%PDF-1.3 1 0 obj << /Kids [ 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R ] /Type /Pages /Count 9 >> endobj 2 0 obj << /Subject (Neural Information Processing Systems http\072\057\057nips\056cc\057) /Publisher (Curran Associates\054 Inc\056) /Language (en\055US) /Created (2015) /Description-Abstract (Scene labeling is a challenging computer vision task\056 It requires the use of both local discriminative features and global context information\056 We adopt a deep recurrent convolutional neural network \050RCNN\051 for this task\054 which is originally proposed for object recognition\056 Different from traditional convolutional neural networks \050CNN\051\054 this model has intra\055layer recurrent connections in the convolutional layers\056 Therefore each convolutional layer becomes a two\055dimensional recurrent neural network\056 The units receive constant feed\055forward inputs from the previous layer and recurrent inputs from their neighborhoods\056 While recurrent iterations proceed\054 the region of context captured by each unit expands\056 In this way\054 feature extraction and context modulation are seamlessly integrated\054 which is different from typical methods that entail separate modules for the two steps\056 To further utilize the context\054 a multi\055scale RCNN is proposed\056 Over two benchmark datasets\054 Standford Background and Sift Flow\054 the model outperforms many state\055of\055the\055art models in accuracy and efficiency\056) /Producer (PyPDF2) /Title (Convolutional Neural Networks with Intra\055Layer Recurrent Connections for Scene Labeling) /Date (2015) /ModDate (D\07220160216125206\05508\04700\047) /Published (2015) /Type (Conference Proceedings) /firstpage (937) /Book (Advances in Neural Information Processing Systems 28) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /EventType (Poster) /Author (Ming Liang\054 Xiaolin Hu\054 Bo Zhang) /lastpage (945) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Resources 14 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 32 0 R 33 0 R 34 0 R 35 0 R 36 0 R 37 0 R 38 0 R 39 0 R 40 0 R 41 0 R 42 0 R 43 0 R 44 0 R 45 0 R 46 0 R 47 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 48 0 R /Parent 1 0 R /Resources 49 0 R /Group 84 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 86 0 R 87 0 R 88 0 R 89 0 R 90 0 R 91 0 R 92 0 R 93 0 R 94 0 R 95 0 R 96 0 R 97 0 R 98 0 R 99 0 R 100 0 R 101 0 R 102 0 R 103 0 R 104 0 R 105 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 106 0 R /Parent 1 0 R /Resources 107 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 148 0 R 149 0 R 150 0 R 151 0 R 152 0 R 153 0 R 154 0 R 155 0 R 156 0 R 157 0 R 158 0 R 159 0 R 160 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 161 0 R /Parent 1 0 R /Resources 162 0 R /Group 172 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 174 0 R 175 0 R 176 0 R 177 0 R 178 0 R 179 0 R 180 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 181 0 R /Parent 1 0 R /Resources 182 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 183 0 R 184 0 R 185 0 R 186 0 R 187 0 R 188 0 R 189 0 R 190 0 R 191 0 R 192 0 R 193 0 R 194 0 R 195 0 R 196 0 R 197 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 198 0 R /Parent 1 0 R /Resources 199 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 208 0 R 209 0 R 210 0 R 211 0 R 212 0 R 213 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 214 0 R /Parent 1 0 R /Resources 215 0 R /Group 222 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 224 0 R 225 0 R 226 0 R 227 0 R 228 0 R 229 0 R 230 0 R 231 0 R 232 0 R 233 0 R 234 0 R 235 0 R 236 0 R 237 0 R 238 0 R 239 0 R 240 0 R 241 0 R 242 0 R 243 0 R 244 0 R 245 0 R 246 0 R 247 0 R 248 0 R 249 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 250 0 R /Parent 1 0 R /Resources 251 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 252 0 R 253 0 R 254 0 R 255 0 R 256 0 R 257 0 R 258 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 259 0 R /Parent 1 0 R /Type /Page /Resources 260 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 2914 /Filter /FlateDecode >> stream xڕYK ϯQS5z]{u9xlMmQ/6I ;N^..Ћ(,,2MCbRf^E ;_%A{EqeeX{O۾߇Q4S.NCx|%g˔3yk+.^yVz8eQu5 }Ty+HtB>NA|ty:t'd~1032s0%兖dkOۀnYi,( /- )sVo(,CFO0 Mτ]Q{Vi-H8OJ,UlaKk*1j
ٛAn3z)sj5Tyy|8