CVPR 2016 accepted papers on Architectures and efficiency
44 of the 643 papers accepted at CVPR 2016 (6.8%) are on Architectures and efficiency. They fall into 4 topics.
See CVPR 2016 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN design · 26 papers
- Rethinking the Inception Architecture for Computer Vision (31,549 citations)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (7,779 citations)
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (2,686 citations)
- Quantized Convolutional Neural Networks for Mobile Devices (1,258 citations)
- Fast Algorithms for Convolutional Neural Networks (943 citations)
- Eye Tracking for Everyone (934 citations)
- Efficient Deep Learning for Stereo Matching (811 citations)
- Recursive Recurrent Nets With Attention Modeling for OCR in the Wild (497 citations)
- Shallow and Deep Convolutional Networks for Saliency Prediction (443 citations)
- Fast ConvNets Using Group-Wise Brain Damage (399 citations)
- Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction (360 citations)
- Monocular Depth Estimation Using Neural Regression Forest (353 citations)
and 14 more in the interactive map.
RNNs and normalization · 16 papers
- Social LSTM: Human Trajectory Prediction in Crowded Spaces (3,627 citations)
- Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment (367 citations)
- FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters (298 citations)
- D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images (229 citations)
- Analyzing Classifiers: Fisher Vectors and Deep Neural Networks (209 citations)
- Efficient Indexing of Billion-Scale Datasets of Deep Descriptors (191 citations)
- Sparsifying Neural Network Connections for Face Recognition (156 citations)
- Efficient Training of Very Deep Neural Networks for Supervised Hashing (107 citations)
- Bottom-Up and Top-Down Reasoning With Hierarchical Rectified Gaussians (95 citations)
- PatchBatch: A Batch Augmented Loss for Optical Flow (90 citations)
- Efficient Large-Scale Approximate Nearest Neighbor Search on the GPU (59 citations)
- TenSR: Multi-Dimensional Tensor Sparse Representation (44 citations)
and 4 more in the interactive map.
Neural architecture search · 1 paper
- Improved Hamming Distance Search Using Variable Length Substrings (30 citations)
Attention and transformers · 1 paper
- Learning to Match Aerial Images With Deep Attentive Architectures (87 citations)
