207 citations · 786 across the 32 of their papers we have counts for
32 papers
Multi-Task Learning with Multi-Query Transformer for Dense Prediction
Yangyang Xu, Xiangtai Li, Haobo Yuan +2
Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each tas…
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
Xiangtai Li, Wenwei Zhang, Jiangmiao Pang +4
This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies ima…
Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang +3
Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff,…
Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition
Shilin Xu, Xiangtai Li, Jingbo Wang +3
Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation a…
TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers
Qianyu Zhou, Xiangtai Li, Lu He +5
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance…
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
Haobo Yuan, Xiangtai Li, Yibo Yang +5
The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously. The previous…
Graph Pointer Neural Networks
Tianmeng Yang, Yujing Wang, Zhihan Yue +3
Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invarian…
Global Aggregation then Local Distribution for Scene Parsing
Xiangtai Li, Li Zhang, Guangliang Cheng +4
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherentl…
Improving Video Instance Segmentation via Temporal Pyramid Routing
Xiangtai Li, Hao He, Yibo Yang +5
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are ma…
Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation
Chen Shi, Xiangtai Li, Yanran Wu +2
Representation of semantic context and local details is the essential issue for building modern semantic segmentation models. However, the interrelationship between semantic contex…
Fast and Accurate Scene Parsing via Bi-direction Alignment Networks
Yanran Wu, Xiangtai Li, Chen Shi +5
In this paper, we propose an effective method for fast and accurate scene parsing called Bidirectional Alignment Network (BiAlignNet). Previously, one representative work BiSeNet~\…
BoundarySqueeze: Image Segmentation as Boundary Squeezing
Hao He, Xiangtai Li, Yibo Yang +5
This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing…
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
Defu Cao, Yujing Wang, Juanyong Duan +8
Multivariate time-series forecasting plays a crucial role in many real-world applications. It is a challenging problem as one needs to consider both intra-series temporal correlati…
PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
Xiangtai Li, Hao He, Xia Li +6
Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two…
Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees
Jiangang Bai, Yujing Wang, Yiren Chen +4
Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information h…
Enhanced Boundary Learning for Glass-like Object Segmentation
Hao He, Xiangtai Li, Guangliang Cheng +5
Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. Howev…
Evolving Attention with Residual Convolutions
Yujing Wang, Yaming Yang, Jiangang Bai +6
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model…
Towards Efficient Scene Understanding via Squeeze Reasoning
Xiangtai Li, Xia Li, Ansheng You +5
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, i…
AutoADR: Automatic Model Design for Ad Relevance
Yiren Chen, Yaming Yang, Hong Sun +7
Large-scale pre-trained models have attracted extensive attention in the research community and shown promising results on various tasks of natural language processing. However, th…
Multivariate Time-series Anomaly Detection via Graph Attention Network
Hang Zhao, Yujing Wang, Juanyong Duan +7
Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications. Recent approaches have achieved significant progress…
Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Xiangtai Li, Xia Li, Li Zhang +5
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by mu…
Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Yueran Bai, Yingying Wang, Yunhai Tong +3
Temporal action proposal generation plays an important role in video action understanding, which requires localizing high-quality action content precisely. However, generating temp…
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression
Yihuan Mao, Yujing Wang, Chufan Wu +6
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a…
Improving BERT with Self-Supervised Attention
Yiren Chen, Xiaoyu Kou, Jiangang Bai +1
One of the most popular paradigms of applying large pre-trained NLP models such as BERT is to fine-tune it on a smaller dataset. However, one challenge remains as the fine-tuned mo…