arXiv subjects

Jingfeng Liu

Publications and source records attributed to Jingfeng Liu.

At least 19 recordsLinked to original sources

arXiv2026

FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation

Functional tissue units (FTUs), including tertiary lymphoid structures (TLSs), blood vessels, and glands, encode localized immune, vascular, and epithelial organization in histopathology. Accurate quantification of these structures is important for studying tissue architecture and disease-associated tissue organization. However, FTUs are frequently sparse, heterogeneous, and surrounded by large amounts of morphologically similar background tissue, making automated segmentation in whole-slide images (WSIs) challenging. We therefore developed FTU-Seek, a pathology foundation model-guided framework that treats morphology-aware negative-patch selection as a key component of sparse FTU segmentation. FTU-Seek uses frozen multi-depth features from the UNI pathology foundation model to train a patch-level classifier that distinguishes FTU-containing from FTU-absent tissue. Target-absent patches are subsequently ranked according to their predicted target-containing probabilities, and the highest-scoring hard negatives are selected through a static Top$K$ strategy to construct compact segmentation training sets. The framework was evaluated using five-fold cross-validation and internal test cohorts across TLS, blood-vessel, and gland segmentation tasks, with an additional independent 30-WSI held-out cohort for TLS. Positive-only, all-tissue, random-negative, and matched random Top$K$ sampling strategies served as comparators. Segmentation-derived phenotypes were further explored in external TCGA cohorts.

cs.CV↗

arXiv2026

Computational Oncology of Chemotaxis-Driven Tumour--Immune Spatial Patterning and Stability

We develop a reaction--diffusion--chemotaxis model for spatial tumour--immune--chemokine dynamics that couples logistic tumour growth, immune-mediated killing, chemokine-dependent immune recruitment, chemotactic migration, and signal production. For the nondimensional system, we establish local classical solvability, nonnegativity, a uniform tumour-density bound, and global mass estimates for the immune and chemokine components. The tumour-free equilibrium is stable precisely when the baseline immune-control index satisfies $\sigma_0/\delta>1$, whereas positive homogeneous coexistence is characterized by a scalar nonlinear equation. Linearization in the Neumann Laplacian eigenbasis yields a mode-dependent cubic dispersion relation, showing that chemotaxis does not alter the tumour-invasion threshold but can destabilize homogeneous coexistence through a finite-wavelength oscillatory instability above a critical sensitivity $\xi_c$. A conservative finite-volume discretization with upwind chemotactic fluxes and implicit backward differentiation formula time integration is used to test these predictions. Numerical experiments recover the analytical equilibria and growth rates, identify the dominant unstable mode, reproduce the transition to spatial heterogeneity, and quantify the effects of immune recruitment, decay, and diffusion on the stability boundary. Grid-refinement, mass-balance, residual, and nonnegativity diagnostics support the computational reliability of the results.

math.AP↗

arXiv2026

Mode-Wise Spectral Criteria for Coupled Mass Transport in Hybrid PDE--ODE Tumor Microenvironments

We study coupled mass transport in a tumor--microenvironment setting with two motile densities $(S,R)$ and non-motile state switching $(P,A)$. The populations diffuse and undergo chemotactic drift; $(P,A)$ follow pointwise ODE switching. A decoupled inhibitory field $D$ satisfies a damped Neumann heat equation, giving maximum-principle bounds and exponential decay. Together with the pointwise invariant $P+A$, these identities yield global existence, positivity, and long-time reduction to limiting $(S,R)$ kinetics with a unique globally attracting coexistence state. Neumann eigenmode reduction gives closed dispersion relations. The base $(S,R)$ reaction--diffusion block remains stable for all nonconstant modes for any $d_S,d_R>0$, excluding classical Turing destabilization. Chemotaxis is posed via a diffusive cue $c$, since $\nabla A$ is undefined for non-diffusive $A$. In one-way damped coupling, the linearized mode matrix is block triangular and leaves the $(S,R)$ spectrum unchanged. Two-way coupling adds a feedback rank-one mobility correction, induces effective cross-diffusion, and admits mode growth. We give explicit trace/determinant criteria for unstable Laplacian modes and the resulting instability thresholds.

