Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs - either text prompts or individual reference images. In this paper, we focus on the task of controllable image generation using multiple visual references. We introduce MultiRef-bench, a rigorous evaluation framework comprising 990 synthetic and 1,000 real-world samples that require incorporating visual content from multiple reference images. The synthetic samples are synthetically generated through our data engine RefBlend, with 10 reference types and 33 reference combinations. Based on RefBlend, we further construct a dataset MultiRef containing 38k high-quality images to facilitate further research. Our experiments across three interleaved image-text models (i.e., OmniGen, ACE, and Show-o) and six agentic frameworks (e.g., ChatDiT and LLM + SD) reveal that even state-of-the-art systems struggle with multi-reference conditioning, with the best model OmniGen achieving only 66.6% in synthetic samples and 79.0% in real-world cases on average compared to the golden answer. These findings provide valuable directions for developing more flexible and human-like creative tools that can effectively integrate multiple sources of visual inspiration. The dataset is publicly available at: https://multiref.github.io/.
论文检索
输入标题、作者或关键词，从 1,620 篇学术成果中精准定位
Preserving the semantic integrity of image details is difficult in neural image compression. Failure to do so can result in miscompressions: reconstruction errors that change the meaning between the original and reconstructed images. Undetected miscompressions can compromise the reliability of reconstructed images and potentially reduce the accuracy of downstream computer vision tasks. To advance research on this problem, we present SCLIC, a curated dataset of 18k human-annotated miscompressions generated by 12 neural compression models. It includes images from three common benchmark datasets, compressed and reconstructed using codecs based on CNNs, GANs, diffusion models, and image transformers for different perceptual metrics and rate-distortion settings. We envision that this dataset will facilitate the development of strategies to mitigate miscompressions and enable more reliable neural image compression codecs.
EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluation
PDF ↗Instruction-based garment editing enables precise image modifications via natural language, with broad applications in fashion design and customization. Unlike general editing tasks, it requires understanding garment-specific semantics and attribute dependencies. However, progress is limited by the scarcity of high-quality instruction-image pairs, as manual annotation is costly and hard to scale. While MLLMs have shown promise in automated data synthesis, their application to garment editing is constrained by imprecise instruction modeling and a lack of fashion-specific supervisory signals. To address these challenges, we present an automated pipeline for constructing a garment editing dataset. We first define six editing instruction categories aligned with real-world fashion workflows to guide the generation of balanced and diverse instruction-image triplets. Second, we introduce Fashion Edit Score, a semantic-aware evaluation metric that captures semantic dependencies between garment attributes and provides reliable supervision during construction. Using this pipeline, we construct a total of 52,257 candidate triplets and retain 20,596 high-quality triplets to build EditGarment, the first instruction-based dataset tailored to standalone garment editing. The project page is https://yindq99.github.io/EditGarment-project/.
Detecting hate speech in videos remains challenging due to the complexity of multimodal content and the lack of fine-grained annotations in existing datasets. We present HateClipSeg, a large-scale multimodal dataset with both video-level and segment-level annotations, comprising over 11,714 segments labeled as Normal or across five Offensive categories: Hateful, Insulting, Sexual, Violence, Self-Harm, along with explicit target victim labels. Our three-stage annotation process yields high inter-annotator agreement (Krippendorff's alpha = 0.817). We propose three tasks to benchmark performance: (1) Trimmed Hateful Video Classification, (2) Temporal Hateful Video Localization, and (3) Online Hateful Video Classification. Results highlight substantial gaps in current models, emphasizing the need for more sophisticated multimodal and temporally aware approaches. The HateClipSeg dataset are publicly available at https://github.com/Social-AI-Studio/HateClipSeg.git.
