arXiv subjects

Dan Jiang

Publications and source records attributed to Dan Jiang.

13 recordsLinked to original sources

arXiv2026

EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration

The rapid proliferation of artificial intelligence-generated content necessitates reliable multimodal forensics. Beyond video-level binary classification, precisely localizing sparsely distributed forged segments in long-form videos remains a critical challenge. This task is particularly difficult when manipulations are subtly embedded and cross-modal signals are weak and temporally diffuse. To address these challenges, we propose EVAS, an end-to-end multimodal framework for temporal forgery localization. At its core, a Multi-Stage Audio-Visual Synergy mechanism facilitates progressive cross-modal interaction to learn deep multimodal forensic representations and capture high-order semantic traces of sparse manipulations. Furthermore, we introduce a Boundary-Aware Refinement strategy to achieve steered boundary calibration. By incorporating invalid-frame masking, this strategy suppresses ambiguous regions and sharpens transition predictions. We adopt a decoupled training paradigm with auxiliary heads to disentangle representation learning from inference objectives, enhancing model generalization and stability. Additionally, a lightweight HourglassFFN is incorporated to reduce computational overhead. Extensive experiments demonstrate that EVAS achieves state-of-the-art average localization accuracy and average recall across three benchmark datasets, validating its effectiveness for fine-grained temporal forgery localization.

cs.CV↗

arXiv2026

UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization

With the proliferation of AI-generated content, sophisticated multimedia manipulation has raised critical concerns about malicious applications such as opinion manipulation and evidence fabrication, making Audio-Visual Temporal Forgery Localization (AV-TFL) an urgent research frontier. Existing TFL methods have progressed along two main paradigms: Transformer-based temporal modeling and channel-wise multimodal fusion. While these approaches capture temporal dependencies and cross-modal correlations, they process all frequency components indiscriminately, leading to overfitting on high-frequency noise and limited robustness under real-world data degradation. Through systematic frequency domain analysis, we find that forgery-discriminative patterns concentrate in the low/mid-frequency range (normalized frequency 0-0.15), while high-frequency components primarily introduce noise, removing them even improves detection performance by +1.4%. Based on this phenomenon, we propose UniSkip-Mamba, a frequency-aware State Space Model framework that incorporates Unified Multimodal Sequence Fusion to preserve cross-modal phase relationships, and Skip-Scanning Mamba Blocks that implement frequency-aware regularization through a novel Group-Scan-Merge mechanism, naturally biasing learning toward discriminative low/mid-frequency patterns (0-0.15) while maintaining representational completeness. We achieve state-of-the-art (SOTA) performance: 63.4% AP@0.95 on LAV-DF (+9.8% improvement) and 63.58% mAP on AV-Deepfake1M (+14.32% improvement), with 6x faster inference. Our frequency-domain analysis provides theoretical justification from a signal processing perspective for why skip-scanning inherently improves both accuracy and robustness.

cs.CV↗

arXiv2026

MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization

Driven by Artificial Intelligence-Generated Content (AIGC), the authenticity of audio-visual content is facing severe challenges. Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments within untrimmed sequences. However, existing methods are limited by CNNs' local receptive fields or Transformers' quadratic complexity, while emerging linear models often struggle to balance global authentic context compression with local abrupt forgery perception. To address this, we propose MG-RWKV, a multi-granularity framework that leverages the data-dependent state evolution of RWKV to achieve efficient full-sequence processing with O(T) complexity. Our framework features three core innovations: (1) a Bidirectional RWKV architecture that captures bidirectional temporal contexts without quadratic overhead; (2) a Multi-Granularity Mixture of Experts (MG-MoE) that performs dynamic routing over explicit temporal receptive fields, adaptively selecting granularities based on forgery duration to significantly enhance decision interpretability; and (3) Cross-Granularity Consistency (CGC), which aligns adjacent feature pyramid levels through hierarchical scale-wise pairing and spatial boundary-aware weighting, effectively reducing false positives in authentic regions. Extensive experiments on Lav-DF, TVIL, and Psynd datasets demonstrate that MG-RWKV achieves state-of-the-art performance with low computational cost.

