arXiv subjects

Zhedong Zheng

Publications and source records attributed to Zhedong Zheng.

At least 55 records · Page 3Linked to original sources

arXiv2025

Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search

Text-based person search aims to retrieve specific individuals across camera networks using natural language descriptions. However, current benchmarks often exhibit biases towards common actions like walking or standing, neglecting the critical need for identifying abnormal behaviors in real-world scenarios. To meet such demands, we propose a new task, text-based person anomaly search, locating pedestrians engaged in both routine or anomalous activities via text. To enable the training and evaluation of this new task, we construct a large-scale image-text Pedestrian Anomaly Behavior (PAB) benchmark, featuring a broad spectrum of actions, e.g., running, performing, playing soccer, and the corresponding anomalies, e.g., lying, being hit, and falling of the same identity. The training set of PAB comprises 1,013,605 synthesized image-text pairs of both normalities and anomalies, while the test set includes 1,978 real-world image-text pairs. To validate the potential of PAB, we introduce a cross-modal pose-aware framework, which integrates human pose patterns with identity-based hard negative pair sampling. Extensive experiments on the proposed benchmark show that synthetic training data facilitates the fine-grained behavior retrieval, and the proposed pose-aware method arrives at 84.93% recall@1 accuracy, surpassing other competitive methods. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/CMP.

cs.CV↗

arXiv2025

Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models

Large Multimodal Models (LMMs), harnessing the complementarity among diverse modalities, are often considered more robust than pure Language Large Models (LLMs); yet do LMMs know what they do not know? There are three key open questions remaining: (1) how to evaluate the uncertainty of diverse LMMs in a unified manner, (2) how to prompt LMMs to show its uncertainty, and (3) how to quantify uncertainty for downstream tasks. In an attempt to address these challenges, we introduce Uncertainty-o: (1) a model-agnostic framework designed to reveal uncertainty in LMMs regardless of their modalities, architectures, or capabilities, (2) an empirical exploration of multimodal prompt perturbations to uncover LMM uncertainty, offering insights and findings, and (3) derive the formulation of multimodal semantic uncertainty, which enables quantifying uncertainty from multimodal responses. Experiments across 18 benchmarks spanning various modalities and 10 LMMs (both open- and closed-source) demonstrate the effectiveness of Uncertainty-o in reliably estimating LMM uncertainty, thereby enhancing downstream tasks such as hallucination detection, hallucination mitigation, and uncertainty-aware Chain-of-Thought reasoning.

cs.CV↗

arXiv2025

Towards Scalable Video Anomaly Retrieval: A Synthetic Video-Text Benchmark

Video anomaly retrieval aims to localize anomalous events in videos using natural language queries to facilitate public safety. However, existing datasets suffer from severe limitations: (1) data scarcity due to the long-tail nature of real-world anomalies, and (2) privacy constraints that impede large-scale collection. To address the aforementioned issues in one go, we introduce SVTA (Synthetic Video-Text Anomaly benchmark), the first large-scale dataset for cross-modal anomaly retrieval, leveraging generative models to overcome data availability challenges. Specifically, we collect and generate video descriptions via the off-the-shelf LLM (Large Language Model) covering 68 anomaly categories, e.g., throwing, stealing, and shooting. These descriptions encompass common long-tail events. We adopt these texts to guide the video generative model to produce diverse and high-quality videos. Finally, our SVTA involves 41,315 videos (1.36M frames) with paired captions, covering 30 normal activities, e.g., standing, walking, and sports, and 68 anomalous events, e.g., falling, fighting, theft, explosions, and natural disasters. We adopt three widely-used video-text retrieval baselines to comprehensively test our SVTA, revealing SVTA's challenging nature and its effectiveness in evaluating a robust cross-modal retrieval method. SVTA eliminates privacy risks associated with real-world anomaly collection while maintaining realistic scenarios. The dataset demo is available at: [https://svta-mm.github.io/SVTA.github.io/].

