arXiv subjects

Lin Zhu

Publications and source records attributed to Lin Zhu.

At least 109 records · Page 6Linked to original sources

arXiv2024

CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras

Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution ($346 \times 260$) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, and the newly designed neuromorphic cameras may have different resolutions. The latest neuromorphic sensors can output high-definition event streams, but it is very difficult to achieve strict alignment between events and frames on both spatial and temporal views. Therefore, how to achieve accurate tracking with unaligned neuromorphic and visible sensors is a valuable but unresearched problem. In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras. We build the first unaligned frame-event dataset CRSOT collected with a specially built data acquisition system, which contains 1,030 high-definition RGB-Event video pairs, 304,974 video frames. In addition, we propose a novel unaligned object tracking framework that can realize robust tracking even using the loosely aligned RGB-Event data. Specifically, we extract the template and search regions of RGB and Event data and feed them into a unified ViT backbone for feature embedding. Then, we propose uncertainty perception modules to encode the RGB and Event features, respectively, then, we propose a modality uncertainty fusion module to aggregate the two modalities. These three branches are jointly optimized in the training phase. Extensive experiments demonstrate that our tracker can collaborate the dual modalities for high-performance tracking even without strictly temporal and spatial alignment. The source code, dataset, and pre-trained models will be released at https://github.com/Event-AHU/Cross_Resolution_SOT.

cs.CV↗

arXiv2023

FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content

Recent advancement in personalized image generation have unveiled the intriguing capability of pre-trained text-to-image models on learning identity information from a collection of portrait images. However, existing solutions are vulnerable in producing truthful details, and usually suffer from several defects such as (i) The generated face exhibit its own unique characteristics, \ie facial shape and facial feature positioning may not resemble key characteristics of the input, and (ii) The synthesized face may contain warped, blurred or corrupted regions. In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input. Concretely, we inject several SOTA face models into the generation procedure, achieving a more efficient label-tagging, data-processing, and model post-processing compared to previous solutions, such as DreamBooth ~\cite{ruiz2023dreambooth} , InstantBooth ~\cite{shi2023instantbooth} , or other LoRA-only approaches ~\cite{hu2021lora} . Besides, based on FaceChain, we further develop several applications to build a broader playground for better showing its value, including virtual try on and 2D talking head. We hope it can grow to serve the burgeoning needs from the communities. Note that this is an ongoing work that will be consistently refined and improved upon. FaceChain is open-sourced under Apache-2.0 license at \url{https://github.com/modelscope/facechain}.

cs.CV↗

arXiv2023

A Centralized Voltage Controller for Offshore Wind Plants: NY State Grid Case Study

This paper proposes a centralized multi-plant reactive power and voltage controller to support voltage control in the interconnected onshore power system. This controller utilizes a hierarchical control structure consisting of a master controller and multiple slave controllers. To validate the proposed method, a realistic planning case of the New York State grid is created for the year 2035, in which nearly 9,500 MW AC or DC connected offshore wind resources are modeled. The performance of the proposed controller is analyzed in the large-scale model under three realistic disturbance scenarios: generator loss, load ramps, and load steps. Results demonstrate how the controller can adequately perform under disturbances to share reactive support proportionally among plants based on their ratings and improve grid voltage stability margins.

eess.SY↗

arXiv2023

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

Tracking using bio-inspired event cameras has drawn more and more attention in recent years. Existing works either utilize aligned RGB and event data for accurate tracking or directly learn an event-based tracker. The first category needs more cost for inference and the second one may be easily influenced by noisy events or sparse spatial resolution. In this paper, we propose a novel hierarchical knowledge distillation framework that can fully utilize multi-modal / multi-view information during training to facilitate knowledge transfer, enabling us to achieve high-speed and low-latency visual tracking during testing by using only event signals. Specifically, a teacher Transformer-based multi-modal tracking framework is first trained by feeding the RGB frame and event stream simultaneously. Then, we design a new hierarchical knowledge distillation strategy which includes pairwise similarity, feature representation, and response maps-based knowledge distillation to guide the learning of the student Transformer network. Moreover, since existing event-based tracking datasets are all low-resolution ($346 \times 260$), we propose the first large-scale high-resolution ($1280 \times 720$) dataset named EventVOT. It contains 1141 videos and covers a wide range of categories such as pedestrians, vehicles, UAVs, ping pongs, etc. Extensive experiments on both low-resolution (FE240hz, VisEvent, COESOT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method. The dataset, evaluation toolkit, and source code are available on \url{https://github.com/Event-AHU/EventVOT_Benchmark}

cs.CV↗

arXiv2023

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency. In practice, visible cameras can better perceive texture details and slow motion, while event cameras can be free from motion blurs and have a larger dynamic range which enables them to work well under fast motion and low illumination. Therefore, the two sensors can cooperate with each other to achieve more reliable object tracking. In this work, we propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task. Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios, and it is divided into a training and a testing subset, each of which contains 500 and 320 videos, respectively. Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods by extending current single-modality trackers into dual-modality versions. More importantly, we further build a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data. Extensive experiments on the proposed VisEvent dataset, FE108, COESOT, and two simulated datasets (i.e., OTB-DVS and VOT-DVS), validated the effectiveness of our model. The dataset and source code have been released on: \url{https://github.com/wangxiao5791509/VisEvent_SOT_Benchmark}.

cs.CV↗

arXiv2023

GlassMessaging: Supporting Messaging Needs During Daily Activities Using OST-HMDs

The act of communicating with others during routine daily tasks is both common and intuitive for individuals. However, the hands- and eyes-engaged nature of present digital messaging applications makes it difficult to message someone amidst such activities. We introduce GlassMessaging, a messaging application designed for Optical See-Through Head-Mounted Displays (OST-HMDs). It facilitates messaging through both voice and manual inputs, catering to situations where hands and eyes are preoccupied. GlassMessaging was iteratively developed through a formative study identifying current messaging behaviors and challenges in common multitasking with messaging scenarios

cs.HC↗

arXiv2023

Recurrent Spike-based Image Restoration under General Illumination

Spike camera is a new type of bio-inspired vision sensor that records light intensity in the form of a spike array with high temporal resolution (20,000 Hz). This new paradigm of vision sensor offers significant advantages for many vision tasks such as high speed image reconstruction. However, existing spike-based approaches typically assume that the scenes are with sufficient light intensity, which is usually unavailable in many real-world scenarios such as rainy days or dusk scenes. To unlock more spike-based application scenarios, we propose a Recurrent Spike-based Image Restoration (RSIR) network, which is the first work towards restoring clear images from spike arrays under general illumination. Specifically, to accurately describe the noise distribution under different illuminations, we build a physical-based spike noise model according to the sampling process of the spike camera. Based on the noise model, we design our RSIR network which consists of an adaptive spike transformation module, a recurrent temporal feature fusion module, and a frequency-based spike denoising module. Our RSIR can process the spike array in a recursive manner to ensure that the spike temporal information is well utilized. In the training process, we generate the simulated spike data based on our noise model to train our network. Extensive experiments on real-world datasets with different illuminations demonstrate the effectiveness of the proposed network. The code and dataset are released at https://github.com/BIT-Vision/RSIR.

cs.CV↗

arXiv2023

Data-Driven Fast Frequency Control using Inverter-Based Resources

To address the control challenges associated with the increasing share of inverter-connected renewable energy resources, this paper proposes a direct data-driven approach for fast frequency control in the bulk power system. The proposed control scheme partitions the power system into control areas, and leverages local dispatchable inverter-based resources to rapidly mitigate local power imbalances upon events. The controller design is based directly on historical measurement sequences, and does not require identification of a parametric power system model. Theoretical results are provided to support the approach. Simulation studies on a nonlinear three-area test system demonstrate that the controller provides fast and localized frequency control under several types of contingencies.

eess.SY↗

arXiv2023

Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction

Cellular traffic prediction is an indispensable part for intelligent telecommunication networks. Nevertheless, due to the frequent user mobility and complex network scheduling mechanisms, cellular traffic often inherits complicated spatial-temporal patterns, making the prediction incredibly challenging. Although recent advanced algorithms such as graph-based prediction approaches have been proposed, they frequently model spatial dependencies based on static or dynamic graphs and neglect the coexisting multiple spatial correlations induced by traffic generation. Meanwhile, some works lack the consideration of the diverse cellular traffic patterns, result in suboptimal prediction results. In this paper, we propose a novel deep learning network architecture, Adaptive Hybrid Spatial-Temporal Graph Neural Network (AHSTGNN), to tackle the cellular traffic prediction problem. First, we apply adaptive hybrid graph learning to learn the compound spatial correlations among cell towers. Second, we implement a Temporal Convolution Module with multi-periodic temporal data input to capture the nonlinear temporal dependencies. In addition, we introduce an extra Spatial-Temporal Adaptive Module to conquer the heterogeneity lying in cell towers. Our experiments on two real-world cellular traffic datasets show AHSTGNN outperforms the state-of-the-art by a significant margin, illustrating the superior scalability of our method for spatial-temporal cellular traffic prediction.

cs.NI↗

arXiv2022

Proposal for the search for exotic spin-spin interactions at the micrometer scale using functionalized cantilever force sensors

