CVPR 2016

Deep Residual Learning for Image Recognition

CVPR 2016 tensorflow/models

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

IMAGE CLASSIFICATION OBJECT DETECTION

Rethinking the Inception Architecture for Computer Vision

CVPR 2016 tensorflow/models

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.

IMAGE CLASSIFICATION

Convolutional Pose Machines

CVPR 2016 CMU-Perceptual-Computing-Lab/openpose

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models.

POSE ESTIMATION STRUCTURED PREDICTION

You Only Look Once: Unified, Real-Time Object Detection

CVPR 2016 thtrieu/darkflow

A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.

REAL-TIME OBJECT DETECTION

Learning Deep Features for Discriminative Localization

CVPR 2016 tensorpack/tensorpack

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.

OBJECT LOCALIZATION

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

CVPR 2016 awentzonline/image-analogies

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.

IMAGE GENERATION TEXTURE SYNTHESIS

Fast Algorithms for Convolutional Neural Networks

CVPR 2016 XiaoMi/mace

The algorithms compute minimal complexity convolution over small tiles, which makes them fast with small filters and small batch sizes.

PEDESTRIAN DETECTION SELF-DRIVING CARS

Structure-From-Motion Revisited

CVPR 2016 colmap/colmap

Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections.

3D RECONSTRUCTION

End-to-end people detection in crowded scenes

CVPR 2016 Russell91/TensorBox

Current people detectors operate either by scanning an image in a sliding window fashion or by classifying a discrete set of proposals.