Recent large vision-language models (LVLMs) for video understanding are primarily fine-tuned with various videos scraped from online platforms. Existing datasets, such as ActivityNet, require considerable human labor for structuring and annotation before effectively utilized for tuning LVLMs. While current LVLMs are primarily trained on existing datasets in broad, general-purpose settings, adapting them to specific downstream scenarios remains challenging, as collecting and annotating task-specific videos is highly labor-intensive and time-consuming. To address this issue, we propose a three-stage framework named DreamFrame for automatically generating style-consistent keyframes and corresponding question-answer (QA) pairs to support LVLM instruction tuning. DreamFrame generates datasets in a movie-like manner. First, we utilize an LLM to generate structured movie plots including movie prior information (like overview and style), frame descriptions and plot-related QA pairs, with a story expansion strategy to mitigate context length limitations. Then, to ensure visual consistency across generated frames, we design a Style Immobilization Process which maintains consistent style through an embedding learning strategy. Finally, frame descriptions and style embeddings are integrated to produce coherent keyframes. Using DreamFrame, we construct a dataset comprising approximately 1k stylized keyframe-like videos and 100k diverse QA pairs. Extensive fine-tuned experiments on various LVLM architectures demonstrate the effectiveness of the proposed dataset. Furthermore, based on the proposed dataset, we fine-tune a new LVLM named DreamFrame-7B, which significantly surpasses the previous similar-sized LVLMs (+2.2 compared with VideoLLaVA-7B on MvBench) across different benchmarks.
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
Aerial navigation is a fundamental yet underexplored capability in embodied intelligence, enabling agents to operate in large-scale, unstructured environments where traditional navigation paradigms fall short. However, most existing research follows the Vision-and-Language Navigation (VLN) paradigm, which heavily depends on sequential linguistic instructions, limiting its scalability and autonomy. To address this gap, we introduce UAV-ON, a benchmark for large-scale Object Goal Navigation (ObjectNav) by aerial agents in open-world environments, where agents operate based on high-level semantic goals without relying on detailed instructional guidance as in VLN. UAV-ON comprises 14 high-fidelity Unreal Engine environments with diverse semantic regions and complex spatial layouts, covering urban, natural, and mixed-use settings. It defines 1270 annotated target objects, each characterized by an instance-level instruction that encodes category, physical footprint, and visual descriptors, allowing grounded reasoning. These instructions serve as semantic goals, introducing realistic ambiguity and complex reasoning challenges for aerial agents. To evaluate the benchmark, we implement several baseline methods, including Aerial ObjectNav Agent (AOA)-a modular policy that integrates instruction semantics with egocentric observations for long-horizon, goal-directed exploration. Empirical results show that all baselines struggle in this setting, highlighting the compounded challenges of aerial navigation and semantic goal grounding. UAV-ON aims to advance research on scalable UAV autonomy driven by semantic goal descriptions in complex real-world environments. Our benchmark and code are available at: https://github.com/Kyaren/UAV_ON.
Gaussian splatting video has recently emerged as a promising representation for immersive 6-degree-of-freedom (6DoF) content due to its low-latency rendering, compact data structure, and high visual fidelity. In particular, 4D Gaussian splatting video-which models dynamic scenes as temporally evolving Gaussian splats in 3D space-offers an efficient solution for rendering photorealistic, interactive experiences. However, a systematic understanding of user behavior in such environments, especially head movement, remains largely unexplored due to the absence of dedicated datasets tailored to this format. This lack of data severely limits progress in viewpoint prediction, attention modeling, and video streaming optimization. To address this critical gap, we introduce ViewGauss-the first publicly available dataset that captures full 6DoF head movement during the viewing of 4D Gaussian splatting videos. Our dataset is collected from 35 participants using a high-precision Vive Focus Vision headset in a controlled environment, while they freely watched four reconstructed Gaussian splatting video sequences derived from the HiFi4G dataset. The data are recorded with high temporal resolution using position coordinates and unit quaternions, and organized into structured CSV files with precise timestamps for downstream synchronization and behavioral analysis. To demonstrate the practical value of ViewGauss, we conduct a preliminary viewpoint prediction experiment using the iTransformer model. The results show that head orientation patterns in 4D Gaussian splatting video scenes are not only temporally coherent but also learnable, highlighting the potential of ViewGauss as a benchmark for future behavioral modeling and predictive rendering systems. The dataset is publicly available at: https://github.com/Cedarleigh/ViewGauss-DataSet.