cs.CV↗

arXiv2025

TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction

Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and inherently restrict the adaptability of models to unconstrained interaction scenarios, e.g., heavily-occluded objects. To overcome this bottleneck, we propose a new Text-Instructed Generation and Refinement (TIGeR) framework, harnessing the power of intuitive text-driven priors to steer the object shape refinement and pose estimation. We use a two-stage framework: a text-instructed prior generation and vision-guided refinement. As the name implies, we first leverage off-the-shelf models to generate shape priors according to the text description without tedious 3D crafting. Considering the geometric gap between the synthesized prototype and the real object interacted with the hand, we further calibrate the synthesized prototype via 2D-3D collaborative attention. TIGeR achieves competitive performance, i.e., 1.979 and 5.468 object Chamfer distance on the widely-used Dex-YCB and Obman datasets, respectively, surpassing existing template-free methods. Notably, the proposed framework shows robustness to occlusion, while maintaining compatibility with heterogeneous prior sources, e.g., retrieved hand-crafted prototypes, in practical deployment scenarios.

cs.CV↗

arXiv2025

SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Models

Diffusion models have recently enabled precise and photorealistic facial editing across a wide range of semantic attributes. Beyond single-step modifications, a growing class of applications now demands the ability to analyze and track sequences of progressive edits, such as stepwise changes to hair, makeup, or accessories. However, sequential editing introduces significant challenges in edit attribution and detection robustness, further complicated by the lack of large-scale, finely annotated benchmarks tailored explicitly for this task. We introduce SEED, a large-scale Sequentially Edited facE Dataset constructed via state-of-the-art diffusion models. SEED contains over 90,000 facial images with one to four sequential attribute modifications, generated using diverse diffusion-based editing pipelines (LEdits, SDXL, SD3). Each image is annotated with detailed edit sequences, attribute masks, and prompts, facilitating research on sequential edit tracking, visual provenance analysis, and manipulation robustness assessment. To benchmark this task, we propose FAITH, a frequency-aware transformer-based model that incorporates high-frequency cues to enhance sensitivity to subtle sequential changes. Comprehensive experiments, including systematic comparisons of multiple frequency-domain methods, demonstrate the effectiveness of FAITH and the unique challenges posed by SEED. SEED offers a challenging and flexible resource for studying progressive diffusion-based edits at scale. Dataset and code will be publicly released at: https://github.com/Zeus1037/SEED.

cs.CV↗

arXiv2025

CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval

Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of pretraining and fine-tuning. However, these generated data often exhibit domain biases in both images and textual annotations, which largely compromise the scalability of the pre-trained model. Therefore, we introduce a domain-agnostic pretraining framework based on Cross-modality Adaptive Meta-Learning (CAMeL) to enhance the model generalization capability during pretraining to facilitate the subsequent downstream tasks. In particular, we develop a series of tasks that reflect the diversity and complexity of real-world scenarios, and introduce a dynamic error sample memory unit to memorize the history for errors encountered within multiple tasks. To further ensure multi-task adaptation, we also adopt an adaptive dual-speed update strategy, balancing fast adaptation to new tasks and slow weight updates for historical tasks. Albeit simple, our proposed model not only surpasses existing state-of-the-art methods on real-world benchmarks, including CUHK-PEDES, ICFG-PEDES, and RSTPReid, but also showcases robustness and scalability in handling biased synthetic images and noisy text annotations. Our code is available at https://github.com/Jahawn-Wen/CAMeL-reID.

