arXiv subjects

Tingting Han

Publications and source records attributed to Tingting Han.

16 recordsLinked to original sources

arXiv2026

HERO: Hierarchical Embedding-Refinement for Open-Vocabulary Temporal Sentence Grounding in Videos

Temporal Sentence Grounding in Videos (TSGV) aims to temporally localize segments of a video that correspond to a given natural language query. Despite recent progress, most existing TSGV approaches operate under closed-vocabulary settings, limiting their ability to generalize to real-world queries involving novel or diverse linguistic expressions. To bridge this critical gap, we introduce the Open-Vocabulary TSGV (OV-TSGV) task and construct the first dedicated benchmarks--Charades-OV and ActivityNet-OV--that simulate realistic vocabulary shifts and paraphrastic variations. These benchmarks facilitate systematic evaluation of model generalization beyond seen training concepts. To tackle OV-TSGV, we propose HERO(Hierarchical Embedding-Refinement for Open-Vocabulary grounding), a unified framework that leverages hierarchical linguistic embeddings and performs parallel cross-modal refinement. HERO jointly models multi-level semantics and enhances video-language alignment via semantic-guided visual filtering and contrastive masked text refinement. Extensive experiments on both standard and open vocabulary benchmarks demonstrate that HERO consistently surpasses state-of-the-art methods, particularly under open-vocabulary scenarios, validating its strong generalization capability and underscoring the significance of OV-TSGV as a new research direction.

cs.CV↗

arXiv2026

FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation

Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information. However, existing methods often overlook personalized client performance and struggle with modality/task discrepancies, as well as model heterogeneity. To address these challenges, we propose FedAFD, a unified MFL framework that enhances client and server learning. On the client side, we introduce a bi-level adversarial alignment strategy to align local and global representations within and across modalities, mitigating modality and task gaps. We further design a granularity-aware fusion module to integrate global knowledge into the personalized features adaptively. On the server side, to handle model heterogeneity, we propose a similarity-guided ensemble distillation mechanism that aggregates client representations on shared public data based on feature similarity and distills the fused knowledge into the global model. Extensive experiments conducted under both IID and non-IID settings demonstrate that FedAFD achieves superior performance and efficiency for both the client and the server.

cs.LG↗

arXiv2024

Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation

Visual emotion recognition (VER), which aims at understanding humans' emotional reactions toward different visual stimuli, has attracted increasing attention. Given the subjective and ambiguous characteristics of emotion, annotating a reliable large-scale dataset is hard. For reducing reliance on data labeling, domain adaptation offers an alternative solution by adapting models trained on labeled source data to unlabeled target data. Conventional domain adaptation methods require access to source data. However, due to privacy concerns, source emotional data may be inaccessible. To address this issue, we propose an unexplored task: source-free domain adaptation (SFDA) for VER, which does not have access to source data during the adaptation process. To achieve this, we propose a novel framework termed Bridge then Begin Anew (BBA), which consists of two steps: domain-bridged model generation (DMG) and target-related model adaptation (TMA). First, the DMG bridges cross-domain gaps by generating an intermediate model, avoiding direct alignment between two VER datasets with significant differences. Then, the TMA begins training the target model anew to fit the target structure, avoiding the influence of source-specific knowledge. Extensive experiments are conducted on six SFDA settings for VER. The results demonstrate the effectiveness of BBA, which achieves remarkable performance gains compared with state-of-the-art SFDA methods and outperforms representative unsupervised domain adaptation approaches.

cs.CV↗

arXiv2024

MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability

This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are incapable of generalizing to unseen view points, MVPbev simultaneously generates cross-view consistent images of different perspective views with a two-stage design, allowing object-level control and novel view generation at test-time. Specifically, MVPbev firstly projects given BEV semantics to perspective view with camera parameters, empowering the model to generalize to unseen view points. Then we introduce a multi-view attention module where special initialization and de-noising processes are introduced to explicitly enforce local consistency among overlapping views w.r.t. cross-view homography. Last but not least, MVPbev further allows test-time instance-level controllability by refining a pre-trained text-to-image diffusion model. Our extensive experiments on NuScenes demonstrate that our method is capable of generating high-resolution photorealistic images from text descriptions with thousands of training samples, surpassing the state-of-the-art methods under various evaluation metrics. We further demonstrate the advances of our method in terms of generalizability and controllability with the help of novel evaluation metrics and comprehensive human analysis. Our code, data, and model can be found in \url{https://github.com/kkaiwwana/MVPbev}.

