activity
20162022
most citedNeural Collaborative Subspace Clustering

13 citations · 61 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

18 papers · 1 filter

cs.CV2022

Deformable VisTR: Spatio temporal deformable attention for video instance segmentation

Sudhir Yarram, Jialian Wu, Pan Ji +2

Video instance segmentation (VIS) task requires classifying, segmenting, and tracking object instances over all frames in a video clip. Recently, VisTR has been proposed as end-to-…

cs.CV20212 cited

MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

Pan Ji, Runze Li, Bir Bhanu +1

Self-supervised depth estimation for indoor environments is more challenging than its outdoor counterpart in at least the following two aspects: (i) the depth range of indoor seque…

cs.CV2021

Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network

Yang Liu, Saeed Anwar, Zhenyue Qin +3

The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. Howe…

cs.CV20211 cited

Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction

Ze Ma, Yifan Yao, Pan Ji +1

Estimating 3D human pose and shape from a single image is highly under-constrained. To address this ambiguity, we propose a novel prior, namely kinematic dictionary, which explicit…

cs.CV2020

Set Augmented Triplet Loss for Video Person Re-Identification

Pengfei Fang, Pan Ji, Lars Petersson +1

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usu…

cs.CV20209 cited

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Jianyuan Wang, Yiran Zhong, Yuchao Dai +3

Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volu…