相关论文: HuM-Eval: A Coarse-to-Fine Framework for Human-Cen…
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic…
Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two…
We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality…
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches…
The rapid advancement of AI-generated video models has created a pressing need for robust and interpretable evaluation frameworks. Existing metrics are limited to producing numerical scores without explanatory comments, resulting in low…
Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since…
Machine translation evaluation is a very important activity in machine translation development. Automatic evaluation metrics proposed in literature are inadequate as they require one or more human reference translations to compare them with…
Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this paper, we propose a simple yet effective model for 3D human…
Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…
We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models' ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual,…
As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fr\'echet Video Distance (FVD), Inception Score (IS), and ClipSim, measure quality primarily…
High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR) input sequence in the image space using optical flow, and…
Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchmarks largely focus on single-task settings and lack fine-grained, human-centric…
What does it mean for two videos to be similar? Videos may appear similar when judged by the actions they depict, yet entirely different if evaluated based on the locations where they were filmed. While humans naturally compare videos by…
Human pose estimation is one of the key problems in computer vision that has been studied in the recent years. The significance of human pose estimation is in the higher level tasks of understanding human actions applications such as…
Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video generation, design animation imposes structured constraints: specific components…
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…
This study investigates the use of large language models (LLMs) for human behavior understanding by jointly leveraging motion and video data. We argue that integrating these complementary modalities is essential for capturing both…
As video generation models achieve unprecedented capabilities, the demand for robust video evaluation metrics becomes increasingly critical. Traditional metrics are intrinsically tailored for short-video evaluation, predominantly assessing…
Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move…