cs.CV↗

arXiv2026

Evidence for New $D_s$-Family Molecular States

Motivated by the observed $KD^{(*)}$ molecular candidates $D_{s0}(2317)$ and $D_{s1}(2460)$, their bottom--strange counterparts, $K\bar{B}^{(*)}$ molecular states, are naturally expected, although not yet experimentally established. This discrepancy may reflect sizable heavy-quark flavor symmetry breaking, which introduces significant model uncertainties. Current studies of heavy-quark flavor symmetry breaking effects still exhibit strong parameter dependence, and further experimental input is required to constrain these effects, in particular regarding possible additional $K^{(*)}D^{(*)}$ and $K^{(*)}\bar{B}^{(*)}$ molecular states. In this work, we examine whether additional $K^{*}D^{(*)}$ molecular states can be identified among the observed $D_s$ resonances. Within the Gaussian expansion method, we solve the Schr\"{o}dinger equation using $\sigma$, $\rho$, $\omega$, $\pi$, and $\eta$ exchange potentials, systematically including $S$-wave and higher partial waves. We find that $D_{s1}(2700)$ can be interpreted as a pure $P$-wave $DK^{*}$ molecule, while $D_{s1}(2860)$ and $D_{s3}(2860)$ are well described as $D^{*}K^{*}$ molecular states dominated by the $^{1}P_{1}$ and $^{5}P_{3}$ components, respectively. We also predict additional molecular states with various $J^{P}$ quantum numbers. These results provide a new description of the charmed-strange spectrum, and once confirmed will provide additional input data for studies of heavy-quark flavor symmetry breaking effects.

hep-ph↗

arXiv2026

The possible $K^{}\Sigma^{}$ molecular state

Within the framework of the one-boson-exchange model, we systematically investigate the interaction between the vector meson $K^{*}$ and the baryon $\Sigma^{*}$ with the aim of exploring the possibility of forming hadronic molecular states. The $K^{*}\Sigma^{*}$ interaction potential is constructed from $\rho$, $\omega$, and $\pi$ meson exchanges, and the nonrelativistic Schr\"odinger equation is solved using the Gaussian expansion method. The binding energies are calculated for different total angular momenta $J^{P}$ and isospin channels $I=1/2$ and $I=3/2$. Our results show that $S$--$D$ wave mixed $K^{*}\Sigma^{*}$ molecular states with $J^{P}=1/2^{-}$ can be formed only in the $I=3/2$ channel, while no bound state appears in the $I=1/2$ channel. In addition, the $S$--$D$ wave mixed states with $J^{P}=3/2^{-}$ and $J^{P}=5/2^{-}$ are also found to support bound-state solutions. For higher partial-wave states in our study, the binding mechanism mainly arises from the interplay between partial-wave mixing and non-central interactions. In particular, the $J^{P}=1/2^{+}$ channel does not support a bound state, as the meson-exchange interaction is predominantly repulsive. Our analysis further supports the interpretation of the experimentally observed $N(2250)$ and $\Delta(2200)$ states as $K^{*}\Sigma^{*}$ molecular candidates, corresponding to $I=1/2,\ J^{P}=9/2^{-}$ and $I=3/2,\ J^{P}=7/2^{-}$, respectively.

hep-ph↗

arXiv2026

FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods, existing weakly-supervised COD methods exhibit significantly poorer performance. Even for the Segment Anything Model (SAM), there are still challenges in handling weakly-supervised camouflage object detection (WSCOD), such as: a. non-camouflage target responses, b. local responses, c. extreme responses, and d. lack of refined boundary awareness, which leads to unsatisfactory results in camouflage scenes. To alleviate these issues, we propose a frequency-aware and contrastive learning-based WSCOD framework in this paper, named FCL-COD. To mitigate the problem of non-camouflaged object responses, we propose the Frequency-aware Low-rank Adaptation (FoRA) method, which incorporates frequency-aware camouflage scene knowledge into SAM. To overcome the challenges of local and extreme responses, we introduce a gradient-aware contrastive learning approach that effectively delineates precise foreground-background boundaries. Additionally, to address the lack of refined boundary perception, we present a multi-scale frequency-aware representation learning strategy that facilitates the modeling of more refined boundaries. We validate the effectiveness of our approach through extensive empirical experiments on three widely recognized COD benchmarks. The results confirm that our method surpasses both state-of-the-art weakly supervised and even fully supervised techniques.

cs.CV↗

arXiv2025

Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations

Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62).

cs.CV↗

arXiv2025

MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models

Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the scientific domain have played an important role in assessing the reasoning capabilities of MLLMs. However, existing benchmarks still face three key challenges: 1) Insufficient evaluation of models' reasoning abilities in multilingual scenarios; 2) Inadequate assessment of MLLMs' comprehensive modality coverage; 3) Lack of fine-grained annotation of scientific knowledge points. To address these gaps, we propose MME-SCI, a comprehensive and challenging benchmark. We carefully collected 1,019 high-quality question-answer pairs, which involve 3 distinct evaluation modes. These pairs cover four subjects, namely mathematics, physics, chemistry, and biology, and support five languages: Chinese, English, French, Spanish, and Japanese. We conducted extensive experiments on 16 open-source models and 4 closed-source models, and the results demonstrate that MME-SCI is widely challenging for existing MLLMs. For instance, under the Image-only evaluation mode, o4-mini achieved accuracy of only 52.11%, 24.73%, 36.57%, and 29.80% in mathematics, physics, chemistry, and biology, respectively, indicating a significantly higher difficulty level compared to existing benchmarks. More importantly, using MME-SCI's multilingual and fine-grained knowledge attributes, we analyzed existing models' performance in depth and identified their weaknesses in specific domains. The Data and Evaluation Code are available at https://github.com/JCruan519/MME-SCI.