Identifying individual animals within large wildlife populations is essential for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown promise in animal re-identification (Animal ReID) by leveraging data from camera traps. However, existing Animal ReID datasets rely exclusively on visual data, overlooking environmental metadata that ecologists have identified as highly correlated with animal behavior and identity, such as temperature and circadian rhythms. Moreover, the emergence of multimodal models capable of jointly processing visual and textual data presents new opportunities for Animal ReID, but existing datasets fail to leverage these models' text-processing capabilities, limiting their full potential. To address these limitations, we propose MetaWild, a multimodal Animal ReID dataset comprising 20,890 images across six species, paired with environmental metadata extracted from embedded camera trap overlays and scene contexts. Additionally, to facilitate the use of metadata in existing ReID methods, we propose the Meta-Feature Adapter (MFA), a lightweight module that can be incorporated into existing vision-language model (VLM)-based Animal ReID methods, allowing ReID models to leverage both environmental metadata and visual information to improve ReID performance. Experiments on MetaWild show that combining baseline ReID models with MFA to incorporate metadata consistently improves performance compared to using visual information alone, validating the effectiveness of incorporating metadata in re-identification. We hope that our proposed dataset can inspire further exploration of multimodal approaches for Animal ReID. Our dataset and supplementary materials are available at https://jim-lyz1024.github.io/MetaWild/.
Intention recognition has traditionally focused on individual intentions, overlooking the complexities of collective intentions in group settings. To address this limitation, we introduce the concept of group intention, which represents shared goals emerging through the actions of multiple individuals, and Group Intention Forecasting (GIF), a novel task that forecasts when group intentions will occur by analyzing individual actions and interactions before the collective goal becomes apparent. To investigate GIF in a specific scenario, we propose SHOT, the first large-scale dataset for GIF, consisting of 1,979 basketball video clips captured from 5 camera views and annotated with 6 types of individual attributes. SHOT is designed with 3 key characteristics: multi-individual information, multi-view adaptability, and multi-level intention, making it well-suited for studying emerging group intentions. Furthermore, we introduce GIFT (Group Intention ForecasTer), a framework that extracts fine-grained individual features and models evolving group dynamics to forecast intention emergence. Experimental results confirm the effectiveness of SHOT and GIFT, establishing a strong foundation for future research in group intention forecasting. The dataset is available at https://xinyi-hu.github.io/SHOT\_DATASET.
We present ICS-MR, a dataset containing three conversational scenarios designed for the evaluation of communication quality in Mixed Reality (MR) systems. Along with detailed descriptions of the conversation tasks, we provide all the materials required to incorporate the tasks into MR user studies. The materials also support application of the scenarios in real-world and video-conferencing contexts for studies that, for example, call for comparison of immersive systems against reference communication media. Open-source Unity implementations of the scenarios are also made available, supporting direct usage of the scenarios in distributed, multi-user experiments. The conversation tasks have all been administered in recent scientific works that address the evaluation of user experiences in immersive communication systems, allowing analysis and comparison of each scenario's evoked behavioral properties. The ICS-MR dataset therefore contributes valuable resources for further research on communication in immersive systems.
Stereoscopic video has long been the subject of research due to its ability to deliver immersive three-dimensional content to a wide range of applications. The dual-view format inherently provides binocular disparity cues that enhance depth perception and realism, making it indispensable for fields such as telepresence, 3D mapping, and robotic vision. Until recently, however, end-to-end pipelines for capturing, encoding, and viewing high-quality stereoscopic video were neither widely accessible nor optimized for consumer-grade devices. Today's smartphones, such as the iPhone Pro, and modern Head-Mounted Displays (HMDs) like the Apple Vision Pro, offer built-in support for stereoscopic video capture, hardware-accelerated encoding, and seamless playback on devices like the Apple Vision Pro and Meta Quest 3, which require minimal user intervention. Apple refers to this streamlined workflow as spatial Video. Making the full stereoscopic video process available to everyone has made new applications possible. Despite these advances, there remains a notable absence of publicly available datasets that include the complete spatial video pipeline on consumer platforms, hindering reproducibility and comparative evaluation of emerging algorithms. In this paper, we introduce SVD, a spatial video dataset comprising 300 five-second video sequences, i.e., 150 captured using an iPhone Pro and 150 with an Apple Vision Pro. Additionally, 10 longer videos with durations ranging from 2 min, 29 s to 5 min have been recorded. The SVD dataset is publicly released to facilitate research in codec performance evaluation, subjective and objective Quality of Experience assessment, depth-based computer vision, stereoscopic video streaming, and other emerging 3D applications such as neural rendering and volumetric capture. Link to the dataset: https://cd-athena.github.io/SVD/.
