• Publications
  • Influence
FCOS: Fully Convolutional One-Stage Object Detection
TLDR
For the first time, a much simpler and flexible detection framework achieving improved detection accuracy is demonstrated, and it is hoped that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks.
Supervised Discrete Hashing
TLDR
This work proposes a new supervised hashing framework, where the learning objective is to generate the optimal binary hash codes for linear classification, and introduces an auxiliary variable to reformulate the objective such that it can be solved substantially efficiently by employing a regularization algorithm.
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TLDR
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner.
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
TLDR
This paper proposes to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum, making training deep networks easier and achieving restoration performance gains consequently.
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
TLDR
A deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF is presented, and a deep structured learning scheme which learns the unary and pairwise potentials of continuousCRF in a unified deep CNN framework is proposed.
Semidefinite Programming
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
TLDR
Experiments demonstrate that the proposed method significantly outperforms most state-of-the-art methods in retrieval precision and training time, and is orders of magnitude faster than many methods in terms of training time.
Repulsion Loss: Detecting Pedestrians in a Crowd
TLDR
This paper first explores how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, and proposes a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss.
VITAL: VIsual Tracking via Adversarial Learning
TLDR
The VITAL algorithm is presented, which uses a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes and identifies the mask that maintains the most robust features of the target objects over a long temporal span.
...
...