math.AP↗

arXiv2026

Chemotactic Feedback Controls Patterning in Hybrid Tumor--Stroma Model

Motivated by an ongoing collaboration with clinical oncologists and pathologists, we develop a hybrid partial differential equation--ordinary differential equation (PDE--ODE) framework that captures (i) competition between susceptible and resistant phenotypes, (ii) stromal state switching, and (iii) a clinically realistic open-loop, single-dose therapeutic agent $I$ with diffusion and clearance. Clinical management of solid tumors is increasingly limited by spatial heterogeneity and therapy-induced resistance niches that are difficult to predict from well-mixed models. We establish a rigorous mathematical backbone with forward invariance of the nonnegative cone and global-in-time well-posedness. Exploiting the decoupled drug equation $\partial_t I=d_I\Delta I-\gamma_I I$, we prove a long-time reduction during washout and show that the damped base dynamics admit no diffusion-driven (Turing-type) instability. We then formulate a directionality--damping principle: unidirectional (open-loop) sensing yields at most transient focusing, whereas bidirectional (closed-loop) feedback reshapes the effective mobility and produces explicit thresholds separating stable homogeneity, finite-band patterning (resistance niche formation), and aggregation when strong parabolicity is violated. Reproducible simulations corroborate this classification and highlight when flux regularization is required for physical realism.

math.AP↗

arXiv2023

Topologically protected subradiant cavity polaritons through linewidth narrowing enabled by dissipationless edge states

Cavity polaritons derived from the strong light-matter interaction at the quantum level provide a basis for efficient manipulation of quantum states via cavity field. Polaritons with narrow linewidth and long lifetime are appealing in applications such as quantum sensing and storage. Here, we propose a prototypical arrangement to implement a whispering-gallery-mode resonator with topological mirror moulded by one-dimensional atom array, which allows to boost the lifetime of cavity polaritons over an order of magnitude. This considerable enhancement attributes to the coupling of polaritonic states to dissipationless edge states protected by the topological bandgap of atom array that suppresses the leakage of cavity modes. When exceeding the width of Rabi splitting, topological bandgap can further reduce the dissipation from polaritonic states to bulk states of atom array, giving arise to subradiant cavity polaritons with extremely sharp linewidth. The resultant Rabi oscillation decays with a rate even below the free-space decay of a single quantum emitter. Inheriting from the topologically protected properties of edge states, the subradiance of cavity polaritons can be preserved in the disordered atom mirror with moderate perturbations involving the atomic frequency, interaction strengths and location. Our work opens up a new paradigm of topology-engineered quantum states with robust quantum coherence for future applications in quantum computing and network.

quant-ph↗

arXiv2023

Weakly Supervised Detection of Baby Cry

Detection of baby cries is an important part of baby monitoring and health care. Almost all existing methods use supervised SVM, CNN, or their varieties. In this work, we propose to use weakly supervised anomaly detection to detect a baby cry. In this weak supervision, we only need weak annotation if there is a cry in an audio file. We design a data mining technique using the pre-trained VGGish feature extractor and an anomaly detection network on long untrimmed audio files. The obtained datasets are used to train a simple CNN feature network for cry/non-cry classification. This CNN is then used as a feature extractor in an anomaly detection framework to achieve better cry detection performance.

cs.CV↗

arXiv2022

Overlooked Video Classification in Weakly Supervised Video Anomaly Detection

Current weakly supervised video anomaly detection algorithms mostly use multiple instance learning (MIL) or their varieties. Almost all recent approaches focus on how to select the correct snippets for training to improve the performance. They overlook or do not realize the power of video classification in boosting the performance of anomaly detection. In this paper, we study explicitly the power of video classification supervision using a BERT or LSTM. With this BERT or LSTM, CNN features of all snippets of a video can be aggregated into a single feature which can be used for video classification. This simple yet powerful video classification supervision, combined into the MIL framework, brings extraordinary performance improvement on all three major video anomaly detection datasets. Particularly it improves the mean average precision (mAP) on the XD-Violence from SOTA 78.84\% to new 82.10\%. The source code is available at https://github.com/wjtan99/BERT_Anomaly_Video_Classification.

cs.CV↗

arXiv2022

Two-Stage COVID19 Classification Using BERT Features

We propose an automatic COVID1-19 diagnosis framework from lung CT-scan slice images using double BERT feature extraction. In the first BERT feature extraction, A 3D-CNN is first used to extract CNN internal feature maps. Instead of using the global average pooling, a late BERT temporal pooing is used to aggregate the temporal information in these feature maps, followed by a classification layer. This 3D-CNN-BERT classification network is first trained on sampled fixed number of slice images from every original CT scan volume. In the second stage, the 3D-CNN-BERT embedding features are extracted on all slice images of every CT scan volume, and these features are averaged into a fixed number of segments. Then another BERT network is used to aggregate these multiple features into a single feature followed by another classification layer. The classification results of both stages are combined to generate final outputs. On the validation dataset, we achieve macro F1 score of 0.9164.