cs.CV↗

arXiv2025

CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe downsampling rates (\eg, 8$\times$ or 16$\times$). The recently developed text-guided SR approaches leverage textual descriptions to enhance their detail restoration capabilities but frequently struggle with effectively performing alignment, resulting in semantic inconsistencies. To address these challenges, we propose a multi-modal semantic enhancement framework that integrates textual semantics with visual features, effectively mitigating semantic mismatches and detail losses in highly degraded low-resolution (LR) images. Our method enables realistic, high-quality SR to be performed at large upscaling factors, with a maximum scaling ratio of 16$\times$. The framework integrates both text and image inputs using the prompt predictor, the Text-Image Fusion Block (TIFBlock), and the Iterative Refinement Module, leveraging Contrastive Language-Image Pretraining (CLIP) features to guide a progressive enhancement process with fine-grained alignment. This synergy produces high-resolution outputs with sharp textures and strong semantic coherence, even at substantial scaling factors. Extensive comparative experiments and ablation studies validate the effectiveness of our approach. Furthermore, by leveraging textual semantics, our method offers a degree of super-resolution editability, allowing for controlled enhancements while preserving semantic consistency. The code is available at https://github.com/hengliusky/CLIP-SR.

cs.CV↗

arXiv2025

3D-TAFS: A Training-free Framework for 3D Affordance Segmentation

Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation. To facilitate a comprehensive evaluation of such frameworks, we present IndoorAfford-Bench, a large-scale benchmark containing 9,248 images spanning 20 diverse indoor scenes across 6 areas, supporting standardized interaction queries. In particular, our framework integrates a large multimodal model with a specialized 3D vision network, enabling a seamless fusion of 2D and 3D visual understanding with language comprehension. Extensive experiments on IndoorAfford-Bench validate the proposed 3D-TAFS's capability in handling interactive 3D affordance segmentation tasks across diverse settings, showcasing competitive performance across various metrics. Our results highlight 3D-TAFS's potential for enhancing human-robot interaction based on affordance understanding in complex indoor environments, advancing the development of more intuitive and efficient robotic frameworks for real-world applications.

cs.RO↗

arXiv2025

Scale-adaptive UAV Geo-localization via Height-aware Partition Learning

UAV Geo-Localization faces significant challenges due to the drastic appearance discrepancy between dronecaptured images and satellite views. Existing methods typically assume a consistent scaling factor across views and rely on predefined partition alignment to extract viewpoint-invariant representations through part-level feature construction. However, this scaling assumption often fails in real-world scenarios, where variations in drone flight states lead to scale mismatches between cross-view images, resulting in severe performance degradation. To address this issue, we propose a scale-adaptive partition learning framework that leverages known drone flight height to predict scale factors and dynamically adjust feature extraction. Our key contribution is a height-aware adjustment strategy, which calculates the relative height ratio between drone and satellite views, dynamically adjusting partition sizes to explicitly align semantic information between partition pairs. This strategy is integrated into a Scale-adaptive Local Partition Network (SaLPN), building upon an existing square partition strategy to extract both finegrained and global features. Additionally, we propose a saliencyguided refinement strategy to enhance part-level features, further improving retrieval accuracy. Extensive experiments validate that our height-aware, scale-adaptive approach achieves stateof-the-art geo-localization accuracy in various scale-inconsistent scenarios and exhibits strong robustness against scale variations. The code will be made publicly available.

cs.CV↗

arXiv2025

Every Painting Awakened: A Training-free Framework for Painting-to-Animation Generation

We introduce a training-free framework specifically designed to bring real-world static paintings to life through image-to-video (I2V) synthesis, addressing the persistent challenge of aligning these motions with textual guidance while preserving fidelity to the original artworks. Existing I2V methods, primarily trained on natural video datasets, often struggle to generate dynamic outputs from static paintings. It remains challenging to generate motion while maintaining visual consistency with real-world paintings. This results in two distinct failure modes: either static outputs due to limited text-based motion interpretation or distorted dynamics caused by inadequate alignment with real-world artistic styles. We leverage the advanced text-image alignment capabilities of pre-trained image models to guide the animation process. Our approach introduces synthetic proxy images through two key innovations: (1) Dual-path score distillation: We employ a dual-path architecture to distill motion priors from both real and synthetic data, preserving static details from the original painting while learning dynamic characteristics from synthetic frames. (2) Hybrid latent fusion: We integrate hybrid features extracted from real paintings and synthetic proxy images via spherical linear interpolation in the latent space, ensuring smooth transitions and enhancing temporal consistency. Experimental evaluations confirm that our approach significantly improves semantic alignment with text prompts while faithfully preserving the unique characteristics and integrity of the original paintings. Crucially, by achieving enhanced dynamic effects without requiring any model training or learnable parameters, our framework enables plug-and-play integration with existing I2V methods, making it an ideal solution for animating real-world paintings. More animated examples can be found on our project website.

