Chaoqun Cui

Shijing Wang, Chaoqun Cui, Yaping Huang et al.

Human gaze provides essential cues for interpreting attention, intention, and social interaction in visual scenes, yet gaze understanding remains largely unexplored in current vision-language models (VLMs). While recent VLMs achieve strong scene-level reasoning across a range of visual tasks, there exists no benchmark that systematically evaluates or trains them for gaze interpretation, leaving open the question of whether gaze understanding can emerge from general-purpose vision-language pre-training. To address this gap, we introduce VL4Gaze, the first large-scale benchmark designed to investigate, evaluate, and unlock the potential of VLMs for gaze understanding. VL4Gaze contains 489K automatically generated question-answer pairs across 124K images and formulates gaze understanding as a unified VQA problem through four complementary tasks: (1) gaze object description, (2) gaze direction description, (3) gaze point location, and (4) ambiguous question recognition. We comprehensively evaluate both commercial and open-source VLMs under in-context learning and fine-tuning settings. The results show that even large-scale VLMs struggle to reliably infer gaze semantics and spatial localization without task-specific supervision. In contrast, training on VL4Gaze brings substantial and consistent improvements across all tasks, highlighting the importance of targeted multi-task supervision for developing gaze understanding capabilities in VLMs. We will release the dataset and code to support further research and development in this direction.

Shijing Wang, Yaping Huang, Chaoqun Cui et al.

Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning. As a result, existing methods often rely on semantically salient objects rather than true gaze cues, leading to degraded performance when targets are not salient. To address this, we propose a novel training mechanism to enhance gaze reasoning in VFMs for gaze following. Our method includes: (1) a head-conditioned local LoRA, which enables localized adaptation to preserve scene token learning while improving head token learning for gaze reasoning; and (2) an out-of-cone penalty, which injects gaze cues into head tokens while aligning them with scene tokens. Experiments on the GazeFollow and VAT datasets demonstrate that our method achieves state-of-the-art performance, with particularly strong improvements when gaze targets are not semantically salient. Our findings offer valuable insights for advancing future gaze following research. We will release the code once the paper is accepted.

Chaoqun Cui, Caiyan Jia

Deep learning techniques for rumor detection typically utilize Graph Neural Networks (GNNs) to analyze post relations. These methods, however, falter due to over-smoothing issues when processing rumor propagation structures, leading to declining performance. Our investigation into this issue reveals that over-smoothing is intrinsically tied to the structural characteristics of rumor propagation trees, in which the majority of nodes are 1-level nodes. Furthermore, GNNs struggle to capture long-range dependencies within these trees. To circumvent these challenges, we propose a Pre-Trained Propagation Tree Transformer (P2T3) method based on pure Transformer architecture. It extracts all conversation chains from a tree structure following the propagation direction of replies, utilizes token-wise embedding to infuse connection information and introduces necessary inductive bias, and pre-trains on large-scale unlabeled datasets. Experiments indicate that P2T3 surpasses previous state-of-the-art methods in multiple benchmark datasets and performs well under few-shot conditions. P2T3 not only avoids the over-smoothing issue inherent in GNNs but also potentially offers a large model or unified multi-modal scheme for future social media research.

Chaoqun Cui, Caiyan Jia

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.

Liangbin Huang, Xiaohua Liao, Chaoqun Cui et al.

Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings.

Chaoqun Cui, Caiyan Jia

Current rumor detection methods based on propagation structure learning predominately treat rumor detection as a class-balanced classification task on limited labeled data. However, real-world social media data exhibits an imbalanced distribution with a minority of rumors among massive regular posts. To address the data scarcity and imbalance issues, we construct two large-scale conversation datasets from Weibo and Twitter and analyze the domain distributions. We find obvious differences between rumor and non-rumor distributions, with non-rumors mostly in entertainment domains while rumors concentrate in news, indicating the conformity of rumor detection to an anomaly detection paradigm. Correspondingly, we propose the Anomaly Detection framework with Graph Supervised Contrastive Learning (AD-GSCL). It heuristically treats unlabeled data as non-rumors and adapts graph contrastive learning for rumor detection. Extensive experiments demonstrate AD-GSCL's superiority under class-balanced, imbalanced, and few-shot conditions. Our findings provide valuable insights for real-world rumor detection featuring imbalanced data distributions.

