arXiv subjects

Chao Liang

Publications and source records attributed to Chao Liang.

At least 55 records · Page 3Linked to original sources

arXiv2024

What Would Happen Next? Predicting Consequences from An Event Causality Graph

Existing script event prediction task forcasts the subsequent event based on an event script chain. However, the evolution of historical events are more complicated in real world scenarios and the limited information provided by the event script chain also make it difficult to accurately predict subsequent events. This paper introduces a Causality Graph Event Prediction(CGEP) task that forecasting consequential event based on an Event Causality Graph (ECG). We propose a Semantic Enhanced Distance-sensitive Graph Prompt Learning (SeDGPL) Model for the CGEP task. In SeDGPL, (1) we design a Distance-sensitive Graph Linearization (DsGL) module to reformulate the ECG into a graph prompt template as the input of a PLM; (2) propose an Event-Enriched Causality Encoding (EeCE) module to integrate both event contextual semantic and graph schema information; (3) propose a Semantic Contrast Event Prediction (ScEP) module to enhance the event representation among numerous candidate events and predict consequential event following prompt learning paradigm. %We construct two CGEP datasets based on existing MAVEN-ERE and ESC corpus for experiments. Experiment results validate our argument our proposed SeDGPL model outperforms the advanced competitors for the CGEP task.

cs.AI↗

arXiv2024

IDRetracor: Towards Visual Forensics Against Malicious Face Swapping

The face swapping technique based on deepfake methods poses significant social risks to personal identity security. While numerous deepfake detection methods have been proposed as countermeasures against malicious face swapping, they can only output binary labels (Fake/Real) for distinguishing fake content without reliable and traceable evidence. To achieve visual forensics and target face attribution, we propose a novel task named face retracing, which considers retracing the original target face from the given fake one via inverse mapping. Toward this goal, we propose an IDRetracor that can retrace arbitrary original target identities from fake faces generated by multiple face swapping methods. Specifically, we first adopt a mapping resolver to perceive the possible solution space of the original target face for the inverse mappings. Then, we propose mapping-aware convolutions to retrace the original target face from the fake one. Such convolutions contain multiple kernels that can be combined under the control of the mapping resolver to tackle different face swapping mappings dynamically. Extensive experiments demonstrate that the IDRetracor exhibits promising retracing performance from both quantitative and qualitative perspectives.

cs.CV↗

arXiv2024

Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking

Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task (ReID) into the detector, achieving a balance between inference speed and tracking performance. However, solving the competition between the detector and the feature extractor has always been a challenge. Meanwhile, the issue of directly embedding the ReID task into MOT has remained unresolved. The lack of high discriminability in appearance features results in their limited utility. In this paper, a new learning approach using cross-correlation to capture temporal information of objects is proposed. The feature extraction network is no longer trained solely on appearance features from each frame but learns richer motion features by utilizing feature heatmaps from consecutive frames, which addresses the challenge of inter-class feature similarity. Furthermore, our learning approach is applied to a more lightweight feature extraction network, and treat the feature matching scores as strong cues rather than auxiliary cues, with an appropriate weight calculation to reflect the compatibility between our obtained features and the MOT task. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks, i.e., MOT17, MOT20, and DanceTrack datasets. Specifically, on the DanceTrack test set, we achieve 56.8 HOTA, 58.1 IDF1 and 92.5 MOTA, making it the best online tracker capable of achieving real-time performance. Comparative evaluations with other trackers prove that our tracker achieves the best balance between speed, robustness and accuracy. Code is available at https://github.com/yfzhang1214/TCBTrack.

cs.CV↗

arXiv2024

On the phenomenon of topological chaos and statistical triviality

There exists a compact manifold so that the set of topologically chaotic but statistically trivial $C^{r} (1\leq r \leq \infty)$ vector fields on this manifold displays considerable scale in the view of dimension. More specifically, it contains an infinitely dimensional connected subset.

math.DS↗

arXiv2024

Revealing spontaneous symmetry breaking in continuous time crystals

Spontaneous symmetry breaking plays a pivotal role in physics ranging from the emergence of elementary particles to the phase transitions of matter. The spontaneous breaking of continuous time translation symmetry leads to a novel state of matter named continuous time crystal (CTC). It exhibits periodic oscillation without the need for periodic driving, and the relative phases for repetitively realized oscillations are random. However, the mechanism behind the spontaneous symmetry breaking in CTCs, particularly the random phases, remains elusive. Here we propose and experimentally realize two types of CTCs based on distinct mechanisms: manifold topology and near-chaotic motion. We observe both types of CTCs in thermal atomic ensembles by artificially synthesizing spin-spin nonlinear interactions through a measurement-feedback scheme. Our work provides general recipes for the realization of CTCs, and paves the way for exploring CTCs in various systems.

