conftrace_
← Deep Learning
Deep Learning ›

Techniques

8,241 papers (36 classified directly here)

Subtopics

Model Architecture (4,354) Pretraining (2,483) Attention (1,111) Normalization (341) Attention Mechanism (150)

Papers per year

4
30
847
998
'10
'15
'20
'25

Papers (including subtopics)

Comparative Deep Learning of Hybrid Representations for Image Recommendations CVPR 2016
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters CVPR 2016
First Person Action Recognition Using Deep Learned Descriptors CVPR 2016
Actionness Estimation Using Hybrid Fully Convolutional Networks CVPR 2016
Inside-Outside Net: Detecting Objects in Context With Skip Pooling and Recurrent Neural Networks CVPR 2016
Semantic Object Parsing With Local-Global Long Short-Term Memory CVPR 2016
Learning to Match Aerial Images With Deep Attentive Architectures CVPR 2016
Attention to Scale: Scale-Aware Semantic Image Segmentation CVPR 2016
Visual Tracking Using Attention-Modulated Disintegration and Integration CVPR 2016
Image Captioning With Semantic Attention CVPR 2016
Gradual DropIn of Layers to Train Very Deep Neural Networks CVPR 2016
Deep SimNets CVPR 2016
Quantized Convolutional Neural Networks for Mobile Devices CVPR 2016
Sparsifying Neural Network Connections for Face Recognition CVPR 2016
Visual7W: Grounded Question Answering in Images CVPR 2016
Volumetric and Multi-View CNNs for Object Classification on 3D Data CVPR 2016
Recombinator Networks: Learning Coarse-To-Fine Feature Aggregation CVPR 2016
Dropout distillation ICML 2016
Multi-Bias Non-linear Activation in Deep Neural Networks ICML 2016
Convolutional Rectifier Networks as Generalized Tensor Decompositions ICML 2016
Unitary Evolution Recurrent Neural Networks ICML 2016
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks ICML 2016
Exploiting Cyclic Symmetry in Convolutional Neural Networks ICML 2016
Discrete Deep Feature Extraction: A Theory and New Architectures ICML 2016
Training Deep Neural Networks via Direct Loss Minimization ICML 2016