Breaking is a dance duel between two dancers to music improvised by a DJ. Since breaking was chosen as an official competition at the Paris Olympics, many people have begun to watch the competitions on television. When a dancer freezes in time with a beat or scratch in breaking, it is called ''kill the beat,'' and when it is successful, the audience gets very excited. However, TV viewers may have difficulty hearing the music due to the announcer's or commentator's voice, making it difficult to judge if the kill the beat is successful or not. In addition, some in the audience may be hard of hearing. Therefore, we developed a visualizer for the beats and scratches of breaking DJ performances.
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
1,620篇论文
第 11 / 81 页
StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
PDF ↗The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two critical limitations: 1) Static annotation mechanisms fail to capture the evolving nature of answers in temporal video streams, and 2) The absence of explicit reasoning process annotations restricts model interpretability and logical deduction capabilities. To address these challenges, we introduce StreamingCoT, the first dataset explicitly designed for temporally evolving reasoning in streaming VideoQA and multimodal Chain-of-Thought (CoT) tasks. Our framework first establishes a dynamic hierarchical annotation architecture that generates per-second dense descriptions and constructs temporally-dependent semantic segments through similarity fusion, paired with question-answer sets constrained by temporal evolution patterns. We further propose an explicit reasoning chain generation paradigm that extracts spatiotemporal objects via keyframe semantic alignment, derives object state transition-based reasoning paths using large language models, and ensures logical coherence through human-verified validation. This dataset establishes a foundation for advancing research in streaming video understanding, complex temporal reasoning, and multimodal inference. Our StreamingCoT and its construction toolkit can be accessed at https://github.com/Fleeting-hyh/StreamingCoT.
Stickers, though small, are a highly condensed form of visual expression, ubiquitous across messaging platforms and embraced by diverse cultures, genders, and age groups. Despite their popularity, sticker retrieval remains an underexplored task due to the significant human effort and subjectivity involved in constructing high-quality query-sticker datasets. Although large language models (LLMs) excel at general NLP tasks, they falter when confronted with the nuanced, intangible, and highly specific nature of sticker query generation. To address the challenge of collecting diverse and contextually appropriate sticker search queries, we introduce Sticktionary, a gamified annotation framework designed to elicit high-quality, semantically rich queries from contributors. Using this framework, we construct StickerQueries, a multilingual dataset comprising 1,115 English and 615 Chinese sticker search queries, annotated by over 60 contributors across more than 60 hours of annotation. We demonstrate the utility of StickerQueries in several downstream tasks, including query generation and sticker retrieval. Through comprehensive quantitative and qualitative evaluations, we demonstrate that StickerQueries significantly improves the quality of query generation, retrieval accuracy, and semantic understanding within the sticker domain. To support future research, we publicly release the multilingual StickerQueries dataset and two fine-tuned query generation models. Additional experiments and supplementary case studies can be found here.
The widespread deployment of large models in resource-constrained environments has underscored the need for efficient transmission of intermediate feature representations. In this context, feature coding, which compresses features into compact bitstreams, becomes a critical component for scenarios involving feature transmission, storage, and reuse. However, this compression process inevitably introduces semantic degradation that is difficult to quantify with traditional metrics. To address this, we formalize the research problem of Compressed Feature Quality Assessment (CFQA), aiming to evaluate the semantic fidelity of compressed features. To advance CFQA research, we propose the first benchmark dataset, comprising 300 original features and 12000 compressed features derived from three vision tasks and four feature codecs. Task-specific performance degradation is provided as true semantic distortion for evaluating CFQA metrics. We systematically assess three widely used metrics -- MSE, cosine similarity, and Centered Kernel Alignment (CKA) -- in terms of their ability to capture semantic degradation. Our findings demonstrate the representativeness of the proposed dataset while underscoring the need for more sophisticated metrics capable of measuring semantic distortion in compressed features. This work advances the field by establishing a foundational benchmark and providing a critical resource for the community to explore CFQA. To foster further research, we release the dataset and all associated source code at https://github.com/chansongoal/Compressed-Feature-Quality-Assessment.