quant-ph↗

arXiv2024

Dissipative time crystal in a strongly interacting Rydberg gas

The notion of spontaneous symmetry breaking has been well established to characterize classical and quantum phase transitions of matter, such as in condensation, crystallization or quantum magnetism. Generalizations of this paradigm to the time dimension can lead to a time crystal phase, which spontaneously breaks the time translation symmetry of the system. Whereas the existence of a continuous time crystal at equilibrium has been challenged by no-go theorems, this difficulty can be circumvented by dissipation in an open system. Here, we report the experimental observation of such dissipative time crystalline order in a room-temperature atomic gas, where ground-state atoms are continuously driven to Rydberg states. The emergent time crystal is revealed by persistent oscillations of the photon transmission, and we show that the observed limit cycles arise from the coexistence and competition between distinct Rydberg components. The nondecaying autocorrelation of the oscillation, together with the robustness against temporal noises, indicate the establishment of true long-range temporal order and demonstrates the realization of a continuous time crystal.

cond-mat.quant-gas↗

arXiv2024

CapHuman: Capture Your Moments in Parallel Universes

We concentrate on a novel human-centric image synthesis task, that is, given only one reference facial photograph, it is expected to generate specific individual images with diverse head positions, poses, facial expressions, and illuminations in different contexts. To accomplish this goal, we argue that our generative model should be capable of the following favorable characteristics: (1) a strong visual and semantic understanding of our world and human society for basic object and human image generation. (2) generalizable identity preservation ability. (3) flexible and fine-grained head control. Recently, large pre-trained text-to-image diffusion models have shown remarkable results, serving as a powerful generative foundation. As a basis, we aim to unleash the above two capabilities of the pre-trained model. In this work, we present a new framework named CapHuman. We embrace the "encode then learn to align" paradigm, which enables generalizable identity preservation for new individuals without cumbersome tuning at inference. CapHuman encodes identity features and then learns to align them into the latent space. Moreover, we introduce the 3D facial prior to equip our model with control over the human head in a flexible and 3D-consistent manner. Extensive qualitative and quantitative analyses demonstrate our CapHuman can produce well-identity-preserved, photo-realistic, and high-fidelity portraits with content-rich representations and various head renditions, superior to established baselines. Code and checkpoint will be released at https://github.com/VamosC/CapHuman.

cs.CV↗

arXiv2024

Superior and Pragmatic Talking Face Generation with Teacher-Student Framework

Talking face generation technology creates talking videos from arbitrary appearance and motion signal, with the "arbitrary" offering ease of use but also introducing challenges in practical applications. Existing methods work well with standard inputs but suffer serious performance degradation with intricate real-world ones. Moreover, efficiency is also an important concern in deployment. To comprehensively address these issues, we introduce SuperFace, a teacher-student framework that balances quality, robustness, cost and editability. We first propose a simple but effective teacher model capable of handling inputs of varying qualities to generate high-quality results. Building on this, we devise an efficient distillation strategy to acquire an identity-specific student model that maintains quality with significantly reduced computational load. Our experiments validate that SuperFace offers a more comprehensive solution than existing methods for the four mentioned objectives, especially in reducing FLOPs by 99\% with the student model. SuperFace can be driven by both video and audio and allows for localized facial attributes editing.

cs.CV↗

arXiv2023

HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation Methods

Talking Face Generation (TFG) aims to reconstruct facial movements to achieve high natural lip movements from audio and facial features that are under potential connections. Existing TFG methods have made significant advancements to produce natural and realistic images. However, most work rarely takes visual quality into consideration. It is challenging to ensure lip synchronization while avoiding visual quality degradation in cross-modal generation methods. To address this issue, we propose a universal High-Definition Teeth Restoration Network, dubbed HDTR-Net, for arbitrary TFG methods. HDTR-Net can enhance teeth regions at an extremely fast speed while maintaining synchronization, and temporal consistency. In particular, we propose a Fine-Grained Feature Fusion (FGFF) module to effectively capture fine texture feature information around teeth and surrounding regions, and use these features to fine-grain the feature map to enhance the clarity of teeth. Extensive experiments show that our method can be adapted to arbitrary TFG methods without suffering from lip synchronization and frame coherence. Another advantage of HDTR-Net is its real-time generation ability. Also under the condition of high-definition restoration of talking face video synthesis, its inference speed is $300\%$ faster than the current state-of-the-art face restoration based on super-resolution.

