Search Results for author:
Found 28 papers, 13 papers with code
Subtype-Former: a deep learning approach for cancer subtype discovery with multi-omics data
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.
In Defense of Online Models for Video Instance Segmentation
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.
Towards Grand Unification of Object Tracking
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.
Ranked #1 on
Multiple Object Tracking
on BDD100K
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+2
Physics-Inspired Unsupervised Classification for Region of Interest in X-Ray Ptychography
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.
Constructions of Polyphase Golay Complementary Arrays
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.
Nonlinear Kalman Filter Using Cramer Rao Bound
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.
MetaFormer: A Unified Meta Framework for Fine-Grained Recognition
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
Image Classification
on iNaturalist 2018
(using extra training data)
Online Learning of Trellis Diagram Using Neural Network for Robust Detection and Decoding
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.
Model-Based Neural Network and Its Application to Line Spectral Estimation
Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm.
Language as Queries for Referring Video Object Segmentation
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 #1 on
Referring Expression Segmentation
on Refer-YouTube-VOS (2021 public validation)
(using extra training data)
SeqFormer: Sequential Transformer for Video Instance Segmentation
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 #4 on
Video Instance Segmentation
on YouTube-VIS validation
(using extra training data)
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion
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.
Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation
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.
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
Ranked #1 on
Multi-Object Tracking
on MOT20
(using extra training data)
Objects in Semantic Topology
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
Hybrid Interference Mitigation Using Analog Prewhitening
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.
Robust Output Regulation and Reinforcement Learning-based Output Tracking Design for Unknown Linear Discrete-Time Systems
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
Optimising SARS-CoV-2 pooled testing strategies on social networks for low-resource settings
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
TransTrack: Multiple Object Tracking with Transformer
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems.
Ranked #4 on
Multi-Object Tracking
on DanceTrack
What Makes for End-to-End Object Detection?
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.
Transferring Orbital Angular Momentum to an Electron Beam Reveals Toroidal and Chiral Order
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
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
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 #75 on
Object Detection
on COCO minival
Same data may bring conflict results: a caution to use the disruptive index
In the last two decades, scholars have designed various types of bibliographic related indicators to identify breakthrough-class academic achievements.
Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019
All methods were based on deep learning and categorized into two groups: multi-model method and single model method.
Learning to Segment the Tail
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data.
Sampling Limits for Electron Tomography with Sparsity-exploiting Reconstructions
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.
SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
A Simple and Versatile Framework for Object Detection and Instance Recognition
Removing Stripes, Scratches, and Curtaining with Non-Recoverable Compressed Sensing
Highly-directional image artifacts such as ion mill curtaining, mechanical scratches, or image striping from beam instability degrade the interpretability of micrographs.