Multimodal Large Language Models (MLLMs) have garnered significant attention for their strong visual-semantic understanding. Most existing chart benchmarks evaluate MLLMs' ability to parse information from charts to answer questions. However, they overlook the inherent output biases of MLLMs, where models rely on their parametric memory to answer questions rather than genuinely understanding the chart content. To address this limitation, we introduce a novel Chart Hypothetical Question Answering (HQA) task, which imposes assumptions on the same question to compel models to engage in counterfactual reasoning based on the chart content. Furthermore, we introduce HAI, a human-AI interactive data synthesis approach that leverages the efficient text-editing capabilities of LLMs alongside human expert knowledge to generate diverse and high-quality HQA data at a low cost. Using HAI, we construct Chart-HQA, a challenging benchmark synthesized from publicly available data sources. Evaluation results on 18 MLLMs of varying model sizes reveal that current models face significant generalization challenges and exhibit imbalanced reasoning performance on the HQA task. Our codebase and newly generated datasets are available at https://github.com/chenxn2020/Chart-HQA.
Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of complexity stratification, and fragmented evaluation paradigms. We introduce SVGenius, a comprehensive benchmark comprising 2,377 queries across three progressive dimensions: understanding, editing, and generation. Built on real-world data from 24 application domains with systematic complexity stratification, SVGenius evaluates models through 8 task categories and 18 metrics. We assess 22 mainstream models spanning different scales, architectures, training paradigms, and accessibility levels. Our analysis reveals that while proprietary models significantly outperform open-source counterparts, all models exhibit systematic performance degradation with increasing complexity, indicating fundamental limitations in current approaches; however, reasoning-enhanced training proves more effective than pure scaling for overcoming these limitations, though style transfer remains the most challenging capability across all model types. SVGenius establishes the first systematic evaluation framework for SVG processing, providing crucial insights for developing more capable vector graphics models and advancing automated graphic design applications. Appendix and supplementary materials (including all data and code) are available at https://zju-real.github.io/SVGenius.
This study centers on the creation of a novel dog bark emotion dataset, EmotionalCanines, capturing the emotional spectrum of canine vocalizations. In the current literature on animal communication and its intersection with machine learning, there is a limited amount of open-sourced data available to facilitate research, mainly due to constraints in animal subjects and recording conditions. To address this gap, we propose a framework that enables the collection of reliable arousal and valence labels in animal emotional state at scale. Through its application, we built a dataset of 1,400 dog bark sequences with corresponding arousal and valence labels, the largest of its kind, for the Husky and Shiba Inu dog breeds. By constructing this dataset, we provide a foundation for decoding dog bark patterns and advancing animal communication research.
Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with ''one click,'' existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge this gap, we formally define the form-filling task and propose FormFactory-an interactive benchmarking suite comprising a web-based interface, backend evaluation module, and carefully constructed dataset. Our benchmark covers diverse real-world scenarios, incorporates various field formats, and simulates high-fidelity form interactions. We conduct a comprehensive evaluation of state-of-the-art MLLMs and observe that no model surpasses 5% accuracy, underscoring the inherent difficulty of the task. These findings also reveal significant limitations in current models' visual layout reasoning and field-value alignment abilities.
