiaogang Wang;Xiaoou Tang Publication Year: 2015,Page(s):2892 – 2900 Cited by: Papers (354)
Is object localization for free? – Weakly-supervised learning with convolutional neural networks Maxime Oquab;Léon Bottou;Ivan Laptev;Josef Sivic Publication Year: 2015,Page(s):685 – 694 Cited by: Papers (341) | Patents (5)
Cross-scene crowd counting via deep convolutional neural networks Cong Zhang;Hongsheng Li;Xiaogang Wang;Xiaokang Yang Publication Year: 2015,Page(s):833 – 841 Cited by: Papers (335) | Patents (4)
ActivityNet: A large-scale video benchmark for human activity understanding Fabian Caba Heilbron;Victor Escorcia;Bernard Ghanem;Juan Carlos Niebles Publication Year: 2015,Page(s):961 – 970 Cited by: Papers (328)
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking Zhibin Hong;Zhe Chen;Chaohui Wang;Xue Mei;Danil Prokhorov;Dacheng Tao Publication Year: 2015,Page(s):749 – 758 Cited by: Papers (324)
Convolutional neural networks at constrained time cost Kaiming He;Jian Sun Publication Year: 2015,Page(s):5353 – 5360 Cited by: Papers (317)
Deep convolutional neural fields for depth estimation from a single image Fayao Liu;Chunhua Shen;Guosheng Lin Publication Year: 2015,Page(s):5162 – 5170 Cited by: Papers (317) | Patents (1)
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time Richard A. Newcombe;Dieter Fox;Steven M. Seitz Publication Year: 2015,Page(s):343 – 352 Cited by: Papers (315) | Patents (6)
Simultaneous feature learning and hash coding with deep neural networks Hanjiang Lai;Yan Pan;Ye Liu;Shuicheng Yan Publication Year: 2015,Page(s):3270 – 3278 Cited by: Papers (315) | Patents (13)
Deep networks for saliency detection via local estimation and global search Lijun Wang;Huchuan Lu;Xiang Ruan;Ming-Hsuan Yang Publication Year: 2015,Page(s):3183 – 3192 Cited by: Papers (277) | Patents (4)
Recurrent convolutional neural network for object recognition Ming Liang;Xiaolin Hu Publication Year: 2015,Page(s):3367 – 3375 Cited by: Papers (268) | Patents (2)
Fast and accurate image upscaling with super-resolution forests Samuel Schulter;Christian Leistner;Horst Bischof Publication Year: 2015,Page(s):3791 – 3799 Cited by: Papers (264) | Patents (3)
A large-scale car dataset for fine-grained categorization and verification Linjie Yang;Ping Luo;Chen Change Loy;Xiaoou Tang Publication Year: 2015,Page(s):3973 – 3981 Cited by: Papers (262) | Patents (2)
Deep filter banks for texture recognition and segmentation Mircea Cimpoi;Subhransu Maji;Andrea Vedaldi Publication Year: 2015,Page(s):3828 – 3836 Cited by: Papers (262) | Patents (2)
Learning to rank in person re-identification with metric ensembles Sakrapee Paisitkriangkrai;Chunhua Shen;Anton van den Hengel Publication Year: 2015,Page(s):1846 – 1855 Cited by: Papers (229)
Accurate depth map estimation from a lenslet light field camera Hae-Gon Jeon;Jaesik Park;Gyeongmin Choe;Jinsun Park;Yunsu Bok;Yu-Wing Tai;In So Kweon Publication Year: 2015,Page(s):1547 – 1555 Cited by: Papers (212) | Patents (2)
We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept All”, you consent to the use of ALL the cookies. However, you may visit "Cookie Settings" to provide a controlled consent.
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.
