activity
20192022
most citedDirectPose: Direct End-to-End Multi-Person Pose Estimation

81 citations · 186 across the 9 of their papers we have counts for

collaborators

14 papers

cs.LG2022

Adaptive-Gravity: A Defense Against Adversarial Samples

Ali Mirzaeian, Zhi Tian, Sai Manoj P D +4

This paper presents a novel model training solution, denoted as Adaptive-Gravity, for enhancing the robustness of deep neural network classifiers against adversarial examples. We c…

cs.CV2021

NAS-FCOS: Efficient Search for Object Detection Architectures

Ning Wang, Yang Gao, Hao Chen +4

Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures. What is notew…

cs.CV20216 cited

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

Bowen Zhang, Yifan Liu, Zhi Tian +1

Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operat…

cs.CV2021

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Xiangxiang Chu, Zhi Tian, Yuqing Wang +5

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their s…

cs.CV202157 cited

TFPose: Direct Human Pose Estimation with Transformers

Weian Mao, Yongtao Ge, Chunhua Shen +3

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-…

cs.CV202028 cited

BoxInst: High-Performance Instance Segmentation with Box Annotations

Zhi Tian, Chunhua Shen, Xinlong Wang +1

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the l…