Recent rapid progress in Text-to-Audio (T2A) models contrasts sharply with the stagnation observed in the evolution of corresponding evaluation benchmarks. Existing benchmarks, such as AudioCaps, suffer from limited diversity and quality, as well as biased category distributions, leading to increasingly questionable reliability in assessing advanced T2A models. This paper introduces AudioAtlas, a comprehensive and balanced evaluation benchmark specifically designed for evaluating T2A models aimed at movie production. Based on an object-centric audio category system, AudioAtlas provides high-quality reference samples characterized by categorical balance and diversity. It includes detailed overall and event-level captions with rich descriptors, plus fine-grained temporal annotations from human experts, enabling thorough evaluation of temporal alignment and semantic accuracy. To enable precise evaluation of temporally-aligned generation across universal categories, two novel metrics are proposed leveraging recent advancements in large-scale Audio Language Models (AudioLLMs) and contrastive learning models. By re-benchmarking six currently influential T2A models, AudioAtlas provides evaluations better aligned with aesthetic considerations, offering clearer optimization directions for movie-production-oriented T2A systems. Additionally, we conduct a comprehensive comparative analysis on temporally-controllable T2A methods with training-based, and promising training-free approaches inspired by region-controllable image generation, clarifying current limitations and pointing out directions for future research. Audio specifically refers to sound event excluding speech and music. Further details are available on the project page: https://audioatlas.github.io/AudioAtlas/
The rapid advancement of GenAI technology over the past few years has significantly contributed towards highly realistic deepfake content generation. Despite ongoing efforts, the research community still lacks a large-scale and reasoning capability driven deepfake benchmark dataset specifically tailored for person-centric object, context and scene manipulations. In this paper, we address this gap by introducing MultiFakeVerse, a large scale person-centric deepfake dataset, comprising 845,286 images generated through manipulation suggestions and image manipulations both derived from vision-language models (VLM). The VLM instructions were specifically targeted towards modifications to individuals or contextual elements of a scene that influence human perception of importance, intent, or narrative. This VLM-driven approach enables semantic, context-aware alterations such as modifying actions, scenes, and human-object interactions rather than synthetic or low-level identity swaps and region-specific edits that are common in existing datasets. Our experiments reveal that current state-of-the-art deepfake detection models and human observers struggle to detect these subtle yet meaningful manipulations. The code and dataset are available on https://github.com/Parul-Gupta/MultiFakeVerse GitHub.
Osteoporosis has emerged as a significant global public health challenge, affecting more than 200 million people worldwide. Precise screening through bone mineral density (BMD) assessment is essential for timely intervention. Although dual-energy X-ray absorptiometry (DXA) serves as the gold standard for BMD evaluation, its widespread application is hampered by high costs and limited accessibility. In recent years, deep learning has demonstrated great potential in osteoporosis classification and predicting BMD from X-ray and CT scans. However, existing public datasets have notable limitations, particularly the absence of paired multimodal imaging datasets for cross-modal modeling and the lack of accurate BMD annotations required for osteoporosis-specific research and clinical model optimization. To address these issues, we introduce the Lumbar Multimodal Osteoporosis Screening dataset (LUMOS), the first multimodal dataset specifically designed for lumbar osteoporosis screening. LUMOS integrates clinical data from 803 patients, including 1,620 anteroposterior/lateral lumbar X-rays with BMD values and T-scores, comprehensive demographic information, and 280 lumbar CT scans. The advent of LUMOS is expected to propel forward research on automated osteoporosis classification, BMD prediction, and other related tasks. Its standardized and multimodal nature fills critical gaps in lumbar osteoporosis data, providing high-quality data support for the development and validation of medical AI algorithms in the early detection of osteoporosis. The dataset is available at https://keyueshi.github.io/LUMOS/.
Understanding the interaction between different drugs (drug-drug interaction or DDI) is critical for ensuring patient safety and optimizing therapeutic outcomes. Existing DDI datasets primarily focus on textual information, overlooking multimodal data that reflect complex drug mechanisms. In this paper, we (1) introduce MUDI, a large-scale Multimodal biomedical dataset for Understanding pharmacodynamic Drug-drug Interactions, and (2) benchmark learning methods to study it. In brief, MUDI provides a comprehensive multimodal representation of drugs by combining pharmacological text, chemical formulas, molecular structure graphs, and images across 310,532 annotated drug pairs labeled as Synergism, Antagonism, or New Effect. Crucially, to effectively evaluate machine-learning based generalization, MUDI consists of unseen drug pairs in the test set. We evaluate benchmark models using both late fusion voting and intermediate fusion strategies. All data, annotations, evaluation scripts, and baselines are released under an open research license.
