794 citations · 1.2k across the 30 of their papers we have counts for
17 papers · 1 filter
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation
Ke Fan, Jingshi Lei, Xuelin Qian +5
Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some s…
Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
Yazhou Zhu, Shidong Wang, Tong Xin +2
Few-shot Medical Image Segmentation (FSMIS) is a more promising solution for medical image segmentation tasks where high-quality annotations are naturally scarce. However, current…
Object-Centric Multiple Object Tracking
Zixu Zhao, Jiaze Wang, Max Horn +13
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing th…
Unsupervised Open-Vocabulary Object Localization in Videos
Ke Fan, Zechen Bai, Tianjun Xiao +11
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video obje…
Local-Global Pseudo-label Correction for Source-free Domain Adaptive Medical Image Segmentation
Yanyu Ye, Zhengxi Zhang, Chunna Tianb +1
Domain shift is a commonly encountered issue in medical imaging solutions, primarily caused by variations in imaging devices and data sources. To mitigate this problem, unsupervise…
Bridging the Gap to Real-World Object-Centric Learning
Maximilian Seitzer, Max Horn, Andrii Zadaianchuk +8
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decompos…
Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
Zhao Zhang, Zemin Tang, Zheng Zhang +3
The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks sti…
Compressed DenseNet for Lightweight Character Recognition
Zhao Zhang, Zemin Tang, Yang Wang +3
Convolutional Recurrent Neural Network (CRNN) is a popular network for recognizing texts in images. Advances like the variant of CRNN, such as Dense Convolutional Network with Conn…
Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning
Yulin Sun, Zhao Zhang, Weiming Jiang +4
In this paper, we propose a structured Robust Adaptive Dic-tionary Pair Learning (RA-DPL) framework for the discrim-inative sparse representation learning. To achieve powerful repr…
Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery
Zhao Zhang, Lei Wang, Sheng Li +4
In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover th…
Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification
Zhao Zhang, Yulin Sun, Zheng Zhang +3
In this paper, we extend the popular dictionary pair learning (DPL) into the scenario of twin-projective latent flexible DPL under a structured twin-incoherence. Technically, a nov…
MMDetection: Open MMLab Detection Toolbox and Benchmark
Kai Chen, Jiaqi Wang, Jiangmiao Pang +22
We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. The to…
Joint Subspace Recovery and Enhanced Locality Driven Robust Flexible Discriminative Dictionary Learning
Zhao Zhang, Jiahuan Ren, Weiming Jiang +4
We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learni…
Effective Occlusion Handling for Fast Correlation Filter-based Trackers
Zheng Zhang, T. T. Wong
Correlation filter-based trackers heavily suffer from the problem of multiple peaks in their response maps incurred by occlusions. Moreover, the whole tracking pipeline may break d…
Saliency-based Sequential Image Attention with Multiset Prediction
Sean Welleck, Jialin Mao, Kyunghyun Cho +1
Humans process visual scenes selectively and sequentially using attention. Central to models of human visual attention is the saliency map. We propose a hierarchical visual archite…
Tractable Clustering of Data on the Curve Manifold
Stephen Tierney, Junbin Gao, Yi Guo +1
In machine learning it is common to interpret each data point as a vector in Euclidean space. However the data may actually be functional i.e.\ each data point is a function of som…
Learning to Point and Count
Jie Shao, Dequan Wang, Xiangyang Xue +1
This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock. Different from the traditional detection problem, the goal is to discover ke…