Spin-dependent exotic interactions can be generated by exchanging hypothetical bosons, which were introduced to solve some puzzles in physics. Many precision experiments have been performed to search for such interactions, but no confirmed observation has been made. Here, we propose new experiments to search for the exotic spin-spin interactions that can be mediated by axions or Z$^\prime$ bosons. A sensitive functionalized cantilever is utilized as a force sensor to measure the interactions between the spin-polarized electrons in a periodic magnetic source structure and a closed-loop magnetic structure integrated on the cantilever. The source is set to oscillate during data acquisition to modulate the exotic force signal to high harmonics of the oscillating frequency. This helps to suppress the spurious signals at the signal frequency. Different magnetic source structures are designed for different interaction detections. A magnetic stripe structure is designed for Z$^\prime$-mediated interaction, which is insensitive to the detection of axion-mediated interaction. This allows us to measure the coupling constant of both if we assume both exist. With the force sensitivity achievable at low temperature, the proposed experiments are expected to search for the parameter spaces with much smaller coupling constant than the current stringent constraints from micrometer to millimeter range. Specifically, the lower bound of the parameter space will be seven orders of magnitude lower than the stringent constraints for Z$^\prime$-mediated interaction, and an order of magnitude lower for axion-mediated interaction, at the interaction range of $10\, μ$m.

hep-ex↗

arXiv2022

Prompt-based Learning for Unpaired Image Captioning

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement learning. However, these existing works were only able to learn limited cross-domain information in vision and language domains, which restrains the captioning performance of UIC. Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL-PTMs for the UIC task. This research is also motivated by recent successes of prompt learning in many downstream multi-modal tasks, including image-text retrieval and vision question answering. In this work, a semantic prompt is introduced and aggregated with visual features for more accurate caption prediction under the adversarial learning framework. In addition, a metric prompt is designed to select high-quality pseudo image-caption samples obtained from the basic captioning model and refine the model in an iterative manner. Extensive experiments on the COCO and Flickr30K datasets validate the promising captioning ability of the proposed model. We expect that the proposed prompt-based UIC model will stimulate a new line of research for the VL-PTMs based captioning.

cs.CV↗

arXiv2022

A greedy randomized average block projection method for linear feasibility problems

The randomized projection (RP) method is a simple iterative scheme for solving linear feasibility problems and has recently gained popularity due to its speed and low memory requirement. This paper develops an accelerated variant of the standard RP method by using two ingredients: the greedy probability criterion and the average block approach, and obtains a greedy randomized average block projection (GRABP) method for solving large-scale systems of linear inequalities. We prove that this method converges linearly in expectation under different choices of extrapolated stepsizes. Numerical experiments on both randomly generated and real-world data show the advantage of GRABP over several state-of-the-art solvers, such as the randomized projection (RP) method, the sampling Kaczmarz Motzkin (SKM) method, the generalized SKM (GSKM) method, and the Nesterov acceleration of SKM method.

math.OC↗

arXiv2022

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption. Meanwhile, the biologically inspired event cameras attracted great interest due to their unique features, such as high dynamic range, dense temporal but sparse spatial resolution, low latency, low power, etc. As it is a newly arising sensor, even there is no realistic large-scale dataset for HAR. Considering its great practical value, in this paper, we propose a large-scale benchmark dataset to bridge this gap, termed HARDVS, which contains 300 categories and more than 100K event sequences. We evaluate and report the performance of multiple popular HAR algorithms, which provide extensive baselines for future works to compare. More importantly, we propose a novel spatial-temporal feature learning and fusion framework, termed ESTF, for event stream based human activity recognition. It first projects the event streams into spatial and temporal embeddings using StemNet, then, encodes and fuses the dual-view representations using Transformer networks. Finally, the dual features are concatenated and fed into a classification head for activity prediction. Extensive experiments on multiple datasets fully validated the effectiveness of our model. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/HARDVS}.