Despite rapid advances, Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge, which correspond to faithfulness and factuality hallucinations, respectively. Prior studies primarily evaluate faithfulness hallucination at a rather coarse level (e.g., object-level) and lack fine-grained analysis. Additionally, existing benchmarks often rely on costly manual curation or reused public datasets, raising concerns about scalability and data leakage. To address these limitations, we propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data. We also design a hierarchical hallucination induction framework with input perturbations to simulate realistic noisy scenarios. Integrating these designs, we construct SHALE, a Scalable HALlucination Evaluation benchmark designed to assess both faithfulness and factuality hallucinations via a fine-grained hallucination categorization scheme. SHALE comprises over 30K image-instruction pairs spanning 12 representative visual perception aspects for faithfulness and 6 knowledge domains for factuality, considering both clean and noisy scenarios. Extensive experiments on over 20 mainstream LVLMs reveal significant factuality hallucinations and high sensitivity to semantic perturbations.
Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists of 6K high-quality claims drawn from authoritative sources, encompassing multimodal content and diverse domains. Our evaluation framework further introduces the Unknown Rate (UnR) metric, enabling a more nuanced assessment of models' ability to handle uncertainty and balance between over-conservatism and over-confidence. Extensive experiments on 7 representative LLMs and 4 MLLMs reveal their limitations in real-world fact-checking and offer valuable insights for further research. RealFactBench is publicly available at https://github.com/kalendsyang/RealFactBench.git.
Screen sharing is a common feature in video conferencing applications, especially for remote work and presentations. However, internet conditions such as limited bandwidth, packet loss, and compression can significantly reduce the visual quality of shared screen content. Most existing video quality metrics are designed for natural scenes and were not benchmarked on screen content. In this work, we present a large-scale subjective dataset of screen content videos captured from video conferencing apps. The dataset includes 1,600 distorted videos with corresponding subjective quality scores. Subjective scores were collected using crowdsourced pairwise comparisons. The dataset provides a valuable resource for developing and benchmarking video quality metrics tailored to screen content. The evaluation of objective metrics revealed that several general-purpose quality metrics outperform both full-reference and no-reference metrics. The dataset is available at the following link: https://videoprocessing.github.io/screen-content-dataset.
The field of video generation has witnessed remarkable advances in recent years, driven by innovations in deep generative models. Nevertheless, the fidelity of AI-generated videos remains far from perfect, with synthesized content frequently exhibiting visual artifacts, such as temporally inconsistent motion, physically implausible trajectories, unnatural object deformations, and local blurring, that undermine realism and user trust. Precise detection and spatial localization of these artifacts are of critical importance: not only are they essential for automatic quality control pipelines that improves user experience, but they also provide actionable diagnostic signals for researchers and practitioners to guide model development and evaluation. Despite its significance, the research community currently lacks a comprehensive benchmark tailored for artifact localization in AI-generated videos. Existing datasets either focus solely on detection at the video or frame level, or lack fine-grained spatial annotations necessary for developing and benchmarking localization methods. To fill this gap, we present BrokenVideos, a benchmark dataset comprising ~3,254 AI-generated videos with carefully-annotated, pixel-level masks indicating regions of visual corruption. Each annotation is the result of careful human inspection, ensuring high-quality ground truth for artifact localization tasks. We demonstrate that training existing video artifact detection models and multi-modal large language models (MLLMs) on BrokenVideos substantially enhances their ability to localize corrupted regions within generated content. Through extensive experiments and cross-model evaluations, we show that BrokenVideos provides a critical foundation for both benchmarking and advancing artifact localization research. We hope our dataset can catalyze further innovation in both video generation and its quality assurance. The dataset is available at: https://broken-video-detection-datetsets.github.io/Broken-Video-Detection-Datasets.github.io/.
