270 citations · 878 across the 64 of their papers we have counts for
67 papers
Semantic-SAM: Segment and Recognize Anything at Any Granularity
Feng Li, Hao Zhang, Peize Sun +6
In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. Our model offers two key advanta…
Understanding Privacy Over-collection in WeChat Sub-app Ecosystem
Xiaohan Zhang, Yang Wang, Xin Zhang +3
Nowadays the app-in-app paradigm is becoming increasingly popular, and sub-apps have become an important form of mobile applications. WeChat, the leading app-in-app platform, provi…
deController: A Web3 Native Cyberspace Infrastructure Perspective
Hao Xu, Yunqing Sun, Zihao Li +3
Web3 brings an emerging outlook for the value of decentralization, boosting the decentralized infrastructure. People can benefit from Web3, facilitated by the advances in distribut…
LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
Xianbiao Qi, Jianan Wang, Yihao Chen +2
We present a Lipschitz continuous Transformer, called LipsFormer, to pursue training stability both theoretically and empirically for Transformer-based models. In contrast to previ…
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
Yihao Chen, Xianbiao Qi, Jianan Wang +1
We propose DisCo-CLIP, a distributed memory-efficient CLIP training approach, to reduce the memory consumption of contrastive loss when training contrastive learning models. Our ap…
HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
Xuan Ju, Ailing Zeng, Chenchen Zhao +3
Controllable human image generation (HIG) has numerous real-life applications. State-of-the-art solutions, such as ControlNet and T2I-Adapter, introduce an additional learnable bra…
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes
Xuan Ju, Ailing Zeng, Jianan Wang +2
Humans have long been recorded in a variety of forms since antiquity. For example, sculptures and paintings were the primary media for depicting human beings before the invention o…
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
Lei Zhang, Yuge Zhang, Kan Ren +2
The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The…
One-to-Few Label Assignment for End-to-End Dense Detection
Shuai Li, Minghan Li, Ruihuang Li +2
One-to-one (o2o) label assignment plays a key role for transformer based end-to-end detection, and it has been recently introduced in fully convolutional detectors for end-to-end d…
DynaMask: Dynamic Mask Selection for Instance Segmentation
Ruihuang Li, Chenhang He, Shuai Li +2
The representative instance segmentation methods mostly segment different object instances with a mask of the fixed resolution, e.g., 28*28 grid. However, a low-resolution mask los…
Reconfigurable Intelligent Surface: Power Consumption Modeling and Practical Measurement Validation
Jinghe Wang, Wankai Tang, Jing Cheng Liang +6
The reconfigurable intelligent surface (RIS) has received a lot of interest because of its capacity to reconfigure the wireless communication environment in a cost- and energy-effi…
When Digital Economy Meets Web3.0: Applications and Challenges
Chuan Chen, Lei Zhang, Yihao Li +5
With the continuous development of web technology, Web3.0 has attracted a considerable amount of attention due to its unique decentralized characteristics. The digital economy is a…
Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
Lei Zhang, Zhenghua Li, Shilin Zhou +4
Inspired by early research on exploring naturally annotated data for Chinese word segmentation (CWS), and also by recent research on integration of speech and text processing, this…
Masked Surfel Prediction for Self-Supervised Point Cloud Learning
Yabin Zhang, Jiehong Lin, Chenhang He +3
Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points…
Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges
Lei Zhang, Guanyu Gao, Huaizheng Zhang
Data drift is a thorny challenge when deploying person re-identification (ReID) models into real-world devices, where the data distribution is significantly different from that of…
MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources
Haoran Yin, Meng Ge, Yanjie Fu +5
Recent neural network based Direction of Arrival (DoA) estimation algorithms have performed well on unknown number of sound sources scenarios. These algorithms are usually achieved…
Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games
Lei Zhang, Mukesh Ghimire, Wenlong Zhang +2
Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs (HJI) PDEs. Self-supervised learning has been used to approximate soluti…
Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters
Wenyu Liu, Wentong Li, Jianke Zhu +3
Semantic segmentation on driving-scene images is vital for autonomous driving. Although encouraging performance has been achieved on daytime images, the performance on nighttime im…
Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective
Ming Liu, Jianan Pan, Zifei Yan +2
Recently, multiple synthetic and real-world datasets have been built to facilitate the training of deep single image reflection removal (SIRR) models. Meanwhile, diverse testing se…
Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds
Chenhang He, Ruihuang Li, Shuai Li +1
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cl…
Towards Robust 2D Convolution for Reliable Visual Recognition
Lida Li, Shuai Li, Kun Wang +2
2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN). However, Conv2d is vu…
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
Tao Yang, Peiran Ren, Xuansong Xie +2
Video frame interpolation (VFI) aims to improve the temporal resolution of a video sequence. Most of the existing deep learning based VFI methods adopt off-the-shelf optical flow a…
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
Ruihuang Li, Shuai Li, Chenhang He +3
Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One p…
A Dual Weighting Label Assignment Scheme for Object Detection
Shuai Li, Chenhang He, Ruihuang Li +1
Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods…