ICCV 2017

Channel Pruning for Accelerating Very Deep Neural Networks

ICCV 2017 yihui-he/channel-pruning

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction.

DSOD: Learning Deeply Supervised Object Detectors from Scratch

ICCV 2017 szq0214/DSOD

State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.

OBJECT DETECTION

Video Frame Interpolation via Adaptive Separable Convolution

ICCV 2017 sniklaus/pytorch-sepconv

Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.

OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION

Flow-Guided Feature Aggregation for Video Object Detection

ICCV 2017 msracver/Flow-Guided-Feature-Aggregation

The accuracy of detection suffers from degenerated object appearances in videos, e. g., motion blur, video defocus, rare poses, etc.

VIDEO OBJECT DETECTION VIDEO RECOGNITION

Temporal Action Detection with Structured Segment Networks

ICCV 2017 yjxiong/action-detection

Detecting actions in untrimmed videos is an important yet challenging task.

ACTION DETECTION

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

ICCV 2017 ramprs/grad-cam

We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent.

IMAGE CLASSIFICATION INTERPRETABLE MACHINE LEARNING VISUAL QUESTION ANSWERING

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

ICCV 2017 Yijunmaverick/UniversalStyleTransfer

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer.

STYLE TRANSFER

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

ICCV 2017 xingyizhou/pytorch-pose-hg-3d

We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.

3D HUMAN POSE ESTIMATION DEPTH ESTIMATION TRANSFER LEARNING

Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

ICCV 2017 ZhaofanQiu/pseudo-3d-residual-networks

In this paper, we devise multiple variants of bottleneck building blocks in a residual learning framework by simulating $3\times3\times3$ convolutions with $1\times3\times3$ convolutional filters on spatial domain (equivalent to 2D CNN) plus $3\times1\times1$ convolutions to construct temporal connections on adjacent feature maps in time.

VIDEO CLASSIFICATION

StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

ICCV 2017 hanzhanggit/StackGAN-Pytorch

Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications.

TEXT-TO-IMAGE GENERATION