Create gh-pages branch via GitHub

index.html

@@ -96,6 +96,9 @@
 <h3>
 <a id="imagenet-classification" class="anchor" href="#imagenet-classification" aria-hidden="true"><span class="octicon octicon-link"></span></a>ImageNet Classification</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8451949/327b9566-2022-11e5-8b34-53b4a64c13ad.PNG" alt="classification">
+(from Krizhevsky, A., Sutskever, I. and Hinton, G. E, ImageNet Classification with Deep Convolutional Neural Networks NIPS 2012.)</p>
+
 <ul>
 <li>Microsoft (PReLu/Weight Initialization) <a href="http://arxiv.org/pdf/1502.01852v1">[Paper]</a>
 
@@ -133,6 +136,9 @@ NIPS 2012.</li>
 <h3>
 <a id="object-detection" class="anchor" href="#object-detection" aria-hidden="true"><span class="octicon octicon-link"></span></a>Object Detection</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452063/f76ba500-2022-11e5-8db1-2cd5d490e3b3.PNG" alt="object_detection">
+(from Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497)</p>
+
 <ul>
 <li>OverFeat, NYU <a href="http://arxiv.org/pdf/1311.2901v3">[Paper]</a>
 
@@ -225,6 +231,9 @@ NIPS 2012.</li>
 <h3>
 <a id="edge-detection" class="anchor" href="#edge-detection" aria-hidden="true"><span class="octicon octicon-link"></span></a>Edge Detection</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452371/93ca6f7e-2025-11e5-90f2-d428fd5ff7ac.PNG" alt="edge_detection">
+(from Gedas Bertasius, Jianbo Shi, Lorenzo Torresani, DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection, CVPR 2015.)</p>
+
 <ul>
 <li>Holistically-Nested Edge Detection <a href="http://arxiv.org/pdf/1504.06375v1">[Paper]</a>
 
@@ -249,6 +258,9 @@ NIPS 2012.</li>
 <h3>
 <a id="semantic-segmentation" class="anchor" href="#semantic-segmentation" aria-hidden="true"><span class="octicon octicon-link"></span></a>Semantic Segmentation</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452076/0ba8340c-2023-11e5-88bc-bebf4509b6bb.PNG" alt="semantic_segmantation">
+(from Jifeng Dai, Kaiming He, Jian Sun, BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation, arXiv:1503.01640)</p>
+
 <ul>
 <li>Learning Hierarchical Features for Scene Labeling <a href="http://yann.lecun.com/exdb/publis/pdf/farabet-icml-12.pdf">[Paper-ICML12]</a> <a href="http://yann.lecun.com/exdb/publis/pdf/farabet-pami-13.pdf">[Paper-PAMI13]</a>
 
@@ -280,6 +292,9 @@ NIPS 2012.</li>
 <h3>
 <a id="visual-attention-and-saliency" class="anchor" href="#visual-attention-and-saliency" aria-hidden="true"><span class="octicon octicon-link"></span></a>Visual Attention and Saliency</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452391/cdaa3c7e-2025-11e5-81be-ee5243fe9e7c.png" alt="saliency">
+(from Federico Perazzi, Philipp Krahenbuhl, Yael Pritch, Alexander Hornung, Saliency Filters: Contrast Based Filtering for Salient Region Detection, CVPR, 2012)</p>
+
 <ul>
 <li>Mr-CNN <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Liu_Predicting_Eye_Fixations_2015_CVPR_paper.pdf">[Paper]</a>
 
@@ -328,6 +343,9 @@ NIPS 2012.</li>
 <h3>
 <a id="understanding-cnn" class="anchor" href="#understanding-cnn" aria-hidden="true"><span class="octicon octicon-link"></span></a>Understanding CNN</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452083/1aaa0066-2023-11e5-800b-2248ead51584.PNG" alt="understanding">
+(from Aravindh Mahendran, Andrea Vedaldi, Understanding Deep Image Representations by Inverting Them, CVPR, 2015.)</p>
+
 <ul>
 <li>Equivariance and Equivalence of Representations <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Lenc_Understanding_Image_Representations_2015_CVPR_paper.pdf">[Paper]</a>
 
@@ -352,6 +370,9 @@ NIPS 2012.</li>
 <h3>
 <a id="image-captioning" class="anchor" href="#image-captioning" aria-hidden="true"><span class="octicon octicon-link"></span></a>Image Captioning</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452051/e8f81030-2022-11e5-85db-c68e7d8251ce.PNG" alt="image_captioning">
+(from Andrej Karpathy, Li Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Description, CVPR (2015).)</p>
+
 <ul>
 <li>Baidu / UCLA <a href="http://arxiv.org/pdf/1410.1090v1">[Paper]</a>
 
@@ -436,6 +457,9 @@ NIPS 2012.</li>
 <h3>
 <a id="question-answering" class="anchor" href="#question-answering" aria-hidden="true"><span class="octicon octicon-link"></span></a>Question Answering</h3>
 
+<p><img src="https://cloud.githubusercontent.com/assets/5226447/8452068/ffe7b1f6-2022-11e5-87ab-4f6d4696c220.PNG" alt="question_answering">
+(from Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh, VQA: Visual Question Answering, CVPR 2015 SUNw:Scene Understanding workshop)</p>
+
 <ul>
 <li>MSR / Virginia Tech. [<a href="http://www.visualqa.org/">Web</a>] [<a href="http://arxiv.org/pdf/1505.00468v1.pdf">Paper</a>]