Chaoqun Cui, Liangbin Huang, Shijing Wang et al.

Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across languages, target speech often mismatches the source speech duration, causing audio-video synchronization issues that significantly impact viewer experience. In this study, we approach duration alignment in LLM-based video dubbing machine translation as a preference optimization problem. We propose the Segment Supervised Preference Optimization (SSPO) method, which employs a segment-wise sampling strategy and fine-grained loss to mitigate duration mismatches between source and target lines. Experimental results demonstrate that SSPO achieves superior performance in duration alignment tasks.

Chaoqun Cui, Siyuan Li, Kunkun Ma et al.

Pretrained Language Models (PLMs) have excelled in various Natural Language Processing tasks, benefiting from large-scale pretraining and self-attention mechanism's ability to capture long-range dependencies. However, their performance on social media application tasks like rumor detection remains suboptimal. We attribute this to mismatches between pretraining corpora and social texts, inadequate handling of unique social symbols, and pretraining tasks ill-suited for modeling user engagements implicit in propagation structures. To address these issues, we propose a continue pretraining strategy called Post Engagement Prediction (PEP) to infuse information from propagation structures into PLMs. PEP makes models to predict root, branch, and parent relations between posts, capturing interactions of stance and sentiment crucial for rumor detection. We also curate and release large-scale Twitter corpus: TwitterCorpus (269GB text), and two unlabeled claim conversation datasets with propagation structures (UTwitter and UWeibo). Utilizing these resources and PEP strategy, we train a Twitter-tailored PLM called SoLM. Extensive experiments demonstrate PEP significantly boosts rumor detection performance across universal and social media PLMs, even in few-shot scenarios. On benchmark datasets, PEP enhances baseline models by 1.0-3.7\% accuracy, even enabling it to outperform current state-of-the-art methods on multiple datasets. SoLM alone, without high-level modules, also achieves competitive results, highlighting the strategy's effectiveness in learning discriminative post interaction features.

Lin Bai, Caiyan Jia, Ziying Song et al.

With the development of social media, rumors have been spread broadly on social media platforms, causing great harm to society. Beside textual information, many rumors also use manipulated images or conceal textual information within images to deceive people and avoid being detected, making multimodal rumor detection be a critical problem. The majority of multimodal rumor detection methods mainly concentrate on extracting features of source claims and their corresponding images, while ignoring the comments of rumors and their propagation structures. These comments and structures imply the wisdom of crowds and are proved to be crucial to debunk rumors. Moreover, these methods usually only extract visual features in a basic manner, seldom consider tampering or textual information in images. Therefore, in this study, we propose a novel Vision and Graph Fused Attention Network (VGA) for rumor detection to utilize propagation structures among posts so as to obtain the crowd opinions and further explore visual tampering features, as well as the textual information hidden in images. We conduct extensive experiments on three datasets, demonstrating that VGA can effectively detect multimodal rumors and outperform state-of-the-art methods significantly.

Chaoqun Cui, Caiyan Jia

With the development of social media, rumors spread quickly, cause great harm to society and economy. Thereby, many effective rumor detection methods have been developed, among which the rumor propagation structure learning based methods are particularly effective compared to other methods. However, the existing methods still suffer from many issues including the difficulty to obtain large-scale labeled rumor datasets, which leads to the low generalization ability and the performance degeneration on new events since rumors are time-critical and usually appear with hot topics or newly emergent events. In order to solve the above problems, in this study, we used large-scale unlabeled topic datasets crawled from the social media platform Weibo and Twitter with claim propagation structure to improve the semantic learning ability of a graph reprentation learing model on various topics. We use three typical graph self-supervised methods, InfoGraph, JOAO and GraphMAE in two commonly used training strategies, to verify the performance of general graph semi-supervised methods in rumor detection tasks. In addition, for alleviating the time and topic difference between unlabeled topic data and rumor data, we also collected a rumor dataset covering a variety of topics over a decade (10-year ago from 2022) from the Weibo rumor-refuting platform. Our experiments show that these general graph self-supervised learning methods outperform previous methods specifically designed for rumor detection tasks and achieve good performance under few-shot conditions, demonstrating the better generalization ability with the help of our massive unlabeled topic dataset.

Chaoqun Cui, Shijing Wang, Liangbin Huang et al.

The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality.