1 code implementation • 15 Mar 2024 • Chuang Lin, Yi Jiang, Lizhen Qu, Zehuan Yuan, Jianfei Cai
To address it, we formulate object detection as a generative problem and propose a simple framework named GenerateU, which can detect dense objects and generate their names in a free-form way.
no code implementations • 29 Feb 2024 • Yong Yang, Xuhong Zhang, Yi Jiang, Xi Chen, Haoyu Wang, Shouling Ji, Zonghui Wang
In the mutation phase, we propose a prompt attention algorithm based on differential feedback to capture these critical features for effectively inferring the target prompts.
no code implementations • 29 Jan 2024 • Yi Jiang, Richard S. J. Tol
In the era of sustainability, firms grapple with the decision of how much to invest in green innovation and how it influences their economic trajectory.
no code implementations • 23 Jan 2024 • Xin Feng, Yi Jiang, Jia-Xian Qin, Lai-Ping Zhang, Xiao-Gang Deng
The wave equation is an important physical partial differential equation, and in recent years, deep learning has shown promise in accelerating or replacing traditional numerical methods for solving it.
2 code implementations • 25 Dec 2023 • Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo
We evaluate our unified models on various benchmarks.
1 code implementation • 14 Dec 2023 • Guoqing Chao, Yi Jiang, Dianhui Chu
In this work, we proposed a novel Incomplete Contrastive Multi-View Clustering method with high-confidence guiding (ICMVC).
1 code implementation • 14 Dec 2023 • Junfeng Wu, Yi Jiang, Qihao Liu, Zehuan Yuan, Xiang Bai, Song Bai
We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos.
Ranked #1 on Referring Expression Segmentation on Refer-YouTube-VOS (2021 public validation) (using extra training data)
Long-tail Video Object Segmentation Multi-Object Tracking +8
no code implementations • 5 Dec 2023 • Wenqian Xue, Yi Jiang, Frank L. Lewis, Bosen Lian
This paper formulates a stochastic optimal control problem for linear networked control systems featuring stochastic packet disordering with a unique stabilizing solution certified.
1 code implementation • 2 Nov 2023 • Haosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu
Understanding the semantics of individual regions or patches within unconstrained images, such as in open-world object detection, represents a critical yet challenging task in computer vision.
1 code implementation • NeurIPS 2023 • Chuofan Ma, Yi Jiang, Xin Wen, Zehuan Yuan, Xiaojuan Qi
CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept.
Ranked #2 on Open Vocabulary Object Detection on LVIS v1.0 (using extra training data)
no code implementations • 4 Oct 2023 • Yi Jiang, Shohei Shimizu
Our study contributes to a better understanding of the linkages among financial markets in the analyzed data period by supporting the existence of linkages between Japan and the US for the same financial markets and among FX, stock, and bond markets, thus highlighting the importance of leveraging causal discovery methods in the financial domain.
no code implementations • 28 Sep 2023 • Xiuxiu He, Kuangcai Chen, Ning Fang, Yi Jiang
Cell shape has long been used to discern cell phenotypes and states, but the underlying premise has not been quantitatively tested.
no code implementations • ICCV 2023 • Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo
Open-world instance segmentation is a rising task, which aims to segment all objects in the image by learning from a limited number of base-category objects.
no code implementations • 5 May 2023 • Jiawei Liu, Zi Xiong, Yi Jiang, Yongqiang Ma, Wei Lu, Yong Huang, Qikai Cheng
Inspired by recent advancement in prompt learning, in this paper, we propose the Mix Prompt Tuning (MPT), which is a semi-supervised method to alleviate the dependence on annotated data and improve the performance of multi-granularity academic function recognition tasks with a small number of labeled examples.
1 code implementation • 10 Apr 2023 • Iksung Kang, Yi Jiang, Mirko Holler, Manuel Guizar-Sicairos, A. F. J. Levi, Jeffrey Klug, Stefan Vogt, George Barbastathis
Two scanning operations are required: ptychographic to recover the complex transmissivity of the specimen; and rotation of the specimen to acquire multiple projections covering the 3D spatial frequency domain.
1 code implementation • ICCV 2023 • Qiushan Guo, Chuofan Ma, Yi Jiang, Zehuan Yuan, Yizhou Yu, Ping Luo
Learning image classification and image generation using the same set of network parameters is a challenging problem.