cs.CV↗

arXiv2023

Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition

In real-world scenarios, collected and annotated data often exhibit the characteristics of multiple classes and long-tailed distribution. Additionally, label noise is inevitable in large-scale annotations and hinders the applications of learning-based models. Although many deep learning based methods have been proposed for handling long-tailed multi-label recognition or label noise respectively, learning with noisy labels in long-tailed multi-label visual data has not been well-studied because of the complexity of long-tailed distribution entangled with multi-label correlation. To tackle such a critical yet thorny problem, this paper focuses on reducing noise based on some inherent properties of multi-label classification and long-tailed learning under noisy cases. In detail, we propose a Stitch-Up augmentation to synthesize a cleaner sample, which directly reduces multi-label noise by stitching up multiple noisy training samples. Equipped with Stitch-Up, a Heterogeneous Co-Learning framework is further designed to leverage the inconsistency between long-tailed and balanced distributions, yielding cleaner labels for more robust representation learning with noisy long-tailed data. To validate our method, we build two challenging benchmarks, named VOC-MLT-Noise and COCO-MLT-Noise, respectively. Extensive experiments are conducted to demonstrate the effectiveness of our proposed method. Compared to a variety of baselines, our method achieves superior results.

cs.CV↗

arXiv2023

Observation of Exceptional Points in Thermal Atomic Ensembles

Exceptional points (EPs) in non-Hermitian systems have recently attracted wide interests and spawned intriguing prospects for enhanced sensing. However, EPs have not yet been realized in thermal atomic ensembles, which is one of the most important platforms for quantum sensing. Here we experimentally observe EPs in multi-level thermal atomic ensembles, and realize enhanced sensing of magnetic field for one order of magnitude. We take advantage of the rich energy levels of atoms and construct effective decays for selected energy levels by employing laser coupling with the excited state, yielding unbalanced decay rates for different energy levels, which finally results in the existence of EPs. Furthermore, we propose the optical polarization rotation measurement scheme to detect the splitting of the resonance peaks, which makes use of both the absorption and dispersion properties, and shows advantage with enhanced splitting compared with the conventional transmission measurement scheme. Besides, in our system both the effective coupling strength and decay rates are flexibly adjustable, and thus the position of the EPs are tunable, which expands the measurement range. Our work not only provides a new controllable platform for studying EPs and non-Hermitian physics, but also provide new ideas for the design of EP-enhanced sensors and opens up realistic opportunities for practical applications in the high-precision sensing of magnetic field and other physical quantities.

quant-ph↗

arXiv2023

TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition

Implicit Discourse Relation Recognition (IDRR) aims at classifying the relation sense between two arguments without an explicit connective. Recently, the ConnPrompt~\cite{Wei.X:et.al:2022:COLING} has leveraged the powerful prompt learning for IDRR based on the fusion of multi-prompt decisions from three different yet much similar connective prediction templates. Instead of multi-prompt ensembling, we propose to design auxiliary tasks with enlightened prompt learning for the IDRR task. Although an auxiliary task is not used to directly output final prediction, we argue that during the joint training some of its learned features can be useful to boost the main task. In light of such motivations, we propose a task enlightenment prompt learning model, called TEPrompt, to fuse learned features from three related tasks for IDRR. In particular, the TEPrompt contains three tasks, viz., Discourse Relation Recognition (DRR), Sense Semantics Classification (SSC) and Annotated Connective Prediction (ACP), each with a unique prompt template and an answer space. In the training phase, we jointly train three prompt learning tasks with shared argument representation. In the testing phase, we only take the DRR output with fused features as the final IDRR decision. Experiments with the same conditions have shown that the proposed TEPrompt outperforms the ConnPrompt. This can be attributed to the promoted decision features and language models benefited from joint-training of auxiliary tasks.

cs.CL↗

arXiv2023

PT-symmetric feedback induced linewidth narrowing

Narrow linewidth is a long-pursuing goal in precision measurement and sensing. We propose a parity-time (PT )-symmetric feedback method to narrow the linewidths of resonance systems. By using a quadrature measurement-feedback loop, we transform a dissipative resonance system into a PT-symmetric system. Unlike the conventional PT-symmetric systems which typically require two or more modes, here the PT-symmetric feedback system contains only a single resonance mode, which greatly extends the scope of applications. The method enables remarkable linewidth narrowing and enhancement of measurement sensitivity. We illustrate the concept in a thermal ensemble of atoms, achieving a 48-fold narrowing of the magnetic resonance linewidth. By applying the method in magnetometry, we realize a 22-times improvement of the measurement sensitivity. This work opens the avenue for studying non-Hermitian physics and high-precision measurements in resonance systems with feedback.