The SEAR Dataset is a novel multimodal resource designed to study the emerging threat of social engineering (SE) attacks orchestrated through augmented reality (AR) and multimodal large language models (LLMs). This dataset captures 180 annotated conversations across 60 participants in simulated adversarial scenarios, including meetings, classes and networking events. It comprises synchronized AR-captured visual/audio cues (e.g., facial expressions, vocal tones), environmental context, and curated social media profiles, alongside subjective metrics such as trust ratings and susceptibility assessments. Key findings reveal SEAR's alarming efficacy in eliciting compliance (e.g., 93.3% phishing link clicks, 85% call acceptance) and hijacking trust (76.7% post-interaction trust surge). The dataset supports research in detecting AR-driven SE attacks, designing defensive frameworks, and understanding multimodal adversarial manipulation. Rigorous ethical safeguards, including anonymization and IRB compliance, ensure responsible use. The SEAR dataset is available at https://github.com/INSLabCN/SEAR-Dataset.
The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of objects in single viewpoint, and annotations often link instructions to single objects, missing richer contextual alignments between multiple objects. This significantly curtails the development of models capable of deep, multi-view 3D scene understanding over distant objects. To address these challenges, we introduce MV-ScanQA, a novel 3D question answering dataset where 68% of questions explicitly require integrating information from multiple views (compared to less than 7% in existing datasets), thereby rigorously testing multi-view compositional reasoning. To facilitate the training of models for such demanding scenarios, we present TripAlign dataset, a large-scale and low-cost 2D-3D-language pre-training corpus containing 1M <2D view, set of 3D objects, text> triplets that explicitly aligns groups of contextually related objects with text, providing richer, view-grounded multi-object multimodal alignment signals than previous single-object annotations. We further develop LEGO, a baseline method for the multi-view reasoning challenge in MV-ScanQA, transferring knowledge from pre-trained 2D LVLMs to 3D domain with TripAlign. Empirically, LEGO pre-trained on TripAlign achieves state-of-the-art performance not only on the proposed MV-ScanQA, but also on existing benchmarks for 3D dense captioning and question answering. Datasets and code are available at https://matthewdm0816.github.io/tripalign-mvscanqa.
Visual tracking has seen remarkable advancements, largely driven by the availability of large-scale training datasets that have enabled the development of highly accurate and robust algorithms. While significant progress has been made in tracking general objects, research on more challenging scenarios, such as tracking camouflaged objects, remains limited. Camouflaged objects, which blend seamlessly with their surroundings or other objects, present unique challenges for detection and tracking in complex environments. In critical fields like military, security, agriculture, and marine monitoring, accurately tracking camouflaged objects is essential. To address this gap, we introduce the Camouflaged Object Tracking Dataset (COTD), a specialized benchmark designed specifically for evaluating camouflaged object tracking methods. The COTD dataset comprises 200 sequences and approximately 80,000 frames, each annotated with detailed bounding boxes. Our evaluation of 20 existing tracking algorithms reveals significant deficiencies in their performance with camouflaged objects. To address these issues, we propose a novel tracking framework, HIPTrack-MLS, which demonstrates promising results in improving tracking performance for camouflaged objects. COTD and code are avialable at https://github.com/openat25/HIPTrack-MLS.
Deception detection has garnered increasing attention in recent years due to the significant growth of digital media and heightened ethical and security concerns. It has been extensively studied using multimodal methods, including video, audio, and text. In addition, individual differences in deception production and detection are believed to play a crucial role. Although some studies have utilized individual information such as personality traits to enhance the performance of deception detection, current systems remain limited, partly due to a lack of sufficient datasets for evaluating performance. To address this issue, we introduce a multimodal deception dataset MDPE. Besides deception features, this dataset also includes individual differences information in personality and emotional expression characteristics. It can explore the impact of individual differences on deception behavior. It comprises over 104 hours of deception and emotional videos from 193 subjects. Furthermore, we conducted numerous experiments to provide valuable insights for future deception detection research. MDPE not only supports deception detection, but also provides conditions for tasks such as personality recognition and emotion recognition, and can even study the relationships between them. We believe that MDPE will become a valuable resource for promoting research in the field of affective computing.