1 code implementation • 4 Apr 2023 • Qiushan Guo, Yizhou Yu, Yi Jiang, Jiannan Wu, Zehuan Yuan, Ping Luo
We extend our pretext task to supervised pre-training, which achieves a similar performance to self-supervised learning.
1 code implementation • CVPR 2023 • Qihao Liu, Junfeng Wu, Yi Jiang, Xiang Bai, Alan Yuille, Song Bai
A common solution is to use optical flow to provide motion information, but essentially it only considers pixel-level motion, which still relies on appearance similarity and hence is often inaccurate under occlusion and fast movement.
1 code implementation • CVPR 2023 • Bin Yan, Yi Jiang, Jiannan Wu, Dong Wang, Ping Luo, Zehuan Yuan, Huchuan Lu
All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks.
Ranked #1 on Referring Expression Segmentation on RefCoCo val (using extra training data)
Described Object Detection Generalized Referring Expression Comprehension +15
no code implementations • 6 Mar 2023 • Chenhao Yang, Xin Wang, Wei Ni, Yi Jiang
Under this approach, we reveal that the optimal receive beamforming is given by the classic MMSE one and the optimal transmit beamforming design amounts to solving an orthogonal Procrustes problem, thereby allowing for closed-form solutions to subproblems in each BCD step and fast convergence of the proposed algorithm to a high-quality (near-optimal) overall beamforming design.
1 code implementation • 9 Jan 2023 • Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, LiWei Wang, Zehuan Yuan
This is the first use of sparse convolution for 2D masked modeling.
Ranked #1 on Instance Segmentation on COCO 2017 val
no code implementations • ICCV 2023 • Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo
In this work, we end the current fragmented situation and propose UniRef to unify the three reference-based object segmentation tasks with a single architecture.
no code implementations • 3 Dec 2022 • Zhong Wang, Yi Zhang, Yi Jiang
Children have an obvious preference for "prototype matching" in scientific concept learning, which is not only obviously deviated from the current general understanding of science education that emphasizes discovery/inquiry construction, but also points out that there may be a priority relationship among various ways of concept organization (such as definition theory, prototype theory, schema theory, etc.).
no code implementations • 3 Dec 2022 • Chao Pang, Yu Wang, Yi Jiang, Ruheng Wang, Ran Su, Leyi Wei
Moreover, case study results on targeted molecule generation for the SARS-CoV-2 main protease (Mpro) show that by integrating molecule docking into our model as chemical priori, we successfully generate new small molecules with desired drug-like properties for the Mpro, potentially accelerating the de novo design of Covid-19 drugs.
1 code implementation • 29 Nov 2022 • Iksung Kang, Ziling Wu, Yi Jiang, YuDong Yao, Junjing Deng, Jeffrey Klug, Stefan Vogt, George Barbastathis
Noninvasive X-ray imaging of nanoscale three-dimensional objects, e. g. integrated circuits (ICs), generally requires two types of scanning: ptychographic, which is translational and returns estimates of complex electromagnetic field through ICs; and tomographic scanning, which collects complex field projections from multiple angles.
1 code implementation • 27 Nov 2022 • Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai
In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data.
no code implementations • 22 Nov 2022 • Wei zhang, Yi Jiang, Bin Zhou
The wireless in-band full-duplex (IBFD) technology can in theory double the system capacity over the conventional frequency division duplex (FDD) or time-division duplex (TDD) alternatives.
no code implementations • 18 Nov 2022 • Junfeng Wu, Yi Jiang, Qihao Liu, Xiang Bai, Song Bai
This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge.
2 code implementations • Genome Biology 2022 • Junru Jin, Yingying Yu, Ruheng Wang, Xin Zeng, Chao Pang, Yi Jiang, Zhongshen Li, Yutong Dai, Ran Su, Quan Zou, Kenta Nakai, Leyi Wei
In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only.
no code implementations • 14 Oct 2022 • Robert Hovden, Yi Jiang, Huolin L. Xin, Lena F. Kourkoutis
In this method, edge artifacts are reduced by subtracting a smooth background that solves Poisson's equation with boundary conditions set by the image's edges.
1 code implementation • 9 Oct 2022 • Haosen Yang, Deng Huang, Bin Wen, Jiannan Wu, Hongxun Yao, Yi Jiang, Xiatian Zhu, Zehuan Yuan
As a result, our model can extract effectively both static appearance and dynamic motion spontaneously, leading to superior spatiotemporal representation learning capability.
1 code implementation • 6 Oct 2022 • Yu Wang, Chao Pang, Yuzhe Wang, Yi Jiang, Junru Jin, Sirui Liang, Quan Zou, Leyi Wei
Leveraging artificial intelligence for automatic retrosynthesis speeds up organic pathway planning in digital laboratories.
1 code implementation • 26 Sep 2022 • Chuofan Ma, Qiushan Guo, Yi Jiang, Zehuan Yuan, Ping Luo, Xiaojuan Qi
Our key finding is that the major cause of degradation is not information loss in the down-sampling process, but rather the mismatch between network architecture and input scale.
no code implementations • 20 Sep 2022 • Anakha V Babu, Tao Zhou, Saugat Kandel, Tekin Bicer, Zhengchun Liu, William Judge, Daniel J. Ching, Yi Jiang, Sinisa Veseli, Steven Henke, Ryan Chard, YuDong Yao, Ekaterina Sirazitdinova, Geetika Gupta, Martin V. Holt, Ian T. Foster, Antonino Miceli, Mathew J. Cherukara
Coherent microscopy techniques provide an unparalleled multi-scale view of materials across scientific and technological fields, from structural materials to quantum devices, from integrated circuits to biological cells.
no code implementations • 28 Jul 2022 • Hai Yang, Yuhang Sheng, Yi Jiang, Xiaoyang Fang, Dongdong Li, Jing Zhang, Zhe Wang
In addition, Subtype-Former also achieved outstanding results in pan-cancer subtyping, which can help analyze the commonalities and differences across various cancer types at the molecular level.
1 code implementation • 21 Jul 2022 • Junfeng Wu, Qihao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai
In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance.
Ranked #9 on Video Instance Segmentation on YouTube-VIS validation (using extra training data)
1 code implementation • 14 Jul 2022 • Bin Yan, Yi Jiang, Peize Sun, Dong Wang, Zehuan Yuan, Ping Luo, Huchuan Lu
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters.
Multi-Object Tracking Multi-Object Tracking and Segmentation +3
no code implementations • 29 Jun 2022 • Dergan Lin, Yi Jiang, Junjing Deng, Zichao Wendy Di
X-ray ptychography allows for large fields to be imaged at high resolution at the cost of additional computational expense due to the large volume of data.
no code implementations • 20 Apr 2022 • Cheng Du, Yi Jiang
For the binary GCM quads, we conjecture that the feasible sizes are arbitrary, and verify for sizes within 78 $\times$ 78 and other less densely distributed sizes.
no code implementations • 7 Apr 2022 • Xin Liang, Yi Jiang
This paper studies the optimal state estimation for a dynamic system, whose transfer function can be nonlinear and the input noise can be of arbitrary distribution.
2 code implementations • 5 Mar 2022 • Qishuai Diao, Yi Jiang, Bin Wen, Jia Sun, Zehuan Yuan
Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category.
Ranked #1 on Fine-Grained Image Classification on NABirds (using extra training data)
no code implementations • 22 Feb 2022 • Jie Yang, Qinghe Du, Yi Jiang
As an interesting by-product, we propose an enhancement to the BLE standard by introducing a bit interleaver to its physical layer; the resultant improvement of the receiver sensitivity can make it a better fit for some Internet of Things (IoT) communications.
no code implementations • 14 Feb 2022 • Yi Jiang, Tianyi Zhang, Wei zhang
Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm.
1 code implementation • CVPR 2022 • Jiannan Wu, Yi Jiang, Peize Sun, Zehuan Yuan, Ping Luo
Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames.
Ranked #3 on Referring Video Object Segmentation on MeViS
2 code implementations • 15 Dec 2021 • Junfeng Wu, Yi Jiang, Song Bai, Wenqing Zhang, Xiang Bai
Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently.
Ranked #2 on Video Instance Segmentation on HQ-YTVIS
3 code implementations • CVPR 2022 • Peize Sun, Jinkun Cao, Yi Jiang, Zehuan Yuan, Song Bai, Kris Kitani, Ping Luo
A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association.
1 code implementation • 10 Nov 2021 • Chuang Lin, Yi Jiang, Jianfei Cai, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan
Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving.