cs.CL↗

arXiv2025

CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive and time-consuming. Consequently, unsupervised temporal action localization (UTAL) has gained popularity. However, current methods face two main challenges: 1) Classification pre-trained features overly focus on highly discriminative regions; 2) Solely relying on visual modality information makes it difficult to determine contextual boundaries. To address these issues, we propose a CLIP-assisted cross-view audiovisual enhanced UTAL method. Specifically, we introduce visual language pre-training (VLP) and classification pre-training-based collaborative enhancement to avoid excessive focus on highly discriminative regions; we also incorporate audio perception to provide richer contextual boundary information. Finally, we introduce a self-supervised cross-view learning paradigm to achieve multi-view perceptual enhancement without additional annotations. Extensive experiments on two public datasets demonstrate our model's superiority over several state-of-the-art competitors.

cs.CV↗

arXiv2019

Off-Policy Evaluation of Probabilistic Identity Data in Lookalike Modeling

We evaluate the impact of probabilistically-constructed digital identity data collected from Sep. to Dec. 2017 (approx.), in the context of Lookalike-targeted campaigns. The backbone of this study is a large set of probabilistically-constructed "identities", represented as small bags of cookies and mobile ad identifiers with associated metadata, that are likely all owned by the same underlying user. The identity data allows to generate "identity-based", rather than "identifier-based", user models, giving a fuller picture of the interests of the users underlying the identifiers. We employ off-policy techniques to evaluate the potential of identity-powered lookalike models without incurring the risk of allowing untested models to direct large amounts of ad spend or the large cost of performing A/B tests. We add to historical work on off-policy evaluation by noting a significant type of "finite-sample bias" that occurs for studies combining modestly-sized datasets and evaluation metrics involving rare events (e.g., conversions). We illustrate this bias using a simulation study that later informs the handling of inverse propensity weights in our analyses on real data. We demonstrate significant lift in identity-powered lookalikes versus an identity-ignorant baseline: on average ~70% lift in conversion rate. This rises to factors of ~(4-32)x for identifiers having little data themselves, but that can be inferred to belong to users with substantial data to aggregate across identifiers. This implies that identity-powered user modeling is especially important in the context of identifiers having very short lifespans (i.e., frequently churned cookies). Our work motivates and informs the use of probabilistically-constructed identities in marketing. It also deepens the canon of examples in which off-policy learning has been employed to evaluate the complex systems of the internet economy.

cs.LG↗

arXiv2018

A modified subgradient extragradient method for solving the variational inequality problem

The subgradient extragradient method for solving the variational inequality (VI) problem, which is introduced by Censor et al. \cite{CGR}, replaces the second projection onto the feasible set of the VI, in the extragradient method, with a subgradient projection onto some constructible half-space. Since the method has been introduced, many authors proposed extensions and modifications with applications to various problems. In this paper, we introduce a modified subgradient extragradient method by improving the stepsize of its second step. Convergence of the proposed method is proved under standard and mild conditions and primary numerical experiments illustrate the performance and advantage of this new subgradient extragradient variant.

math.OC↗

arXiv2017

Convergence of projection and contraction algorithms with outer perturbations and their applications to sparse signals recovery

In this paper we study the bounded perturbation resilience of projection and contraction algorithms for solving variational inequality (VI) problems in real Hilbert spaces. Under typical and standard assumptions of monotonicity and Lipschitz continuity of the VI's associated mapping, convergence of the perturbed projection and contraction algorithms is proved. Based on the bounded perturbed resilience of projection and contraction algorithms, we present some inertial projection and contraction algorithms. In addition we show that the perturbed algorithms converges at the rate of $O(1/t)$.

math.OC↗

arXiv2017

Bounded perturbation resilience of extragradient-type methods and their applications

In this paper we study the bounded perturbation resilience of the extragradient and the subgradient extragradient methods for solving variational inequality (VI) problem in real Hilbert spaces. This is an important property of algorithms which guarantees the convergence of the scheme under summable errors, meaning that an inexact version of the methods can also be considered. Moreover, once an algorithm is proved to be bounded perturbation resilience, superiorizion can be used, and this allows flexibility in choosing the bounded perturbations in order to obtain a superior solution, as well explained in the paper. We also discuss some inertial extragradient methods. Under mild and standard assumptions of monotonicity and Lipschitz continuity of the VI's associated mapping, convergence of the perturbed extragradient and subgradient extragradient methods is proved. In addition we show that the perturbed algorithms converges at the rate of $O(1/t)$. Numerical illustrations are given to demonstrate the performances of the algorithms.

math.OC↗