Skip to search formSkip to main contentSkip to account menu

Fully Convolutional Instance-Aware Semantic Segmentation

The first fully convolutional end-to-end solution for instance-aware semantic segmentation task, which achieves state-of-the-art performance in both accuracy and efficiency, wins the COCO 2016 segmentation competition by a large margin.
View on IEEE (opens in a new tab)

DeepIM: Deep Iterative Matching for 6D Pose Estimation

A novel deep neural network for 6D pose matching named DeepIM is proposed, trained to predict a relative pose transformation using a disentangled representation of 3D location and 3D orientation and an iterative training process.
View on Springer (opens in a new tab)

CIFAR10-DVS: An Event-Stream Dataset for Object Classification

This work provides a large event-stream dataset and an initial benchmark for comparison, which may boost algorithm developments in even-driven pattern recognition and object classification, based on state-of-the-art classification algorithms.
View on PubMed (opens in a new tab)

CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation

This work proposes a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation.
View on IEEE (opens in a new tab)

Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition

A model-free algorithm UCB-Advantage is proposed and it is proved that it achieves $\tilde{O}(\sqrt{H^2SAT})$ regret where $T = KH$ and $K$ is the number of episodes to play.
View PDF on arXiv (opens in a new tab)

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classication

A new framework, called correlated MIL, is proposed, based on which a Transformer based MIL (TransMIL) is devised, which explored both morphological and spatial information and achieved better performance and faster convergence compared with state-of-the-art methods.
View PDF on arXiv (opens in a new tab)

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation

A simple yet effective Geometry-guided Direct Regression Network (GDR-Net) to learn the 6D pose in an end-to-end manner from dense correspondence-based intermediate geometric representations, which remarkably outperforms state-of-the-art methods on LM, LM-O and YCB-V datasets.
View on IEEE (opens in a new tab)

Residual Highway Convolutional Neural Networks for in-loop Filtering in HEVC

Experimental results demonstrate that the proposed RHCNN is able to not only raise the PSNR of reconstructed frame but also prominently reduce the bit-rate compared with HEVC reference software.
View on IEEE (opens in a new tab)

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

A continuation optimization method is introduced into MIL and thereby creating continuation multiple instance learning (C-MIL), with the intention of alleviating the non-convexity problem in a systematic way.
View on IEEE (opens in a new tab)

Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon

The current paper shows that the long planning horizon and the unknown state-dependent transitions (at most) pose little additional difficulty on sample complexity, and improves the state-of-the-art polynomial-time algorithms.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)