cs.CV↗

arXiv2023

Assessing and Improving Syntactic Adversarial Robustness of Pre-trained Models for Code Translation

Context: Pre-trained models (PTMs) have demonstrated significant potential in automatic code translation. However, the vulnerability of these models in translation tasks, particularly in terms of syntax, has not been extensively investigated. Objective: To fill this gap, our study aims to propose a novel approach CoTR to assess and improve the syntactic adversarial robustness of PTMs in code translation. Method: CoTR consists of two components: CoTR-A and CoTR-D. CoTR-A generates adversarial examples by transforming programs, while CoTR-D proposes a semantic distance-based sampling data augmentation method and adversarial training method to improve the model's robustness and generalization capabilities. The Pass@1 metric is used by CoTR to assess the performance of PTMs, which is more suitable for code translation tasks and offers a more precise evaluation in real world scenarios. Results: The effectiveness of CoTR is evaluated through experiments on real world Java to Python datasets. The results demonstrate that CoTR-A can significantly reduce the performance of existing PTMs, while CoTR-D effectively improves the robustness of PTMs. Conclusion: Our study identifies the limitations of current PTMs, including large language models, in code translation tasks. It highlights the potential of CoTR as an effective solution to enhance the robustness of PTMs for code translation tasks.

cs.SE↗

arXiv2023

A Syntax-Guided Multi-Task Learning Approach for Turducken-Style Code Generation

Due to the development of pre-trained language models, automated code generation techniques have shown great promise in recent years. However, the generated code is difficult to meet the syntactic constraints of the target language, especially in the case of Turducken-style code, where declarative code snippets are embedded within imperative programs. In this study, we summarize the lack of syntactic constraints into three significant challenges: (1) the efficient representation of syntactic constraints, (2) the effective integration of syntactic information, and (3) the scalable syntax-first decoding algorithm. To address these challenges, we propose a syntax-guided multi-task learning approach TurduckenGen. Specifically, we first explicitly append the type information to the code tokens to capture the representation of syntactic constraints. Then we formalize code generation with syntactic constraint representation as an auxiliary task to enable the model to learn the syntactic constraints of the code. Finally, the syntactically correct code is selected accurately from the multiple candidates with the help of the compiler feedback. Extensive experiments and comprehensive analysis demonstrate the effectiveness and general applicability of our approach after being compared with six state-of-the-art baselines on two Turducken-style code datasets. Finally, we conducted a human study and found the code quality generated by our approach is better than baselines in terms of code readability and semantic similarity.

cs.SE↗

arXiv2023

Test Reuse Based on Adaptive Semantic Matching across Android Mobile Applications

Automatic test generation can help verify and develop the behavior of mobile applications. Test reuse based on semantic similarities between applications of the same category has been utilized to reduce the manual effort of Graphical User Interface (GUI) testing. However, most of the existing studies fail to solve the semantic problem of event matching, which leads to the failure of test reuse. To overcome this challenge, we propose TRASM (Test Reuse based on Adaptive Semantic Matching), a test reuse approach based on adaptive strategies to find a better event matching across android mobile applications. TRASM first performs GUI events deduplication on the initial test set obtained from test generation, and then employs an adaptive strategy to find better event matching, which enables reusing the existing test. Preliminary experiments with comparison to baseline methods on 15 applications demonstrate that TRASM can improve the precision of GUI event matching while reducing the failure of test reuse and the running time required for test reuse.