eess.IV↗

arXiv2022

Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition

Detection of fights is an important surveillance application in videos. Most existing methods use supervised binary action recognition. Since frame-level annotations are very hard to get for anomaly detection, weakly supervised learning using multiple instance learning is widely used. This paper explores the detection of fights in videos as one special type of anomaly detection and as binary action recognition. We use the UBI-Fight and NTU-CCTV-Fight datasets for most of the study since they have frame-level annotations. We find that the anomaly detection has similar or even better performance than the action recognition. Furthermore, we study to use anomaly detection as a toolbox to generate training datasets for action recognition in an iterative way conditioned on the performance of the anomaly detection. Experiment results should show that we achieve state-of-the-art performance on three fight detection datasets.

cs.CV↗

arXiv2022

Anomalous spontaneous emission dynamics at chiral exceptional points

An open quantum system operated at the spectral singularities where dimensionality reduces, known as exceptional points (EPs), demonstrates distinguishing behavior from the Hermitian counterpart. Here, we present an analytical description of local density of states (LDOS) for microcavity featuring chiral EPs, and unveil the anomalous spontaneous emission dynamics from a quantum emitter (QE) due to the non-Lorentzian response of EPs. Specifically, we reveal that a square Lorentzian term of LDOS contributed by chiral EPs can destructively interfere with the linear Lorentzian profile, resulting in the null Purcell enhancement to a QE with special transition frequency, which we call {\it{EP induced transparency}}. While for the case of constructive interference, the square Lorentzian term can narrow the linewidth of Rabi splitting even below that of bare components, and thus significantly suppresses the decay of Rabi oscillation. Interestingly, we further find that an open microcavity with chiral EPs supports atom-photon bound states for population trapping and decay suppression in long-time dynamics. As applications, we demonstrate the advantages of microcavity operated at chiral EPs in achieving high-fidelity entanglement generation and high-efficiency single-photon generation. Our work unveils the exotic cavity quantum electrodynamics unique to chiral EPs, which opens the door for controlling light-matter interaction at the quantum level through non-Hermiticity, and holds great potential in building high-performance quantum-optics devices.

quant-ph↗

arXiv2022

YOLO5Face: Why Reinventing a Face Detector

Tremendous progress has been made on face detection in recent years using convolutional neural networks. While many face detectors use designs designated for detecting faces, we treat face detection as a generic object detection task. We implement a face detector based on the YOLOv5 object detector and call it YOLO5Face. We make a few key modifications to the YOLOv5 and optimize it for face detection. These modifications include adding a five-point landmark regression head, using a stem block at the input of the backbone, using smaller-size kernels in the SPP, and adding a P6 output in the PAN block. We design detectors of different model sizes, from an extra-large model to achieve the best performance to a super small model for real-time detection on an embedded or mobile device. Experiment results on the WiderFace dataset show that on VGA images, our face detectors can achieve state-of-the-art performance in almost all the Easy, Medium, and Hard subsets, exceeding the more complex designated face detectors. The code is available at \url{https://github.com/deepcam-cn/yolov5-face}

cs.CV↗

arXiv2021

A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images

We present an automatic COVID1-19 diagnosis framework from lung CT-scan slice images. In this framework, the slice images of a CT-scan volume are first proprocessed using segmentation techniques to filter out images of closed lung, and to remove the useless background. Then a resampling method is used to select one or multiple sets of a fixed number of slice images for training and validation. A 3D CNN network with BERT is used to classify this set of selected slice images. In this network, an embedding feature is also extracted. In cases where there are more than one set of slice images in a volume, the features of all sets are extracted and pooled into a global feature vector for the whole CT-scan volume. A simple multiple-layer perceptron (MLP) network is used to further classify the aggregated feature vector. The models are trained and evaluated on the provided training and validation datasets. On the validation dataset, the accuracy is 0.9278 and the F1 score is 0.9261.