cs.CV↗

arXiv2025

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their semantic alignment with the provided conditions. To tackle this issue, previous studies have employed supervised perceptual losses derived from pre-trained models, i.e., reward models, to enforce alignment between the condition and the generated result. However, we observe one inherent shortcoming: considering the diversity of synthesized images, the reward model usually provides inaccurate feedback when encountering newly generated data, which can undermine the training process. To address this limitation, we propose an uncertainty-aware reward modeling, called Ctrl-U, including uncertainty estimation and uncertainty-aware regularization, designed to reduce the adverse effects of imprecise feedback from the reward model. Given the inherent cognitive uncertainty within reward models, even images generated under identical conditions often result in a relatively large discrepancy in reward loss. Inspired by the observation, we explicitly leverage such prediction variance as an uncertainty indicator. Based on the uncertainty estimation, we regularize the model training by adaptively rectifying the reward. In particular, rewards with lower uncertainty receive higher loss weights, while those with higher uncertainty are given reduced weights to allow for larger variability. The proposed uncertainty regularization facilitates reward fine-tuning through consistency construction. Extensive experiments validate the effectiveness of our methodology in improving the controllability and generation quality, as well as its scalability across diverse conditional scenarios. Codes are publicly available at https://grenoble-zhang.github.io/Ctrl-U-Page/.

cs.CV↗

arXiv2025

EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis

Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future. Current approaches typically treat TAA as a supervised learning task needing the laborious annotation of accident occurrence duration. However, the inherent long-tailed, uncertain, and fast-evolving nature of traffic scenes has the problem that real causal parts of accidents are difficult to identify and are easily dominated by data bias, resulting in a background confounding issue. Thus, we propose an Attentive Video Diffusion (AVD) model that synthesizes additional accident video clips by generating the causal part in dashcam videos, i.e., from normal clips to accident clips. AVD aims to generate causal video frames based on accident or accident-free text prompts while preserving the style and content of frames for TAA after video generation. This approach can be trained using datasets collected from various driving scenes without any extra annotations. Additionally, AVD facilitates an Equivariant TAA (EQ-TAA) with an equivariant triple loss for an anchor accident-free video clip, along with the generated pair of contrastive pseudo-normal and pseudo-accident clips. Extensive experiments have been conducted to evaluate the performance of AVD and EQ-TAA, and competitive performance compared to state-of-the-art methods has been obtained.

cs.MM↗

arXiv2025

Scale Up Composed Image Retrieval Learning via Modification Text Generation

Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and laborious triplet annotation processes. To address this issue, this paper proposes to synthesize the training triplets to augment the training resource for the CIR problem. Specifically, we commence by training a modification text generator exploiting large-scale multimodal models and scale up the CIR learning throughout both the pretraining and fine-tuning stages. During pretraining, we leverage the trained generator to directly create Modification Text-oriented Synthetic Triplets(MTST) conditioned on pairs of images. For fine-tuning, we first synthesize reverse modification text to connect the target image back to the reference image. Subsequently, we devise a two-hop alignment strategy to incrementally close the semantic gap between the multimodal pair and the target image. We initially learn an implicit prototype utilizing both the original triplet and its reversed version in a cycle manner, followed by combining the implicit prototype feature with the modification text to facilitate accurate alignment with the target image. Extensive experiments validate the efficacy of the generated triplets and confirm that our proposed methodology attains competitive recall on both the CIRR and FashionIQ benchmarks.