10 code implementations • arXiv 2021 • Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Fucheng Weng, Zehuan Yuan, Ping Luo, Wenyu Liu, Xinggang Wang
ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
Ranked #1 on Multiple Object Tracking on BDD100K val
no code implementations • ICLR 2022 • Shuo Yang, Peize Sun, Yi Jiang, Xiaobo Xia, Ruiheng Zhang, Zehuan Yuan, Changhu Wang, Ping Luo, Min Xu
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
no code implementations • 4 Mar 2021 • Wei zhang, Yi Jiang, Bin Zhou, Die Hu
This paper proposes a novel scheme for mitigating strong interferences, which is applicable to various wireless scenarios, including full-duplex wireless communications and uncoordinated heterogenous networks.
no code implementations • 21 Jan 2021 • Ci Chen, Lihua Xie, Yi Jiang, Kan Xie, Shengli Xie
To remove such a requirement, an off-policy reinforcement learning algorithm is proposed using only the measured output data along the trajectories of the system and the reference output.
Dynamical Systems
no code implementations • 31 Dec 2020 • Karina I Mazzitello, Yi Jiang, Constancio M Arizmendi
We propose a network approach to determine the optimal low resources setting oriented pool testing strategies that identifies infected individuals in a small number of tests and few rounds of testing, at low prevalence of the virus.
Physics and Society Social and Information Networks
2 code implementations • 31 Dec 2020 • Peize Sun, Jinkun Cao, Yi Jiang, Rufeng Zhang, Enze Xie, Zehuan Yuan, Changhu Wang, Ping Luo
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems.
Ranked #6 on Multi-Object Tracking on SportsMOT (using extra training data)
Multi-Object Tracking Multiple Object Tracking with Transformer +3
1 code implementation • 10 Dec 2020 • Peize Sun, Yi Jiang, Enze Xie, Wenqi Shao, Zehuan Yuan, Changhu Wang, Ping Luo
We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference.
no code implementations • 8 Dec 2020 • Kayla X. Nguyen, Yi Jiang, Michael C. Cao, Prafull Purohit, Ajay K. Yadav, Pablo García-Fernández, Mark W. Tate, Celesta S. Chang, Pablo Aguado-Puente, Jorge Íñiguez, Fernando Gomez-Ortiz, Sol M. Gruner, Javier Junquera, Lane W. Martin, Ramamoorthy Ramesh, D. A. Muller
We find that the presence of an electric toroidal moment in a ferro-rotational phase transfers a measurable torque and orbital angular momentum to the electron beam.
Materials Science Applied Physics
6 code implementations • CVPR 2021 • Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei LI, Zehuan Yuan, Changhu Wang, Ping Luo
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on 2D Object Detection on CeyMo
no code implementations • 15 Sep 2020 • Guoqiang Liang, Yi Jiang, Haiyan Hou
In the last two decades, scholars have designed various types of bibliographic related indicators to identify breakthrough-class academic achievements.
no code implementations • 21 Aug 2020 • Zhang Li, Jiehua Zhang, Tao Tan, Xichao Teng, Xiaoliang Sun, Yang Li, Lihong Liu, Yang Xiao, Byungjae Lee, Yilong Li, Qianni Zhang, Shujiao Sun, Yushan Zheng, Junyu Yan, Ni Li, Yiyu Hong, Junsu Ko, Hyun Jung, Yanling Liu, Yu-cheng Chen, Ching-Wei Wang, Vladimir Yurovskiy, Pavel Maevskikh, Vahid Khanagha, Yi Jiang, Xiangjun Feng, Zhihong Liu, Daiqiang Li, Peter J. Schüffler, Qifeng Yu, Hui Chen, Yuling Tang, Geert Litjens
All methods were based on deep learning and categorized into two groups: multi-model method and single model method.
1 code implementation • CVPR 2020 • Xinting Hu, Yi Jiang, Kaihua Tang, Jingyuan Chen, Chunyan Miao, Hanwang Zhang
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data.
no code implementations • 4 Apr 2019 • Yi Jiang, Elliot Padgett, Robert Hovden, David A. Muller
Popularized by compressed sensing, sparsity-exploiting algorithms have been applied to experimental ET data and show promise for improving reconstruction quality or reducing the total beam dose applied to a specimen.
1 code implementation • 14 Mar 2019 • Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang, Yi Jiang, Naiyan Wang, Zhao-Xiang Zhang
A Simple and Versatile Framework for Object Detection and Instance Recognition
no code implementations • 23 Jan 2019 • Jonathan Schwartz, Yi Jiang, Yongjie Wang, Anthony Aiello, Pallab Bhattacharya, Hui Yuan, Zetian Mi, Nabil Bassim, Robert Hovden
Highly-directional image artifacts such as ion mill curtaining, mechanical scratches, or image striping from beam instability degrade the interpretability of micrographs.