cs.CV↗

arXiv2022

Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity

Most of the existing learning-based deraining methods are supervisedly trained on synthetic rainy-clean pairs. The domain gap between the synthetic and real rain makes them less generalized to complex real rainy scenes. Moreover, the existing methods mainly utilize the property of the image or rain layers independently, while few of them have considered their mutually exclusive relationship. To solve above dilemma, we explore the intrinsic intra-similarity within each layer and inter-exclusiveness between two layers and propose an unsupervised non-local contrastive learning (NLCL) deraining method. The non-local self-similarity image patches as the positives are tightly pulled together, rain patches as the negatives are remarkably pushed away, and vice versa. On one hand, the intrinsic self-similarity knowledge within positive/negative samples of each layer benefits us to discover more compact representation; on the other hand, the mutually exclusive property between the two layers enriches the discriminative decomposition. Thus, the internal self-similarity within each layer (similarity) and the external exclusive relationship of the two layers (dissimilarity) serving as a generic image prior jointly facilitate us to unsupervisedly differentiate the rain from clean image. We further discover that the intrinsic dimension of the non-local image patches is generally higher than that of the rain patches. This motivates us to design an asymmetric contrastive loss to precisely model the compactness discrepancy of the two layers for better discriminative decomposition. In addition, considering that the existing real rain datasets are of low quality, either small scale or downloaded from the internet, we collect a real large-scale dataset under various rainy kinds of weather that contains high-resolution rainy images.

cs.CV↗

arXiv2022

Temporal Up-Sampling for Asynchronous Events

The event camera is a novel bio-inspired vision sensor. When the brightness change exceeds the preset threshold, the sensor generates events asynchronously. The number of valid events directly affects the performance of event-based tasks, such as reconstruction, detection, and recognition. However, when in low-brightness or slow-moving scenes, events are often sparse and accompanied by noise, which poses challenges for event-based tasks. To solve these challenges, we propose an event temporal up-sampling algorithm1 to generate more effective and reliable events. The main idea of our algorithm is to generate up-sampling events on the event motion trajectory. First, we estimate the event motion trajectory by contrast maximization algorithm and then up-sampling the events by temporal point processes. Experimental results show that up-sampling events can provide more effective information and improve the performance of downstream tasks, such as improving the quality of reconstructed images and increasing the accuracy of object detection.

cs.CV↗

arXiv2022

Data-Driven Fast Frequency Control using Inverter-Based Resources

We develop and test a data-driven and area-based fast frequency control scheme, which rapidly redispatches inverter-based resources to compensate for local power imbalances within the bulk power system. The approach requires no explicit system model information, relying only on historical measurement sequences for the computation of control actions. Our technical approach fuses developments in low-gain estimator design and data-driven control to provide a model-free and practical solution for fast frequency control. Theoretical results and extensive simulation scenarios on a three area system are provided to support the approach.

eess.SY↗

arXiv2022

Mirror Complementary Transformer Network for RGB-thermal Salient Object Detection

RGB-thermal salient object detection (RGB-T SOD) aims to locate the common prominent objects of an aligned visible and thermal infrared image pair and accurately segment all the pixels belonging to those objects. It is promising in challenging scenes such as nighttime and complex backgrounds due to the insensitivity to lighting conditions of thermal images. Thus, the key problem of RGB-T SOD is to make the features from the two modalities complement and adjust each other flexibly, since it is inevitable that any modalities of RGB-T image pairs failure due to challenging scenes such as extreme light conditions and thermal crossover. In this paper, we propose a novel mirror complementary Transformer network (MCNet) for RGB-T SOD. Specifically, we introduce a Transformer-based feature extraction module to effective extract hierarchical features of RGB and thermal images. Then, through the attention-based feature interaction and serial multiscale dilated convolution (SDC) based feature fusion modules, the proposed model achieves the complementary interaction of low-level features and the semantic fusion of deep features. Finally, based on the mirror complementary structure, the salient regions of the two modalities can be accurately extracted even one modality is invalid. To demonstrate the robustness of the proposed model under challenging scenes in real world, we build a novel RGB-T SOD dataset VT723 based on a large public semantic segmentation RGB-T dataset used in the autonomous driving domain. Expensive experiments on benchmark and VT723 datasets show that the proposed method outperforms state-of-the-art approaches, including CNN-based and Transformer-based methods. The code and dataset will be released later at https://github.com/jxr326/SwinMCNet.

cs.CV↗

arXiv2022

Noise and Edge Based Dual Branch Image Manipulation Detection

Unlike ordinary computer vision tasks that focus more on the semantic content of images, the image manipulation detection task pays more attention to the subtle information of image manipulation. In this paper, the noise image extracted by the improved constrained convolution is used as the input of the model instead of the original image to obtain more subtle traces of manipulation. Meanwhile, the dual-branch network, consisting of a high-resolution branch and a context branch, is used to capture the traces of artifacts as much as possible. In general, most manipulation leaves manipulation artifacts on the manipulation edge. A specially designed manipulation edge detection module is constructed based on the dual-branch network to identify these artifacts better. The correlation between pixels in an image is closely related to their distance. The farther the two pixels are, the weaker the correlation. We add a distance factor to the self-attention module to better describe the correlation between pixels. Experimental results on four publicly available image manipulation datasets demonstrate the effectiveness of our model.

cs.CV↗