Rapid advances in Artificial Intelligence Generated Content (AIGC) have enabled increasingly sophisticated face forgeries, posing a significant threat to social security. However, current Deepfake detection methods are limited by constraints in existing datasets, which lack the diversity necessary in real-world scenarios. Specifically, these data sets fall short in four key areas: unknown of advanced forgery techniques, variability of facial scenes, richness of real data, and degradation of real-world propagation. To address these challenges, we propose the Multi-dimensional Face Forgery Image (MFFI ) dataset, tailored for real-world scenarios. MFFI enhances realism based on four strategic dimensions: 1) Wider Forgery Methods; 2) Varied Facial Scenes; 3) Diversified Authentic Data; 4) Multi-level Degradation Operations. MFFI integrates 50 different forgery methods and contains 1024K image samples. Benchmark evaluations show that MFFI outperforms existing public datasets in terms of scene complexity, cross-domain generalization capability, and detection difficulty gradients. These results validate the technical advance and practical utility of MFFI in simulating real-world conditions. The dataset and additional details are publicly available at https://github.com/inclusionConf/MFFI.
Short video platforms are popular for sharing information, but they also spread harmful content quickly. Research on detecting harmful videos is limited due to unclear categories and a lack of good datasets. To solve this, we created CH-SV, the first Chinese Harmful Short Video dataset with 6,728 videos labeled into six categories: danger, offense, vulgarity, fakeness, violence, and normal content. We analyzed CH-SV in detail and proposed HAVE, a new detection framework that improves video understanding using AI-generated semantics. Experiments on CH-SV show that our dataset can help advance harmful video detection research, and HAVE outperforms existing methods. Resources including core code, dataset samples, supplementary material, and licensing details are available at https://github.com/DLUTSSL/CH-SV.
Despite growing interest in Ultra-High-Definition (UHD) content, research and development on 8K videos remains constrained by the scarcity and limited quantity of publicly available footage, the lack of accessible, high-quality datasets, and the substantial computational cost of processing such data. To address this gap, we present the VIdeo Dataset for Exploration and Analysis (VIDEA-8K-60FPS), an open 8K 60FPS HDR video dataset comprising 190 video sequences (120x10s, 40x30s, 30x60s) containing more than an hour of unique footage and covering a diverse range of use cases in terms of motion, lighting, colors, and camera stability. Each clip was minimally processed and encoded with lossless-tuned HEVC, achieving approximately 70% file size reduction while preserving visual integrity, allowing the dataset to be more accessible. The dataset is designed to be diverse to support various video research fields. By making VIDEA-8K-60FPS publicly available, we aim to lower the barrier to 8K video research and facilitate the development of more efficient and scalable video processing methods. GitHub: https://github.com/talshoura/VIDEA-8K-60FPS-Dataset
Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images. While recent advances in multi-modal learning have significantly improved performance, current methods still suffer from limited answer reliability and poor interpretability, impairing the ability of clinicians and patients to understand and trust model outputs. To address these limitations, this work first proposes a Region-Aware Multimodal Chain-of-Thought (RMCoT) dataset, in which the process of producing an answer is preceded by a sequence of intermediate reasoning steps that explicitly ground relevant visual regions of the medical image, thereby providing fine-grained explainability. Furthermore, we introduce a novel verifiable reward mechanism for reinforcement learning to guide post-training, improving the alignment between the model's reasoning process and its final answer. Remarkably, our method achieves comparable performance using only one-eighth of the training data, demonstrating the efficiency and effectiveness of the proposal. The dataset is available at https://www.med-vqa.com/GEMeX/.
Food image classification models are crucial for dietary management applications because they reduce the burden of manual meal logging. However, most publicly available datasets for training such models rely on web-crawled images, which often differ from users' real-world meal photos. In this work, we present FoodLogAthl-218, a food image dataset constructed from real-world meal records collected through the dietary management application FoodLog Athl. The dataset contains 6,925 images across 218 food categories, with a total of 14,349 bounding boxes. Rich metadata, including meal date and time, anonymized user IDs, and meal-level context, accompany each image. Unlike conventional datasets-where a predefined class set guides web-based image collection-our data begins with user-submitted photos, and labels are applied afterward. This yields greater intra-class diversity, a natural frequency distribution of meal types, and casual, unfiltered images intended for personal use rather than public sharing. In addition to (1) a standard classification benchmark, we introduce two FoodLog-specific tasks: (2) an incremental fine-tuning protocol that follows the temporal stream of users' logs, and (3) a context-aware classification task where each image contains multiple dishes, and the model must classify each dish by leveraging the overall meal context. We evaluate these tasks using large multimodal models (LMMs). The dataset is publicly available at https://huggingface.co/datasets/FoodLog/FoodLogAthl-218.