cs.SE↗

arXiv2022

DRIVE: Dockerfile Rule Mining and Violation Detection

A Dockerfile defines a set of instructions to build Docker images, which can then be instantiated to support containerized applications. Recent studies have revealed a considerable amount of quality issues with Dockerfiles. In this paper, we propose a novel approach DRIVE (Dockerfiles Rule mIning and Violation dEtection) to mine implicit rules and detect potential violations of such rules in Dockerfiles. DRIVE firstly parses Dockerfiles and transforms them to an intermediate representation. It then leverages an efficient sequential pattern mining algorithm to extract potential patterns. With heuristic-based reduction and moderate human intervention, potential rules are identified, which can then be utilized to detect potential violations of Dockerfiles. DRIVE identifies 34 semantic rules and 19 syntactic rules including 9 new semantic rules which have not been reported elsewhere. Extensive experiments on real-world Dockerfiles demonstrate the efficacy of our approach.

cs.SE↗

arXiv2021

Adversarial Robustness of Deep Code Comment Generation

Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, or natural language processing. Recently they also have been applied to various software engineering tasks, typically involving processing source code. DNNs are well-known to be vulnerable to adversarial examples, i.e., fabricated inputs that could lead to various misbehaviors of the DNN model while being perceived as benign by humans. In this paper, we focus on the code comment generation task in software engineering and study the robustness issue of the DNNs when they are applied to this task. We propose ACCENT, an identifier substitution approach to craft adversarial code snippets, which are syntactically correct and semantically close to the original code snippet, but may mislead the DNNs to produce completely irrelevant code comments. In order to improve the robustness, ACCENT also incorporates a novel training method, which can be applied to existing code comment generation models. We conduct comprehensive experiments to evaluate our approach by attacking the mainstream encoder-decoder architectures on two large-scale publicly available datasets. The results show that ACCENT efficiently produces stable attacks with functionality-preserving adversarial examples, and the generated examples have better transferability compared with baselines. We also confirm, via experiments, the effectiveness in improving model robustness with our training method.

cs.SE↗

arXiv2021

Revealing the intrinsic superconducting gap anisotropy in surface-neutralized BaFe$_2$(As$_{0.7}$P$_{0.3}$)$_2$

Alkaline-earth iron arsenide (122) is one of the most studied families of iron-based superconductors, especially for angle-resolved photoemission spectroscopy. While extensive photoemission results have been obtained, the surface complexity of 122 caused by its charge-non-neutral surface is rarely considered. Here, we show that the surface of 122 can be neutralized by potassium deposition. In potassium-coated BaFe$_2$(As$_{0.7}$P$_{0.3}$)$_2$, the surface-induced spectral broadening is strongly suppressed, and hence the coherent spectra that reflect the intrinsic bulk electronic state recover. This enables the measuring of superconducting gap with unpreceded precision. The result shows the existence of two pairing channels. While the gap anisotropy on the outer hole/electron pockets can be well fitted using an s$_\pm$ gap function, the gap anisotropy on the inner hole/electron shows a clear deviation. Our results provide quantitative constraints for refining theoretical models and also demonstrate an experimental method for revealing the intrinsic electronic properties of 122 in future studies.

cond-mat.supr-con↗

arXiv2020

Finger Texture Biometric Characteristic: a Survey

\begin{abstract} In recent years, the Finger Texture (FT) has attracted considerable attention as a biometric characteristic. It can provide efficient human recognition performance, because it has different human-specific features of apparent lines, wrinkles and ridges distributed along the inner surface of all fingers. Also, such pattern structures are reliable, unique and remain stable throughout a human's life. Efficient biometric systems can be established based only on FTs. In this paper, a comprehensive survey of the relevant FT studies is presented. We also summarise the main drawbacks and obstacles of employing the FT as a biometric characteristic, and provide useful suggestions to further improve the work on FT. \end{abstract}

cs.CV↗

arXiv2018

Preferred magnetic excitations in Sr$_{1-x}$Na$_x$Fe$_2$As$_2$

We have used inelastic neutron scattering to determine magnetic excitations in a single-crystal sample of Sr$_{1-x}$Na$_x$Fe$_2$As$_2$. The material's two magnetic phases, which differ in their orthorhombic and tetragonal lattice symmetries, share very similar strengths of magnetic interactions as seen from the high-energy excitations. At low energies, excitations polarized along the $c$ axis are suppressed in the tetragonal magnetic phase, in accordance with the associated reorientation of the ordered moments. Although excitations perpendicular to the $c$ axis are still prominent, only the weak $c$-axis response exhibits a spin resonant mode in the superconducting state. Our result suggests that $c$-axis polarized magnetic excitations are important for the formation of the superconductivity, and naturally explains why the critical temperature is suppressed in the tetragonal magnetic phase.

