arXiv subjects

Xianglin Huang

Publications and source records attributed to Xianglin Huang.

12 recordsLinked to original sources

arXiv2026

Scattered Hypothesis Generation for Open-Ended Event Forecasting

Despite the importance of open-ended event forecasting for risk management, current LLM-based methods predominantly target only the most probable outcomes, neglecting the intrinsic uncertainty of real-world events. To bridge this gap, we advance open-ended event forecasting from pinpoint forecasting to scatter forecasting by introducing the proxy task of hypothesis generation. This paradigm aims to generate an inclusive and diverse set of hypotheses that broadly cover the space of plausible future events. To this end, we propose SCATTER, a reinforcement learning framework that jointly optimizes inclusiveness and diversity of the hypothesis. Specifically, we design a novel hybrid reward that consists of three components: 1) a validity reward that measures semantic alignment with observed events, 2) an intra-group diversity reward to encourage variation within sampled responses, and 3) an inter-group diversity reward to promote exploration across distinct modes. By integrating the validity-gated score into the overall objective, we confine the exploration of wildly diversified outcomes to contextually plausible futures, preventing the mode collapse issue. Experiments on two real-world benchmark datasets, i.e., OpenForecast and OpenEP, demonstrate that SCATTER significantly outperforms strong baselines. Our code is available at https://github.com/Sambac1/SCATTER.

cs.IR↗

arXiv2025

AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS

Modern Visual-Aware Recommender Systems (VARS) exploit the integration of user interaction data and visual features to deliver personalized recommendations with high precision. However, their robustness against adversarial attacks remains largely underexplored, posing significant risks to system reliability and security. Existing attack strategies suffer from notable limitations: shilling attacks are costly and detectable, and visual-only perturbations often fail to align with user preferences. To address these challenges, we propose AUV-Fusion, a cross-modal adversarial attack framework that adopts high-order user preference modeling and cross-modal adversary generation. Specifically, we obtain robust user embeddings through multi-hop user-item interactions and transform them via an MLP into semantically aligned perturbations. These perturbations are injected onto the latent space of a pre-trained VAE within the diffusion model. By synergistically integrating genuine user interaction data with visually plausible perturbations, AUV-Fusion eliminates the need for injecting fake user profiles and effectively mitigates the challenge of insufficient user preference extraction inherent in traditional visual-only attacks. Comprehensive evaluations on diverse VARS architectures and real-world datasets demonstrate that AUV-Fusion significantly enhances the exposure of target (cold-start) items compared to conventional baseline methods. Moreover, AUV-Fusion maintains exceptional stealth under rigorous scrutiny.

cs.IR↗

arXiv2025

ChronoTailor: Harnessing Attention Guidance for Fine-Grained Video Virtual Try-On

Video virtual try-on aims to seamlessly replace the clothing of a person in a source video with a target garment. Despite significant progress in this field, existing approaches still struggle to maintain continuity and reproduce garment details. In this paper, we introduce ChronoTailor, a diffusion-based framework that generates temporally consistent videos while preserving fine-grained garment details. By employing a precise spatio-temporal attention mechanism to guide the integration of fine-grained garment features, ChronoTailor achieves robust try-on performance. First, ChronoTailor leverages region-aware spatial guidance to steer the evolution of spatial attention and employs an attention-driven temporal feature fusion mechanism to generate more continuous temporal features. This dual approach not only enables fine-grained local editing but also effectively mitigates artifacts arising from video dynamics. Second, ChronoTailor integrates multi-scale garment features to preserve low-level visual details and incorporates a garment-pose feature alignment to ensure temporal continuity during dynamic motion. Additionally, we collect StyleDress, a new dataset featuring intricate garments, varied environments, and diverse poses, offering advantages over existing public datasets, and will be publicly available for research. Extensive experiments show that ChronoTailor maintains spatio-temporal continuity and preserves garment details during motion, significantly outperforming previous methods.

cs.CV↗

arXiv2025

A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting

Recently, Large Language Models (LLMs) have demonstrated great potential in various data mining tasks, such as knowledge question answering, mathematical reasoning, and commonsense reasoning. However, the reasoning capability of LLMs on temporal event forecasting has been under-explored. To systematically investigate their abilities in temporal event forecasting, we conduct a comprehensive evaluation of LLM-based methods for temporal event forecasting. Due to the lack of a high-quality dataset that involves both graph and textual data, we first construct a benchmark dataset, named MidEast-TE-mini. Based on this dataset, we design a series of baseline methods, characterized by various input formats and retrieval augmented generation (RAG) modules. From extensive experiments, we find that directly integrating raw texts into the input of LLMs does not enhance zero-shot extrapolation performance. In contrast, fine-tuning LLMs with raw texts can significantly improve performance. Additionally, LLMs enhanced with retrieval modules can effectively capture temporal relational patterns hidden in historical events. However, issues such as popularity bias and the long-tail problem persist in LLMs, particularly in the retrieval-augmented generation (RAG) method. These findings not only deepen our understanding of LLM-based event forecasting methods but also highlight several promising research directions. We consider that this comprehensive evaluation, along with the identified research opportunities, will significantly contribute to future research on temporal event forecasting through LLMs.

