| DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs |
1207 |
| Places: A 10 Million Image Database for Scene Recognition |
155 |
| HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition |
129 |
| Direct Sparse Odometry |
121 |
| Long-Term Temporal Convolutions for Action Recognition |
105 |
| Multimodal Machine Learning: A Survey and Taxonomy |
104 |
| A Survey on Learning to Hash |
84 |
| SIFT Meets CNN: A Decade Survey of Instance Retrieval |
79 |
| Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning |
67 |
| Deeply Supervised Salient Object Detection with Short Connections |
66 |
| Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization |
65 |
| Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks |
59 |
| StackGAN plus plus : Realistic Image Synthesis with Stacked Generative Adversarial Networks |
58 |
| Learning without Forgetting |
56 |
| Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates |
55 |
| Saliency-Aware Video Object Segmentation |
55 |
| Binary Multi-View Clustering |
51 |
| A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping |
51 |
| Zero-Shot Learning-A Comprehensive Evaluation of the Good, the Bad and the Ugly |
48 |
| Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition |
47 |
| Person Re-Identification by Camera Correlation Aware Feature Augmentation |
46 |
| Fine-Tuning CNN Image Retrieval with No Human Annotation |
46 |
| Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks |
44 |
| Richer Convolutional Features for Edge Detection |
39 |
| What Do Different Evaluation Metrics Tell Us About Saliency Models? |
39 |
| Drawing and Recognizing Chinese Characters with Recurrent Neural Network |
38 |
| NetVLAD: CNN Architecture for Weakly Supervised Place Recognition |
37 |
| Deep Collaborative Embedding for Social Image Understanding |
37 |
| Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery |
36 |
| Beyond Sharing Weights for Deep Domain Adaptation |
34 |
| Image Captioning and Visual Question Answering Based on Attributes and External Knowledge |
33 |
| Context-Aware Local Binary Feature Learning for Face Recognition |
31 |
| Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks |
31 |
| Salient Object Detection with Recurrent Fully Convolutional Networks |
31 |
| Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans |
31 |
| Video Super-Resolution via Bidirectional Recurrent Convolutional Networks |
31 |
| Robust Visual Tracking via Hierarchical Convolutional Features |
30 |
| Learning a Deep Model for Human Action Recognition from Novel Viewpoints |
30 |
| Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition |
30 |
| Fast Supervised Discrete Hashing |
30 |
| 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection |
29 |
| Robust Online Matrix Factorization for Dynamic Background Subtraction |
29 |
| Denoising Prior Driven Deep Neural Network for Image Restoration |
28 |
| Subspace Clustering by Block Diagonal Representation |
27 |
| Person Re-Identification by Cross-View Multi-Level Dictionary Learning |
27 |
| Towards Reaching Human Performance in Pedestrian Detection |
27 |
| Face Recognition via Collaborative Representation: Its Discriminant Nature and Superposed Representation |
26 |
| Temporal Segment Networks for Action Recognition in Videos |
26 |
| w Bilinear Convolutional Neural Networks for Fine-Grained Visual Recognition |
26 |
| Learning Building Extraction in Aerial Scenes with Convolutional Networks |
26 |