As camera-equipped robotic platforms become increasingly integrated into daily life, robotic-generated videos have begun to appear on streaming media platforms, enabling us to envision a future where humans and robots coexist. We innovatively propose the concept of Robotic-Generated Content (RGC) to term these videos generated from egocentric perspective of robots. The perceptual quality of RGC videos is critical in human-robot interaction scenarios, and RGC videos exhibit unique distortions and visual requirements that differ markedly from those of professionally-generated content (PGC) videos and user-generated content (UGC) videos. However, dedicated research on quality assessment of RGC videos is still lacking. To address this gap and to support broader robotic applications, we establish the first Robotic-Generated Content Database (RGCD), which contains a total of 2,100 videos drawn from three robot categories and sourced from diverse platforms. A subjective VQA experiment is conducted subsequently to assess human visual perception of robotic-generated videos. Finally, we conduct a benchmark experiment to evaluate the performance of 11 state-of-the-art VQA models on our database. Experimental results reveal significant limitations in existing VQA models when applied to complex, robotic-generated content, highlighting a critical need for RGC-specific VQA models. Our RGCD is publicly available at: https://github.com/IntMeGroup/RGC-VQA.
We propose the LEHA-CVQAD (Large-scale Enriched Human Annotated) dataset, which comprises 6,240 clips for compression-oriented video quality assessment. 59 source videos are encoded with 186 codec-preset variants, ≈1.8M pairwise, and ≈1.5k MOS ratings are fused into a single quality scale; part of the videos remains hidden for blind evaluation. We also propose Rate-Distortion Alignment Error (RDAE), a novel evaluation metric that quantifies how well VQA models preserve bitrate-quality ordering, directly supporting codec parameter tuning. Testing IQA/VQA methods reveals that popular VQA metrics exhibit high RDAE and lower correlations, underscoring the dataset's challenges and utility. The open part and the results of LEHA-CVQAD are available at https://aleksandrgushchin.github.io/lcvqad/
Emerging text-to-3D generative models based on large diffusion backbones have markedly lowered the barrier to high-quality 3D asset creation, yet rigorous quantitative evaluation remains elusive. We introduce T23D-QA, a novel open benchmark that couples diverse prompts, multiple generation paradigms, and fine-grained human judgements for text-conditioned 3D synthesis. The dataset comprises 1,710 textured meshes produced by nine state-of-the-art pipelines spanning feed-forward, optimization-based, and view-reconstruction families. Assets are driven by a tri-categorical prompt suite: single-object, multi-object, and primitive-anchored, covering 160 ShapeNet-level object classes. Each mesh is rated by 20 participants along three orthogonal dimensions: geometry, texture, and alignment. Building upon this corpus, we propose an evaluator that decouples multi-modal features via cross-attention. On T23D-QA, our baseline surpasses the strongest published metric by 8.1% (geometry), 6.1% (texture), and 1.9% (alignment) in Spearman rank correlation. Dataset and code are publicly available at https://t23d-qa.github.io to foster reproducible research.
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ''chain'' instructions where operations are interdependent. Current models struggle with these intricate directives, and existing benchmarks inadequately evaluate such capabilities. Specifically, they often overlook multi-instruction and chain-instruction complexities, and common consistency metrics are flawed. To address this, we introduce ComplexBench-Edit, a novel benchmark designed to systematically assess model performance on complex, multi-instruction, and chain-dependent image editing tasks. ComplexBench-Edit also features a new vision consistency evaluation method that accurately assesses non-modified regions by excluding edited areas. Furthermore, we propose a simple yet powerful Chain-of-Thought (CoT)-based approach that significantly enhances the ability of existing models to follow complex instructions. Our extensive experiments demonstrate ComplexBench-Edit's efficacy in differentiating model capabilities and highlight the superior performance of our CoT-based method in handling complex edits. The data and code are released at https://github.com/llllly26/ComplexBench-Edit.