cs.CL↗

arXiv2025

A Lightweight and Effective Image Tampering Localization Network with Vision Mamba

Current image tampering localization methods primarily rely on Convolutional Neural Networks (CNNs) and Transformers. While CNNs suffer from limited local receptive fields, Transformers offer global context modeling at the expense of quadratic computational complexity. Recently, the state space model Mamba has emerged as a competitive alternative, enabling linear-complexity global dependency modeling. Inspired by it, we propose a lightweight and effective FORensic network based on vision MAmba (ForMa) for blind image tampering localization. Firstly, ForMa captures multi-scale global features that achieves efficient global dependency modeling through linear complexity. Then the pixel-wise localization map is generated by a lightweight decoder, which employs a parameter-free pixel shuffle layer for upsampling. Additionally, a noise-assisted decoding strategy is proposed to integrate complementary manipulation traces from tampered images, boosting decoder sensitivity to forgery cues. Experimental results on 10 standard datasets demonstrate that ForMa achieves state-of-the-art generalization ability and robustness, while maintaining the lowest computational complexity. Code is available at https://github.com/multimediaFor/ForMa.

cs.CV↗

arXiv2025

Progressive Feedback-Enhanced Transformer for Image Forgery Localization

Blind detection of the forged regions in digital images is an effective authentication means to counter the malicious use of local image editing techniques. Existing encoder-decoder forensic networks overlook the fact that detecting complex and subtle tampered regions typically requires more feedback information. In this paper, we propose a Progressive FeedbACk-enhanced Transformer (ProFact) network to achieve coarse-to-fine image forgery localization. Specifically, the coarse localization map generated by an initial branch network is adaptively fed back to the early transformer encoder layers, which can enhance the representation of positive features while suppressing interference factors. The cascaded transformer network, combined with a contextual spatial pyramid module, is designed to refine discriminative forensic features for improving the forgery localization accuracy and reliability. Furthermore, we present an effective strategy to automatically generate large-scale forged image samples close to real-world forensic scenarios, especially in realistic and coherent processing. Leveraging on such samples, a progressive and cost-effective two-stage training protocol is applied to the ProFact network. The extensive experimental results on nine public forensic datasets show that our proposed localizer greatly outperforms the state-of-the-art on the generalization ability and robustness of image forgery localization. Code will be publicly available at https://github.com/multimediaFor/ProFact.

cs.CV↗

arXiv2025

Integrate Temporal Graph Learning into LLM-based Temporal Knowledge Graph Model

Temporal Knowledge Graph Forecasting (TKGF) aims to predict future events based on the observed events in history. Recently, Large Language Models (LLMs) have exhibited remarkable capabilities, generating significant research interest in their application for reasoning over temporal knowledge graphs (TKGs). Existing LLM-based methods have integrated retrieved historical facts or static graph representations into LLMs. Despite the notable performance of LLM-based methods, they are limited by the insufficient modeling of temporal patterns and ineffective cross-modal alignment between graph and language, hindering the ability of LLMs to fully grasp the temporal and structural information in TKGs. To tackle these issues, we propose a novel framework TGL-LLM to integrate temporal graph learning into LLM-based temporal knowledge graph model. Specifically, we introduce temporal graph learning to capture the temporal and relational patterns and obtain the historical graph embedding. Furthermore, we design a hybrid graph tokenization to sufficiently model the temporal patterns within LLMs. To achieve better alignment between graph and language, we employ a two-stage training paradigm to finetune LLMs on high-quality and diverse data, thereby resulting in better performance. Extensive experiments on three real-world datasets show that our approach outperforms a range of state-of-the-art (SOTA) methods.

cs.IR↗

arXiv2024

Determination of dynamic flow stress equation based on discrete experimental data: Part 1 Methodology and the dependence of dynamic flow stress on strain-rate

