Trending Research
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.
#2 best model for
Atari Games
on Atari 2600 Pong
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.
Depth-Aware Video Frame Interpolation
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.
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.
#8 best model for
Semantic Segmentation
on Cityscapes val
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
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
Classification is a Strong Baseline for Deep Metric Learning
• microsoft/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
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.
#3 best model for
Action Recognition In Videos
on Sports-1M
Deep Reinforcement Learning with Double Q-learning
• deepmind/rlax
•
The popular Q-learning algorithm is known to overestimate action values under certain conditions.
#4 best model for
Atari Games
on Atari 2600 Tennis
Analyzing Learned Molecular Representations for Property Prediction
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.