158 citations · 759 across the 45 of their papers we have counts for
45 papers
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
Gensheng Pei, Fumin Shen, Yazhou Yao +3
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical f…
MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection
Yixuan Zhou, Xing Xu, Jingkuan Song +2
Unsupervised anomaly detection (UAD) attracts a lot of research interest and drives widespread applications, where only anomaly-free samples are available for training. Some UAD ap…
Co-attention Propagation Network for Zero-Shot Video Object Segmentation
Gensheng Pei, Yazhou Yao, Fumin Shen +3
Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often…
Attention Map Guided Transformer Pruning for Edge Device
Junzhu Mao, Yazhou Yao, Zeren Sun +3
Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identificatio…
Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
Gensheng Pei, Fumin Shen, Yazhou Yao +3
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion…
Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation
Tao Chen, Yazhou Yao, Lei Zhang +3
Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activat…
Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach
Zeren Sun, Yazhou Yao, Xiu-Shen Wei +5
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distingui…
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing
Xunguang Wang, Zheng Zhang, Baoyuan Wu +2
Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep…
Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
Yazhou Yao, Tao Chen, Guosen Xie +5
Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels…
Jo-SRC: A Contrastive Approach for Combating Noisy Labels
Yazhou Yao, Zeren Sun, Chuanyi Zhang +4
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily…
Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
Tao Chen, Guosen Xie, Yazhou Yao +4
One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimi…
Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones
Huafeng Liu, Chuanyi Zhang, Yazhou Yao +4
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images…
Dual ResGCN for Balanced Scene GraphGeneration
Jingyi Zhang, Yong Zhang, Baoyuan Wu +3
Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene gra…
Auto-Encoding Twin-Bottleneck Hashing
Yuming Shen, Jie Qin, Jiaxin Chen +5
Conventional unsupervised hashing methods usually take advantage of similarity graphs, which are either pre-computed in the high-dimensional space or obtained from random anchor po…
Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent
Huan Xiong, Mengyang Yu, Li Liu +3
Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and ma…
Cooperative Cross-Stream Network for Discriminative Action Representation
Jingran Zhang, Fumin Shen, Xing Xu +1
Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which…
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
Zhijun Mai, Guosheng Hu, Dexiong Chen +2
MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important…
Temporal Reasoning Graph for Activity Recognition
Jingran Zhang, Fumin Shen, Xing Xu +1
Despite great success has been achieved in activity analysis, it still has many challenges. Most existing work in activity recognition pay more attention to design efficient archit…
Make a Face: Towards Arbitrary High Fidelity Face Manipulation
Shengju Qian, Kwan-Yee Lin, Wayne Wu +5
Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack…
Extracting Visual Knowledge from the Internet: Making Sense of Image Data
Yazhou Yao, Jian Zhang, Xiansheng Hua +2
Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive…
Dynamically Visual Disambiguation of Keyword-based Image Search
Yazhou Yao, Zeren Sun, Fumin Shen +6
Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy.…
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Yan Xu, Baoyuan Wu, Fumin Shen +4
In this work, we study the robustness of a CNN+RNN based image captioning system being subjected to adversarial noises. We propose to fool an image captioning system to generate so…
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition
Yanli Ji, Feixiang Xu, Yang Yang +3
Current researches of action recognition mainly focus on single-view and multi-view recognition, which can hardly satisfies the requirements of human-robot interaction (HRI) applic…
Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Zheng Zhang, Li Liu, Jie Qin +5
How to economically cluster large-scale multi-view images is a long-standing problem in computer vision. To tackle this challenge, we introduce a novel approach named Highly-econom…