The increasing demand for large-scale, high-quality datasets in dynamic point cloud compression (PCC) and human visual perception research underscores the limitations of existing datasets, which are often constrained by limited scale and insufficient dynamism, hindering algorithm validation and perceptual analysis in complex scenarios. To address this gap, we present DPCSet, a comprehensive dynamic point cloud dataset designed to support advanced research in PCC, human perception, and related domains. Comprising 100 dynamic object point clouds-the largest collection of its kind-DPCSet includes 200-frame sequences with geometry and attribute information, capturing diverse object types across real and virtual environments. Organized into seven superclasses, the dataset ensures broad scenario coverage. By rigorous selection, format conversion, quantization, DPCSet delivers standardized, high-precision point cloud data. Evaluation of multiple compression algorithms on a curated subset demonstrates DPCSet's efficacy in assessing trade-offs between compression efficiency and quality loss, positioning it as a potential benchmark for PCC. Furthermore, just noticeable distortion (JND) experiments on a compression-distorted subset reveal distinct perceptual characteristics of dynamic point clouds, offering valuable insights for perception-driven compression algorithms. The dataset is released at https://openi.pcl.ac.cn/gaowx/DPCSet.
Human-centric videos play a significant role in the pervasive video content of modern life. However, the capabilities of text-to-video (T2V) generation models and video-to-text (V2T) understanding models for human-centric videos remain largely unexplored. To this end, we present HVEval, the first comprehensive evaluation dataset focusing on human-centric videos, which consists of 20,000 videos, 60k MOS annotations across 3 dimensions (i.e., spatial quality, temporal quality, and text-video correspondence), and 20k category-specific Q&A pairs. Based on the HVEval dataset, this paper aims to answer three questions: (1) can today's T2V models effectively generate human-centric videos following the given prompts? (2) how effective are today's V2T LMMs in understanding and evaluating human-centric videos? (3) are current VQA metrics good enough for evaluating human-centric videos? Comprehensive evaluations of 24 T2V models, 20 LMMs, and 18 VQA metrics reveal their limitations in fine-grained text-controlled generation and human-aligned perception and understanding, highlighting the significant potential of our dataset and benchmarks to advance research in human-centric video generation and understanding.
Progress in understanding real-world canine vocal communication is constrained by datasets lacking scale and 'in-the-wild' diversity. We introduce DogSpeak, a large-scale public dataset of 77,202 Barkseqs (33.162 hours) from 156 dogs (5 breeds), uniquely sourced from online social media with accurate dog ID, sex, and breed labels. DogSpeak, one of the largest of its kind, addresses prior limitations. Benchmark tasks (sex, breed, individual dog recognition) demonstrate its utility and highlight how its inherent real-world challenges necessitate and foster research into more robust bioacoustic models, preprocessing, and feature representation.
Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not capture the quality of generated results. To address these issues, we introduce an approach to synthesizing a text removal benchmark applicable to domains other than scene texts. Our dataset features text rendered on complex backgrounds using object-aware placement and vision-language model-generated content, ensuring clean ground truth and challenging text removal scenarios. The dataset is available at https://huggingface.co/datasets/cyberagent/OTR.
Low-light Image Enhancement (LIE) technology adaptively improves brightness while preserving texture details and suppressing noise artifacts, thereby reducing visual degradation caused by insufficient illumination. While deep learning-based image enhancement algorithms have made significant progress, a key gap remains in establishing standardized methods for fairly evaluating and comparing their performance. To bridge this gap, this paper systematically investigates enhanced low-light image quality assessment from both subjective and objective dimensions. First, we introduce a Real-world Low-light Image Enhancement quality assessment dataset (RLIE), which contains 1540 images from 154 scenarios, each with a subjective score given by the subjects. Based on this, we propose a low light enhanced image quality assessment method based on Multi-level Illumination Injection and Hierarchical Discrepancy Perception (MIIHDP). The core idea of this method is to hierarchically inject separated illumination information into the feature extraction process, then tailor the processing of difference information at different scales to obtain a more comprehensive representation. Finally, extensive statistical analyses demonstrate the rationality of the proposed RLIE dataset, and experimental results show the superior performance of the proposed MIIHDP compared with state-of-the-arts. Our dataset and code are released at: https://github.com/BoHu90/RLIE.