eess.IV↗

arXiv2021

Balanced Masked and Standard Face Recognition

We present the improved network architecture, data augmentation, and training strategies for the Webface track and Insightface/Glint360K track of the masked face recognition challenge of ICCV2021. One of the key goals is to have a balanced performance of masked and standard face recognition. In order to prevent the overfitting for the masked face recognition, we control the total number of masked faces by not more than 10\% of the total face recognition in the training dataset. We propose a few key changes to the face recognition network including a new stem unit, drop block, face detection and alignment using YOLO5Face, feature concatenation, a cycle cosine learning rate, etc. With this strategy, we achieve good and balanced performance for both masked and standard face recognition.

cs.CV↗

arXiv2021

A Dataset and System for Real-Time Gun Detection in Surveillance Video Using Deep Learning

Gun violence is a severe problem in the world, particularly in the United States. Deep learning methods have been studied to detect guns in surveillance video cameras or smart IP cameras and to send a real-time alert to security personals. One problem for the development of gun detection algorithms is the lack of large public datasets. In this work, we first publish a dataset with 51K annotated gun images for gun detection and other 51K cropped gun chip images for gun classification we collect from a few different sources. To our knowledge, this is the largest dataset for the study of gun detection. This dataset can be downloaded at www.linksprite.com/gun-detection-datasets. We present a gun detection system using a smart IP camera as an embedded edge device, and a cloud server as a manager for device, data, alert, and to further reduce the false positive rate. We study to find solutions for gun detection in an embedded device, and for gun classification on the edge device and the cloud server. This edge/cloud framework makes the deployment of gun detection in the real world possible.

cs.CV↗

arXiv2019

A Joint Optimization Approach of LiDAR-Camera Fusion for Accurate Dense 3D Reconstructions

Fusing data from LiDAR and camera is conceptually attractive because of their complementary properties. For instance, camera images are higher resolution and have colors, while LiDAR data provide more accurate range measurements and have a wider Field Of View (FOV). However, the sensor fusion problem remains challenging since it is difficult to find reliable correlations between data of very different characteristics (geometry vs. texture, sparse vs. dense). This paper proposes an offline LiDAR-camera fusion method to build dense, accurate 3D models. Specifically, our method jointly solves a bundle adjustment (BA) problem and a cloud registration problem to compute camera poses and the sensor extrinsic calibration. In experiments, we show that our method can achieve an averaged accuracy of 2.7mm and resolution of 70 points per square cm by comparing to the ground truth data from a survey scanner. Furthermore, the extrinsic calibration result is discussed and shown to outperform the state-of-the-art method.

cs.RO↗

arXiv2018

Strong magneto-optical response enabled by quantum two level systems

The magneto-optical effect breaks time-reversal symmetry, a unique property that makes it indispensable in nonreciprocal optics and topological photonics. Unfortunately, all natural materials have a rather weak magneto-optical response in the optical frequency range, posing a significant challenge to the practical application of many emerging device concepts. Here we theoretically propose a composite material system that exhibits an intrinsic magneto-optical response orders of magnitude stronger than most magneto-optical materials used today. This is achieved by tailoring the resonant interplay between the quantum electrodynamics of electronic transitions in two-level systems and the classical electromagnetic response of local plasmon resonance.

physics.optics↗

arXiv2016

Atomic metasurfaces for manipulation of single photons

Metasurfaces are an emerging platform for manipulating light on a two-dimensional plane. Existing metasurfaces comprise arrays of optical resonators such as plasmonic antennas or high-index nanorods. In this letter, we describe a new approach to realize metasurfaces based on electronic transitions in two-level systems (TLSs). These metasurfaces can reproduce all of the major results in conventional metasurfaces. In addition, since TLSs can be lossless, tunable, and orders of magnitude smaller than optical resonators, atomic metasurfaces can realize functions that are difficult to achieve with optical resonators. Specifically, we develop quantum scattering theory to describe the interaction between single photons and atomic metasurfaces. Based on the theory, we use a sheet of three-level Λ-type atoms as an example and theoretically demonstrate dynamically tunable single-photon steering. We further show directional beaming of spontaneously emitted photons from atomic metasurfaces.

physics.optics↗

arXiv2016

Quantum scattering theory of Fock states in high-dimensional spaces

A quantum scattering theory is developed for Fock states scattered by two-level systems in the free space. Compared to existing scattering theories that treat incident light semi-classically, the theory fully quantizes the incident light as Fock states. This non-perturbative method provides exact scattering matrix.

physics.optics↗