As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited datasets, where the training and testing sets share the same distribution. In this paper, we consider the task of adapting indoor 3D object detectors from one dataset to another, presenting a comprehensive benchmark with ScanNet, SUN RGB-D and 3D Front datasets, as well as our newly proposed large-scale datasets ProcTHOR-OD and ProcFront generated by a 3D simulator. Since indoor point cloud datasets are collected and constructed in different ways, the object detectors are likely to overfit to specific factors within each dataset, such as point cloud quality, bounding box layout and instance features. We conduct experiments across datasets on different adaptation scenarios including synthetic-to-real adaptation, point cloud quality adaptation, layout adaptation and instance adaptation, analyzing the impact of different domain gaps on 3D object detectors. We also introduce several approaches to improve adaptation performances, providing baselines for domain adaptive indoor 3D object detection, hoping that future works may propose detectors with stronger generalization ability across domains. The benchmark datasets and baseline code are available on our project homepage: https://jeremyzhao1998.github.io/DAVoteNet-release.
To meet the growing demand for systematic surgical training, wet-lab environments have become indispensable platforms for hands-on practice in ophthalmology. Yet, traditional wet-lab training depends heavily on manual performance evaluations, which are labor-intensive, time-consuming, and often subject to variability. Recent advances in computer vision offer promising avenues for automated skill assessment, enhancing both the efficiency and objectivity of surgical education. Despite notable progress in ophthalmic surgical datasets, existing resources predominantly focus on real surgeries or isolated tasks, falling short of supporting comprehensive skill evaluation in controlled wet-lab settings. To address these limitations, we introduce WetCat, the first dataset of wet-lab cataract surgery videos specifically curated for automated skill assessment. WetCat comprises high-resolution recordings of surgeries performed by trainees on artificial eyes, featuring comprehensive phase annotations and semantic segmentations of key anatomical structures. These annotations are meticulously designed to facilitate skill assessment during the critical capsulorhexis and phacoemulsification phases, adhering to standardized surgical skill assessment frameworks. By focusing on these essential phases, WetCat enables the development of interpretable, AI-driven evaluation tools aligned with established clinical metrics. This dataset lays a strong foundation for advancing objective, scalable surgical education and sets a new benchmark for automated workflow analysis and skill assessment in ophthalmology training. The dataset and annotations are publicly available in Synapse (https://www.synapse.org/Synapse:syn66401174/files/).
Large-scale high-quality 3D motion datasets with multi-person interactions are crucial for data-driven models in autonomous driving to achieve fine-grained pedestrian interaction understanding in dynamic urban environments. However, existing datasets mostly rely on estimating 3D poses from monocular RGB video frames, which suffer from occlusion and lack of temporal continuity, thus resulting in unrealistic and low-quality human motion. In this paper, we introduce Waymo-3DSkelMo, the first large-scale dataset providing high-quality, temporally coherent 3D skeletal motions with explicit interaction semantics, derived from the Waymo Perception dataset. Our key insight is to utilize 3D human body shape and motion priors to enhance the quality of the 3D pose sequences extracted from the raw LiDRA point clouds. The dataset covers over 14,000 seconds across more than 800 real driving scenarios, including rich interactions among an average of 27 agents per scene (with up to 250 agents in the largest scene). Furthermore, we establish 3D pose forecasting benchmarks under varying pedestrian densities, and the results demonstrate its value as a foundational resource for future research on fine-grained human behavior understanding in complex urban environments. The dataset and code will be available at https://github.com/GuangxunZhu/Waymo-3DSkelMo