Skin Neglected Tropical Diseases (NTDs) impose severe health and socioeconomic burdens in impoverished tropical communities. Yet, advancements in AI-driven diagnostic support are hindered by data scarcity, particularly for underrepresented populations and rare manifestations of NTDs. Existing dermatological datasets often lack the demographic and disease spectrum crucial for developing reliable recognition models of NTDs. To address this, we introduce eSkinHealth, a novel dermatological dataset collected on-site in Côte d'Ivoire and Ghana. Specifically, eSkinHealth contains 5,623 images from 1,639 cases and encompasses 47 skin diseases, focusing uniquely on skin NTDs and rare conditions among West African populations. We further propose an AI-expert collaboration paradigm to implement foundation language and segmentation models for efficient generation of multimodal annotations, under dermatologists' guidance. In addition to patient metadata and diagnosis labels, eSkinHealth also includes semantic lesion masks, instance-specific visual captions, and clinical concepts. Overall, our work provides a valuable new resource and a scalable annotation framework, aiming to catalyze the development of more equitable, accurate, and interpretable AI tools for global dermatology.
With the rapid progress of Multimodal LLMs, evaluating their mathematical reasoning capabilities has become an increasingly important research direction. In particular, visual-textual mathematical reasoning serves as a key indicator of an MLLM's ability to comprehend and solve complex, multi-step quantitative problems. While existing benchmarks such as MathVista and MathVerse have advanced the evaluation of multimodal math proficiency, they primarily rely on digitally rendered content and fall short in capturing the complexity of real-world scenarios. To bridge this gap, we introduce MathScape, a novel benchmark focused on assessing MLLMs' reasoning ability in realistic mathematical contexts. MathScape comprises 1,369 high-quality math problems paired with human-captured real-world images, closely reflecting the challenges encountered in practical educational settings. We conduct a thorough multi-dimensional evaluation across nine leading closed-source MLLMs, three open-source MLLMs with over 20 billion parameters, and seven smaller-scale MLLMs. Our results show that even SOTA models struggle with real-world math tasks, lagging behind human performance-highlighting critical limitations in current model capabilities. Moreover, we find that strong performance on synthetic or digitally rendered images does not guarantee similar effectiveness on real-world tasks. This underscores the necessity of MathScape in the next stage of multimodal mathematical reasoning.
Ultra-low bitrate image compression is a challenging and demand- ing topic. With the development of Large Multimodal Models (LMMs), a Cross Modality Compression (CMC) paradigm of Image-Text- Image has emerged. Compared with traditional codecs, this semantic- level compression can reduce image data size to 0.1% or even lower, which has strong potential applications. However, CMC has cer- tain defects in consistency with the original image and perceptual quality. To inspire insights into such a problem, we introduce CMC- Bench, a benchmark of the cooperative performance of Image-to- Text (I2T) and Text-to-Image (T2I) models for image compression. This benchmark covers 18,000 and 40,000 images respectively to verify 6 mainstream I2T and 12 T2I models, including 160,000 sub- jective preference scores annotated by human experts. At ultra-low bitrates, it proves that the combination of some I2T and T2I models has surpassed the most advanced visual signal codecs; meanwhile, it highlights where LMMs can be further optimized toward the compression task. We encourage LMM developers to participate in this test to promote the evolution of visual signal codec protocols.
Building Information Model (BIM) has become a significantly digital platform for representing buildings in the Architecture, Engineering, and Construction (AEC) industry. However, the absence of extensive, class- diverse, and balanced datasets at the BIM component level has limited the development of AI-driven BIM analysis. In this study, BIMCompNet is proposed as a large-scale multimodal dataset from Industry Foundation Classes (IFC), which can learn BIM component geometry features from multiple representation methods, including rendered views, point clouds, mesh structures, voxel grids, and semantic graphs. BIMCompNet is constructed by a standardized two-stage processing pipeline: (1) At the model level, geometry units are normalized to the SI units, models are converted to the IFC format, metadata is anonymized, and components are automatically extracted into individual IFC files. (2) At the component level, semantic labels are corrected, geometry and positioning are aligned, duplicates at model and project levels are removed, and five synchronized modalities (OBJ meshes, multi-view images, point clouds, voxel grids, and heterogeneous IFC graphs) are generated. BIMCompNet comprises 1,304,206 cleaned and labeled components across 87 IFC classes, collected from 1,607 real-world BIM models spanning 14 building types. To mitigate class imbalance, underrepresented classes are merged, and dominant classes are down-sampled to create balanced subsets suitable for robust AI model training and benchmarking. Benchmarking is performed on classification tasks by different models with multiple data modalities. Both the dataset and the processing pipeline will be publicly released to support reproducibility and private dataset extension.
Recent advancements in Large Multimodal Models (LMMs) have shown promise in Autonomous Driving Systems (ADS). However, their direct application to ADS is hindered by challenges such as misunderstanding of traffic knowledge, complex road conditions, and diverse states of vehicle. To address these challenges, we propose the use of Knowledge Editing, which enables targeted modifications to a model's behavior without the need for full retraining. Meanwhile, we introduce ADS-Edit, a multimodal knowledge editing dataset specifically designed for ADS, which includes various real-world scenarios, multiple data types, and comprehensive evaluation metrics. We conduct comprehensive experiments and derive several interesting conclusions. We hope that our work will contribute to the further advancement of knowledge editing applications in the field of autonomous driving.
