Trending Research

Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research

12 Nov 2019NVIDIAGameWorks/kaolin

We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research.

539
3.03 stars / hour

Tiramisu: A Polyhedral Compiler for Expressing Fast and Portable Code

27 Apr 2018Tiramisu-Compiler/tiramisu

This paper introduces Tiramisu, a polyhedral framework designed to generate high performance code for multiple platforms including multicores, GPUs, and distributed machines.

502
2.49 stars / hour

Detecting Photoshopped Faces by Scripting Photoshop

ICCV 2019 PeterWang512/FALdetector

Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop.

IMAGE MANIPULATION DETECTION

676
0.80 stars / hour

Scale-Aware Trident Networks for Object Detection

ICCV 2019 facebookresearch/detectron2

In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection.

OBJECT DETECTION

5,667
0.54 stars / hour

End to End Learning for Self-Driving Cars

25 Apr 2016LeonHillmann/Self-Driving-Car-Tensorflow

The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal.

LANE DETECTION SELF-DRIVING CARS

71
0.52 stars / hour

The Measure of Intelligence

5 Nov 2019fchollet/ARC

To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans.

499
0.39 stars / hour

Fast Learning of Temporal Action Proposal via Dense Boundary Generator

11 Nov 2019TencentYoutuResearch/ActionDetection-DBG

In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.

OPTICAL FLOW ESTIMATION REGRESSION

78
0.35 stars / hour

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

ICCV 2019 TencentYoutuResearch/ActionDetection-DBG

To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.

ACTION DETECTION TEMPORAL ACTION PROPOSAL GENERATION

78
0.35 stars / hour