cond-mat.supr-con↗

arXiv2017

Raman scattering study of tetragonal magnetic phase in Sr$_{1-x}$Na$_x$Fe$_2$As$_2$: structural symmetry and electronic gap

We use inelastic light scattering to study Sr$_{1-x}$Na$_x$Fe$_2$As$_2$ ($x\approx0.34$), which exhibits a robust tetragonal magnetic phase that restores the four-fold rotation symmetry inside the orthorhombic magnetic phase. With cooling, we observe splitting and recombination of an $E_g$ phonon peak upon entering the orthorhombic and tetragonal magnetic phases, respectively, consistent with the reentrant phase behavior. Our electronic Raman data reveal a pronounced feature that is clearly associated with the tetragonal magnetic phase, suggesting the opening of an electronic gap. No phonon back-folding behavior can be detected above the noise level, which implies that any lattice translation symmetry breaking in the tetragonal magnetic phase must be very weak.

cond-mat.supr-con↗

arXiv2017

Polynomial-time Algorithms for Computing Distances of Fuzzy Transition Systems

Behaviour distances to measure the resemblance of two states in a (nondeterministic) fuzzy transition system have been proposed recently in the literature. Such a distance, defined as a pseudo-ultrametric over the state space of the model, provides a quantitative analogue of bisimilarity. In this paper, we focus on the problem of computing these distances. We first extend the definition of the pseudo-ultrametric by introducing discount such that the discounting factor being equal to 1 captures the original definition. We then provide polynomial-time algorithms to calculate the behavioural distances, in both the non-discounted and the discounted setting. The algorithm is strongly polynomial in the former case. Furthermore, we give a polynomial-time algorithm to compute bisimulation over fuzzy transition systems which captures the distance being equal to 0.

cs.LO↗

arXiv2013

Modal Specifications for Probabilistic Timed Systems

Modal automata are a classic formal model for component-based systems that comes equipped with a rich specification theory supporting abstraction, refinement and compositional reasoning. In recent years, quantitative variants of modal automata were introduced for specifying and reasoning about component-based designs for embedded and mobile systems. These respectively generalize modal specification theories for timed and probabilistic systems. In this paper, we define a modal specification language for combined probabilistic timed systems, called abstract probabilistic timed automata, which generalizes existing formalisms. We introduce appropriate syntactic and semantic refinement notions and discuss consistency of our specification language, also with respect to time-divergence. We identify a subclass of our models for which we define the fundamental operations for abstraction, conjunction and parallel composition, and show several compositionality results.

cs.LO↗

arXiv2011

Model Checking of Continuous-Time Markov Chains Against Timed Automata Specifications

We study the verification of a finite continuous-time Markov chain (CTMC) C against a linear real-time specification given as a deterministic timed automaton (DTA) A with finite or Muller acceptance conditions. The central question that we address is: what is the probability of the set of paths of C that are accepted by A, i.e., the likelihood that C satisfies A? It is shown that under finite acceptance criteria this equals the reachability probability in a finite piecewise deterministic Markov process (PDP), whereas for Muller acceptance criteria it coincides with the reachability probability of terminal strongly connected components in such a PDP. Qualitative verification is shown to amount to a graph analysis of the PDP. Reachability probabilities in our PDPs are then characterized as the least solution of a system of Volterra integral equations of the second type and are shown to be approximated by the solution of a system of partial differential equations. For single-clock DTA, this integral equation system can be transformed into a system of linear equations where the coefficients are solutions of ordinary differential equations. As the coefficients are in fact transient probabilities in CTMCs, this result implies that standard algorithms for CTMC analysis suffice to verify single-clock DTA specifications.

cs.LO↗