Recent advances in AI-generated content have fueled the rise of highly realistic synthetic videos, posing severe risks to societal trust and digital integrity. Existing benchmarks for video authenticity detection typically suffer from limited realism, insufficient scale, and inadequate complexity, failing to effectively evaluate modern vision-language models against sophisticated forgeries. To address this critical gap, we introduce AEGIS, a novel large-scale benchmark explicitly targeting the detection of hyper-realistic and semantically nuanced AI-generated videos. AEGIS comprises over 10,000 rigorously curated real and synthetic videos generated by diverse, state-of-the-art generative models, including Stable Video Diffusion, CogVideoX-5B, KLing, and Sora, encompassing open-source and proprietary architectures. In particular, AEGIS features specially constructed challenging subsets enhanced with GPT-4o-refined prompts, creating unprecedentedly realistic scenarios for rigorous robustness evaluation. Furthermore, we provide multimodal annotations spanning Semantic-Authenticity Descriptions, Motion Features, and Low-level Visual Features, facilitating authenticity detection and supporting downstream tasks such as multimodal fusion and forgery localization. Extensive experiments using advanced vision-language models demonstrate limited detection capabilities on the most challenging subsets of AEGIS, highlighting the dataset's unique complexity and realism beyond the current generalization capabilities of existing models. In essence, AEGIS establishes an indispensable evaluation benchmark, fundamentally advancing research toward developing genuinely robust, reliable, and broadly generalizable video authenticity detection methodologies capable of addressing real-world forgery threats. Our dataset is avaliable on https://huggingface.co/datasets/Clarifiedfish/AEGIS.
Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into natural scenes. Although RGB-based methods have advanced, their performance remains limited under challenging conditions. Multispectral imagery, providing rich spectral information, offers a promising alternative for enhanced foreground-background discrimination. However, existing COD benchmark datasets are exclusively RGB-based, lacking essential support for multispectral approaches, which has impeded progress in this area. To address this gap, we introduce MCOD, the first challenging benchmark dataset specifically designed for multispectral camouflaged object detection. MCOD features three key advantages: (i) Comprehensive challenge attributes: It captures real-world difficulties such as small object sizes and extreme lighting conditions commonly encountered in COD tasks. (ii) Diverse real-world scenarios: The dataset spans a wide range of natural environments to better reflect practical applications. (iii) High-quality pixel-level annotations: Each image is manually annotated with precise object masks and corresponding challenge attribute labels. We benchmark eleven representative COD methods on MCOD, observing a consistent performance drop due to increased task difficulty. Notably, integrating multispectral modalities substantially alleviates this degradation, highlighting the value of spectral information in enhancing detection robustness. We anticipate MCOD will provide a strong foundation for future research in multispectral camouflaged object detection. The dataset is publicly accessible at https://github.com/yl2900260-bit/MCOD.
Robotic task planning in real-world environments requires not only object recognition but also a nuanced understanding of spatial relationships between objects. We present a spatial-relationship-aware dataset of nearly 1,000 robot-acquired indoor images, annotated with object attributes, positions, and detailed spatial relationships. Captured using a Boston Dynamics Spot robot and labelled with a custom annotation tool, the dataset reflects complex scenarios with similar or identical objects and intricate spatial arrangements. We benchmark six state-of-the-art scene-graph generation models on this dataset, analysing their inference speed and relational accuracy. Our results highlight significant differences in model performance and demonstrate that integrating explicit spatial relationships into foundation models, such as ChatGPT 4o, substantially improves their ability to generate executable, spatially-aware plans for robotics. The dataset and annotation tool are publicly available at https://github.com/PengPaulWang/SpatialAwareRobotDataset, supporting further research in spatial reasoning for robotics.