In this study, a framework to determine the dynamic flow stress equation of materials based on discrete data of varied (or instantaneous) strain-rate from split Hopkinson pressure bar (SHPB) experiments is proposed. The conventional constant strain-rate requirement in SHPB test is purposely relaxed to generate rich dynamic flow stress data which are widely and diversely distributed in plastic strain and strain-rate space. Two groups of independent SHPB tests, i.e. Group A (without shaper) and Group B (with shaper) were conducted on the C54400 phosphor-bronze copper alloy at room temperature, obtaining flow stress data (FSD) (two-dimensional (2D) matrix). Data qualification criteria were proposed to screen the FSD, with which qualified FSD were obtained. The qualified FSD of Group A were coarsely filled with missing data and were reconstructed by the Artificial Neural Network (ANN). As a result, finely-filled FSD of Group A were obtained, which were carefully evaluated by the qualified FSD of Group B. The evaluation proves the effectiveness of ANN in FSD prediction. Next, the finely-filled FSD from Group A were decomposed by Singular Value Decomposition (SVD) method. Discrete and analytical flow stress equation f(strain, strain-rate)_ana were obtained from the SVD results. Finally, flow stress equation (f(strain, strain-rate)_MJC) based on conventional method were established. Five uncertainties inherent in the conventional method in the determination of the flow stress equation were identified. The comparison between f(strain, strain-rate)_ana and f(strain, strain-rate)_MJC demonstrated the effectiveness and reliability of the flow stress equation obtained from the proposed method.

physics.app-ph↗

arXiv2022

Contrast Enhancement of Brightness-Distorted Images by Improved Adaptive Gamma Correction

As an efficient image contrast enhancement (CE) tool, adaptive gamma correction (AGC) was previously proposed by relating gamma parameter with cumulative distribution function (CDF) of the pixel gray levels within an image. ACG deals well with most dimmed images, but fails for globally bright images and the dimmed images with local bright regions. Such two categories of brightness-distorted images are universal in real scenarios, such as improper exposure and white object regions. In order to attenuate such deficiencies, here we propose an improved AGC algorithm. The novel strategy of negative images is used to realize CE of the bright images, and the gamma correction modulated by truncated CDF is employed to enhance the dimmed ones. As such, local over-enhancement and structure distortion can be alleviated. Both qualitative and quantitative experimental results show that our proposed method yields consistently good CE results.

cs.MM↗

arXiv2022

Acceleration of Histogram-Based Contrast Enhancement via Selective Downsampling

In this paper, we propose a general framework to accelerate the universal histogram-based image contrast enhancement (CE) algorithms. Both spatial and gray-level selective down-sampling of digital images are adopted to decrease computational cost, while the visual quality of enhanced images is still preserved and without apparent degradation. Mapping function calibration is novelly proposed to reconstruct the pixel mapping on the gray levels missed by downsampling. As two case studies, accelerations of histogram equalization (HE) and the state-of-the-art global CE algorithm, i.e., spatial mutual information and PageRank (SMIRANK), are presented detailedly. Both quantitative and qualitative assessment results have verified the effectiveness of our proposed CE acceleration framework. In typical tests, computational efficiencies of HE and SMIRANK have been speeded up by about 3.9 and 13.5 times, respectively.

cs.MM↗

arXiv2021

Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments

At present, attention mechanism has been widely applied to the fields of deep learning models. Structural models that based on attention mechanism can not only record the relationships between features position, but also can measure the importance of different features based on their weights. By establishing dynamically weighted parameters for choosing relevant and irrelevant features, the key information can be strengthened, and the irrelevant information can be weakened. Therefore, the efficiency of deep learning algorithms can be significantly elevated and improved. Although transformers have been performed very well in many fields including reinforcement learning, there are still many problems and applications can be solved and made with transformers within this area. MARL (known as Multi-Agent Reinforcement Learning) can be recognized as a set of independent agents trying to adapt and learn through their way to reach the goal. In order to emphasize the relationship between each MDP decision in a certain time period, we applied the hierarchical coding method and validated the effectiveness of this method. This paper proposed a hierarchical transformers MADDPG based on RNN which we call it Hierarchical RNNs-Based Transformers MADDPG(HRTMADDPG). It consists of a lower level encoder based on RNNs that encodes multiple step sizes in each time sequence, and it also consists of an upper sequence level encoder based on transformer for learning the correlations between multiple sequences so that we can capture the causal relationship between sub-time sequences and make HRTMADDPG more efficient.

cs.LG↗

arXiv2019

Resampling detection of recompressed images via dual-stream convolutional neural network

Resampling detection plays an important role in identifying image tampering, such as image splicing. Currently, the resampling detection is still difficult in recompressed images, which are yielded by applying resampling followed by post-JPEG compression to primary JPEG images. Except for the scenario of low quality primary compression, it remains rather challenging due to the widespread use of middle/high quality compression in imaging devices. In this paper, we propose a new convolution neural network (CNN) method to learn the resampling trace features directly from the recompressed images. To this end, a noise extraction layer based on low-order high pass filters is deployed to yield the image residual domain, which is more beneficial to extract manipulation trace features. A dual-stream CNN is presented to capture the resampling trails along different directions, where the horizontal and vertical streams are interleaved and concatenated. Lastly, the learned features are fed into Sigmoid/Softmax layer, which acts as a binary/multiple classifier for achieving the blind detection and parameter estimation of resampling, respectively. Extensive experimental results demonstrate that our proposed method could detect resampling effectively in recompressed images and outperform the state-of-the-art detectors.

cs.CV↗