49 citations · 139 across the 13 of their papers we have counts for
14 papers
Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
Tianmeng Yang, Min Zhou, Yujing Wang +4
Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many res…
Towards Open Vocabulary Learning: A Survey
Jianzong Wu, Xiangtai Li, Shilin Xu +9
In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most a…
PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang +6
Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions with…
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation
Jianzong Wu, Xiangtai Li, Henghui Ding +4
In this work, we focus on open vocabulary instance segmentation to expand a segmentation model to classify and segment instance-level novel categories. Previous approaches have rel…
Label-Efficient Interactive Time-Series Anomaly Detection
Hong Guo, Yujing Wang, Jieyu Zhang +5
Time-series anomaly detection is an important task and has been widely applied in the industry. Since manual data annotation is expensive and inefficient, most applications adopt u…
Convolution-enhanced Evolving Attention Networks
Yujing Wang, Yaming Yang, Zhuo Li +7
Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series anal…
Towards Robust Referring Image Segmentation
Jianzong Wu, Xiangtai Li, Xia Li +3
Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs object masks based on text descriptions. Many works have achieved considerable progress for RI…
SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow
Xiangtai Li, Jiangning Zhang, Yibo Yang +4
In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feat…
Customizing Graph Neural Networks using Path Reweighting
Jianpeng Chen, Yujing Wang, Ming Zeng +5
Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish amo…
TS2Vec: Towards Universal Representation of Time Series
Zhihan Yue, Yujing Wang, Juanyong Duan +4
This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive l…
End-to-End Video Object Detection with Spatial-Temporal Transformers
Lu He, Qianyu Zhou, Xiangtai Li +7
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous c…
News Image Steganography: A Novel Architecture Facilitates the Fake News Identification
Jizhe Zhou, Chi-Man Pun, Yu Tong
A larger portion of fake news quotes untampered images from other sources with ulterior motives rather than conducting image forgery. Such elaborate engraftments keep the inconsist…
Privacy-sensitive Objects Pixelation for Live Video Streaming
Jizhe Zhou, Chi-Man Pun, Yu Tong
With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency. Caused by the inaccurate detection of privacy-sen…
CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese
Liang Xu, Yu tong, Qianqian Dong +7
In this paper, we introduce the NER dataset from CLUE organization (CLUENER2020), a well-defined fine-grained dataset for named entity recognition in Chinese. CLUENER2020 contains…