physics.optics↗

arXiv2023

Shub's example revisited

For a class of robustly transitive diffeomorphisms on $\mathbb T^4$ introduced by Shub in [24], satisfying an additional bunching condition, we show that there exits a $C^2$ open and $C^r$ dense subset $\mathcal U^r$, $2\leq r\leq\infty$, such that any two hyperbolic points of $g\in \mathcal U^r$ with stable index $2$ are homoclinically related. As a consequence, every $g\in \mathcal U^r$ admits a unique homoclinic class associated to the hyperbolic periodic points with index $2$, and this homoclinic class coincides to the whole ambient manifold. Moreover, every $g\in \mathcal U^r$ admits at most one measure with maximal entropy, and every $g\in\mathcal U^{\infty}$ admits a unique measure of maximal entropy.

math.DS↗

arXiv2023

Nanoparticles Passive Targeting Allows Optical Imaging of Bone Diseases

Bone health related skeletal disorders are commonly diagnosed by X-ray imaging, but the radiation limits its use. Light excitation and optical imaging through the near-infrared-II window (NIR-II, 1000-1700 nm) can penetrate deep tissues without radiation risk, but the targeting of contrast agent is non-specific. Here, we report that lanthanide-doped nanocrystals can be passively transported by endothelial cells and macrophages from the blood vessels into bone marrow microenvironment. We found that this passive targeting scheme can be effective for longer than two months. We therefore developed an intravital 3D and high-resolution planar imaging instrumentation for bone disease diagnosis. We demonstrated the regular monitoring of 1 mm bone defects for over 10 days, with resolution similar to X-ray imaging result, but more flexible use in prognosis. Moreover, the passive targeting can be used to reveal the early onset inflammation at the joints as the synovitis in the early stage of rheumatoid arthritis. Furthermore, the proposed method is comparable to μCT in recognizing symptoms of osteoarthritis, including the mild hyperostosis in femur which is ~100 μm thicker than normal, and the growth of millimeter-scale osteophyte in the knee joint, which further proves the power and universality of our approach in diagnosis of bone diseases

physics.bio-ph↗

arXiv2022

Confidence-Aware Active Feedback for Interactive Instance Search

Online relevance feedback (RF) is widely utilized in instance search (INS) tasks to further refine imperfect ranking results, but it often has low interaction efficiency. The active learning (AL) technique addresses this problem by selecting valuable feedback candidates. However, mainstream AL methods require an initial labeled set for a cold start and are often computationally complex to solve. Therefore, they cannot fully satisfy the requirements for online RF in interactive INS tasks. To address this issue, we propose a confidence-aware active feedback method (CAAF) that is specifically designed for online RF in interactive INS tasks. Inspired by the explicit difficulty modeling scheme in self-paced learning, CAAF utilizes a pairwise manifold ranking loss to evaluate the ranking confidence of each unlabeled sample. The ranking confidence improves not only the interaction efficiency by indicating valuable feedback candidates but also the ranking quality by modulating the diffusion weights in manifold ranking. In addition, we design two acceleration strategies, an approximate optimization scheme and a top-K search scheme, to reduce the computational complexity of CAAF. Extensive experiments on both image INS tasks and video INS tasks searching for buildings, landscapes, persons, and human behaviors demonstrate the effectiveness of the proposed method. Notably, in the real-world, large-scale video INS task of NIST TRECVID 2021, CAAF uses 25% fewer feedback samples to achieve a performance that is nearly equivalent to the champion solution. Moreover, with the same number of feedback samples, CAAF's mAP is 51.9%, significantly surpassing the champion solution by 5.9%. Code is available at https://github.com/nercms-mmap/caaf.

cs.CV↗

arXiv2022

whu-nercms at trecvid2021:instance search task

We will make a brief introduction of the experimental methods and results of the WHU-NERCMS in the TRECVID2021 in the paper. This year we participate in the automatic and interactive tasks of Instance Search (INS). For the automatic task, the retrieval target is divided into two parts, person retrieval, and action retrieval. We adopt a two-stage method including face detection and face recognition for person retrieval and two kinds of action detection methods consisting of three frame-based human-object interaction detection methods and two video-based general action detection methods for action retrieval. After that, the person retrieval results and action retrieval results are fused to initialize the result ranking lists. In addition, we make attempts to use complementary methods to further improve search performance. For interactive tasks, we test two different interaction strategies on the fusion results. We submit 4 runs for automatic and interactive tasks respectively. The introduction of each run is shown in Table 1. The official evaluations show that the proposed strategies rank 1st in both automatic and interactive tracks.

cs.CV↗

arXiv2022

Rethinking the competition between detection and ReID in Multi-Object Tracking

Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS.

cs.CV↗