As an increasing number of users share their lives and mental states on social media, many studies attempt to detect depression risk through social media videos using non-verbal cues like facial expressions, posture, gaze, and intonation from individual social media platforms, a proven effective field. However, these studies have focused on single-video level analysis to detect depression. These researches fail to capture the dynamic nature of social media streams and the complex, often gradual manifestation of depression. This limitation overlooks the comprehensive mental state of users, which can only be understood through their extended video histories. To address this, we introduce the Multimodal User-level Depression Detection Dataset (MUD3). MUD3 includes the long-term video histories of depressed users on social media platforms, containing user mental states across multiple videos and treating the video histories as a continuous social media stream. This allows us to model multiple videos at the user-level and analyze users' long-term mental states. MUD3 and supplementary materials are available at https://github.com/Syx1030/MUD3.
Visual Question Answering (VQA) in remote sensing (RS) is pivotal for interpreting Earth observation data. However, existing RS VQA datasets are constrained by limitations in annotation richness, question diversity, and the assessment of specific reasoning capabilities. This paper introduces Remote Sensing Vision Language Model Question Answering (RSVLM-QA) dataset, a new large-scale, content-rich VQA dataset for the RS domain. RSVLM-QA is constructed by integrating data from several prominent RS segmentation and detection datasets: WHU, LoveDA, INRIA, and iSAID. We employ an innovative dual-track annotation generation pipeline. Firstly, we leverage Large Language Models (LLMs), specifically GPT-4.1, with meticulously designed prompts to automatically generate a suite of detailed annotations including image captions, spatial relations, and semantic tags, alongside complex caption-based VQA pairs. Secondly, to address the challenging task of object counting in RS imagery, we have developed a specialized automated process that extracts object counts directly from the original segmentation data; GPT-4.1 then formulates natural language answers from these counts, which are paired with preset question templates to create counting QA pairs. RSVLM-QA comprises 13,820 images and 162,373 VQA pairs, featuring extensive annotations and diverse question types. We provide a detailed statistical analysis of the dataset and a comparison with existing RS VQA benchmarks, highlighting the superior depth and breadth of RSVLM-QA's annotations. Furthermore, we conduct benchmark experiments on Six mainstream Vision Language Models (VLMs), demonstrating that RSVLM-QA effectively evaluates and challenges the understanding and reasoning abilities of current VLMs in the RS domain. We believe RSVLM-QA will serve as a pivotal resource for the RS VQA and VLM research communities, poised to catalyze advancements in the field. The dataset, generation code, and benchmark models are publicly available at https://github.com/StarZi0213/RSVLM-QA.
Recently, numerous benchmarks have been constructed to evaluate various general capabilities (e.g., perception and reasoning) of Vision-Language Large Models (VLLMs). However, few studies have focused on the robustness of VLLMs when dealing with altered prompts and images. To fill this gap, this paper first constructs a real-world, high-quality, and challenging benchmark, namely RBench (i.e., Robust Bench). Specifically, RBench is human-annotated, with both prompts and images being modified to enrich the difficulty, and cross-validation to ensure data quality. Then, we propose a new method, called Robustness Booster (RBoost in short), to effectively enhance the robustness of existing VLLMs by automatically generating high-value instruction-tuning training data. Extensive experiments demonstrate the vulnerability of existing VLLMs when handling altered inputs, and the superiority of our RBoost method in improving model robustness. RBench is available at https://github.com/zhaominyiz/RBench.
CT reconstruction provides radiologists with images for diagnosis and treatment, yet current deep learning methods are typically limited to specific anatomies and datasets, hindering generalization ability to unseen anatomies and lesions. To address this, we introduce the Multi-Organ medical image REconstruction (MORE) dataset, comprising CT scans across 9 diverse anatomies with 15 lesion types. This dataset serves two key purposes: (1) enabling robust training of deep learning models on extensive, heterogeneous data, and (2) facilitating rigorous evaluation of model generalization for CT reconstruction. We further establish a strong baseline solution that outperforms prior approaches under these challenging conditions. Our results demonstrate that: (1) a comprehensive dataset helps improve the generalization capability of models, and (2) optimization-based methods offer enhanced robustness for unseen anatomies. The MORE dataset is freely accessible under CC-BY-NC 4.0 at our project page https://more-med.github.io/.