• 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.
Detecting Text in Natural Image with Connectionist Text Proposal Network
TLDR
A novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image and develops a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy.
Conditional Convolutions for Instance Segmentation
TLDR
A simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed on the COCO dataset, and outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed.
An End-to-End TextSpotter with Explicit Alignment and Attention
TLDR
A novel text-alignment layer is proposed that allows it to precisely compute convolutional features of a text instance in arbitrary orientation, which is the key to boost the performance of the model on the ICDAR 2015.
Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
TLDR
This work proposes a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
Knowledge Adaptation for Efficient Semantic Segmentation
TLDR
This work proposes a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride and optimize the feature similarity in a transferred latent domain formulated by utilizing a pre-trained autoencoder.
NAS-FCOS: Fast Neural Architecture Search for Object Detection
TLDR
This work efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm, and is able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs.
Single Shot TextSpotter with Explicit Alignment and Attention
TLDR
A novel text-alignment layer is proposed that allows it to precisely compute convolutional features of a text instance in ar- bitrary orientation, which is critical to identify challenging text instances.
FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
TLDR
The experiment results show that FCPose is a simple yet effective multi-person pose estimation framework that offers better speed/accuracy trade-off than other state-of-the-art methods.
Similarity Analysis of DNA Sequences Based on a Novel 3D Graphical Representation and New Similarity Measure
A 3D graphical representation of DNA sequence has been derived from chaos game representation of DNA sequence. The 3D graphical representation also avoids loss of information. The geometrical centers