cs.IR↗

arXiv2025

From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search

In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Low-Rank Adaptation) learning strategy for light fine-tuning. The filtering algorithm is based on the cross-modality relevance to remove the lots of coarse matching synthesis pairs. As the number of data decreases, we do not need to fine-tune the entire model. Therefore, we propose a WoRA learning strategy to efficiently update a minimal portion of model parameters. WoRA streamlines the learning process, enabling heightened efficiency in extracting knowledge from fewer, yet potent, data instances. Extensive experimentation validates the efficacy of pretraining, where our model achieves advanced and efficient retrieval performance on challenging real-world benchmarks. Notably, on the CUHK-PEDES dataset, we have achieved a competitive mAP of 67.02% while reducing model training time by 19.82%.

cs.CV↗

arXiv2024

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in LVLMs. Different from most existing methods that require ground-truth or pseudo annotations, VL-Uncertainty utilizes uncertainty as an intrinsic metric. We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts, including visual and textual data. When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries. However, when uncertain, the responses of the target LVLM become more random. Considering semantically similar answers with different wordings, we cluster LVLM responses based on their semantic content and then calculate the cluster distribution entropy as the uncertainty measure to detect hallucination. Our extensive experiments on 10 LVLMs across four benchmarks, covering both free-form and multi-choice tasks, show that VL-Uncertainty significantly outperforms strong baseline methods in hallucination detection.

cs.CV↗

arXiv2024

RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning

Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, to bridge the gap between input image and the 3D target, thereby guiding the generation of both shape and texture. However, inconsistencies in the generated multi-view snapshots frequently introduce noise and artifacts along object boundaries, undermining the 3D reconstruction process. To address this challenge, we leverage 3D Gaussian Splatting (3DGS) for 3D reconstruction, and explicitly integrate uncertainty-aware learning into the reconstruction process. By capturing the stochasticity between two Gaussian models, we estimate an uncertainty map, which is subsequently used for uncertainty-aware regularization to rectify the impact of inconsistencies. Specifically, we optimize both Gaussian models simultaneously, calculating the uncertainty map by evaluating the discrepancies between rendered images from identical viewpoints. Based on the uncertainty map, we apply adaptive pixel-wise loss weighting to regularize the models, reducing reconstruction intensity in high-uncertainty regions. This approach dynamically detects and mitigates conflicts in multi-view labels, leading to smoother results and effectively reducing artifacts. Extensive experiments show the effectiveness of our method in improving 3D generation quality by reducing inconsistencies and artifacts.

cs.CV↗

arXiv2024

Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection

Unsupervised 3D object detection aims to identify objects of interest from unlabeled raw data, such as LiDAR points. Recent approaches usually adopt pseudo 3D bounding boxes (3D bboxes) from clustering algorithm to initialize the model training. However, pseudo bboxes inevitably contain noise, and such inaccuracies accumulate to the final model, compromising the performance. Therefore, in an attempt to mitigate the negative impact of inaccurate pseudo bboxes, we introduce a new uncertainty-aware framework for unsupervised 3D object detection, dubbed UA3D. In particular, our method consists of two phases: uncertainty estimation and uncertainty regularization. (1) In the uncertainty estimation phase, we incorporate an extra auxiliary detection branch alongside the original primary detector. The prediction disparity between the primary and auxiliary detectors could reflect fine-grained uncertainty at the box coordinate level. (2) Based on the assessed uncertainty, we adaptively adjust the weight of every 3D bbox coordinate via uncertainty regularization, refining the training process on pseudo bboxes. For pseudo bbox coordinate with high uncertainty, we assign a relatively low loss weight. Extensive experiments verify that the proposed method is robust against the noisy pseudo bboxes, yielding substantial improvements on nuScenes and Lyft compared to existing approaches, with increases of +6.9% AP$_{BEV}$ and +2.5% AP$_{3D}$ on nuScenes, and +4.1% AP$_{BEV}$ and +2.0% AP$_{3D}$ on Lyft.

cs.CV↗

arXiv2024

Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations

Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.

cs.CV↗