Trending Research

Hacking Neural Networks: A Short Introduction

18 Nov 2019Kayzaks/HackingNeuralNetworks

A large chunk of research on the security issues of neural networks is focused on adversarial attacks.

NEURAL NETWORK SECURITY

1,757
4.14 stars / hour

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

17 Nov 2019clvrai/furniture

The IKEA Furniture Assembly Environment is one of the first benchmarks for testing and accelerating the automation of complex manipulation tasks.

ROBOTIC GRASPING

93
1.97 stars / hour

Learning Spatial Fusion for Single-Shot Object Detection

21 Nov 2019ruinmessi/ASFF

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection.

OBJECT DETECTION

51
1.92 stars / hour

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

15 Nov 2019wei-tim/YOWO

YOWO makes use of a single neural network to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.

ACTION LOCALIZATION

179
1.89 stars / hour

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.

871
1.77 stars / hour
5,879
1.35 stars / hour

LIDA: Lightweight Interactive Dialogue Annotator

IJCNLP 2019 Wluper/lida

Dialogue systems have the potential to change how people interact with machines but are highly dependent on the quality of the data used to train them.

80
0.81 stars / hour

DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation

1 Nov 2019microsoft/DialogLSP

We present a large, tunable neural conversational response generation model, DialoGPT (dialogue generative pre-trained transformer).

CONVERSATIONAL RESPONSE GENERATION

352
0.60 stars / hour
352
0.60 stars / hour

A Diversity-Promoting Objective Function for Neural Conversation Models

NAACL 2016 microsoft/DialogLSP

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e. g., "I don't know") regardless of the input.

CONVERSATIONAL RESPONSE GENERATION

352
0.60 stars / hour