Trending Research

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

ICML 2018 deepmind/haiku

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.

ATARI GAMES

349
1.34 stars / hour

Attention Is All You Need

NeurIPS 2017 deepmind/haiku

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.

CONSTITUENCY PARSING MACHINE TRANSLATION

349
1.34 stars / hour

Depth-Aware Video Frame Interpolation

CVPR 2019 baowenbo/DAIN

The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.

OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION

2,123
1.23 stars / hour

Deep Residual Learning for Image Recognition

CVPR 2016 deepmind/dm-haiku

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 SEMANTIC SEGMENTATION

349
1.15 stars / hour

CenterMask : Real-Time Anchor-Free Instance Segmentation

arXiv 2019 youngwanLEE/centermask2

Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise.

PANOPTIC SEGMENTATION REAL-TIME INSTANCE SEGMENTATION REAL-TIME OBJECT DETECTION

85
0.87 stars / hour

Large-scale weakly-supervised pre-training for video action recognition

CVPR 2019 microsoft/computervision-recipes

Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?

ACTION RECOGNITION IN VIDEOS ACTIVITY RECOGNITION IN VIDEOS TRANSFER LEARNING

1,728
0.86 stars / hour

Classification is a Strong Baseline for Deep Metric Learning

30 Nov 2018microsoft/computervision-recipes

Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images.

CONTENT-BASED IMAGE RETRIEVAL FACE VERIFICATION METRIC LEARNING

1,728
0.86 stars / hour

A Closer Look at Spatiotemporal Convolutions for Action Recognition

CVPR 2018 microsoft/computervision-recipes

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition.

ACTION RECOGNITION IN VIDEOS

1,728
0.86 stars / hour

Deep Reinforcement Learning with Double Q-learning

22 Sep 2015deepmind/rlax

The popular Q-learning algorithm is known to overestimate action values under certain conditions.

ATARI GAMES Q-LEARNING

275
0.81 stars / hour

Analyzing Learned Molecular Representations for Property Prediction

2 Apr 2019swansonk14/chemprop

In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.

MOLECULAR PROPERTY PREDICTION

140
0.65 stars / hour