Hasil untuk "Motion pictures"

D. Chapman, D. M. Kuehn, H. K. Larson

R. Giménez Conejero, Ignacio Breva Ribes

We study corank one $A$-finite germs $f:(\mathbb{R}^n,0)\rightarrow (\mathbb{R}^{n+1},0)$ and their complexifications. More precisely, we study when these germs provide good real pictures of the complex germs, i.e., when there is a real deformation that has the same homology in the image (hence, homotopy) than the generic complex deformation. We give a new sufficient condition that can be computed in practice, as well as examples.

Haiyang Liu, Zhan Xu, Fa-Ting Hong et al.

We present Video Motion Graphs, a system designed to generate realistic human motion videos. Using a reference video and conditional signals such as music or motion tags, the system synthesizes new videos by first retrieving video clips with gestures matching the conditions and then generating interpolation frames to seamlessly connect clip boundaries. The core of our approach is HMInterp, a robust Video Frame Interpolation (VFI) model that enables seamless interpolation of discontinuous frames, even for complex motion scenarios like dancing. HMInterp i) employs a dual-branch interpolation approach, combining a Motion Diffusion Model for human skeleton motion interpolation with a diffusion-based video frame interpolation model for final frame generation. ii) adopts condition progressive training to effectively leverage identity strong and weak conditions, such as images and pose. These designs ensure both high video texture quality and accurate motion trajectory. Results show that our Video Motion Graphs outperforms existing generative- and retrieval-based methods for multi-modal conditioned human motion video generation. Project page can be found at https://h-liu1997.github.io/Video-Motion-Graphs/

Daniel Leão

A derrubada de Dilma Rousseff levou à realização de um número inusual de filmes. Parte considerável desses foi dirigido e editado por mulheres — Karen Akerman (O Processo de Maria Ramos, 2017), Karen Harley (Democracia em Vertigem de Petra Costa, 2019), Vânia Debs e Anna Muylaert (em Alvorada de Muylaert e Politi, 2020) e Paula Fabiana (2016) também diretora de Filme Manifesto. Analisaremos as operações de montagem predominantes nesses filmes, observando suas especificidades e traços estilísticos. O processo cria a sensação de observação exaustiva e a pontual contraposição com o entorno do congresso; Democracia em Vertigem realiza uma montagem não-linear marcada por elipses motivadas pelas memórias da diretora e pela trama antidemocrática, numa complexa articulação de imagens e sons, que visam o engajamento e a criação de significado à maneira dos soviéticos; Alvorada busca o cotidiano da residência de Dilma em uma linha narrativa que progressivamente ressalta o afastamento da presidenta); Filme manifesto articula, de forma linear, as manifestações até o afastamento de Dilma, contrapondo-as e situando-as a partir de material de arquivo. Abordaremos ainda o filme Sementes – mulheres pretas no poder de Éthel Oliveira e Júlia Mariano (editado por Mariana Penedo) realizado em 2020 [...].

Macdonald, João

Review of the film Ophiussa – Uma Cidade de Fernando Pessoa (2012)

Qing Yu, Mikihiro Tanaka, Kent Fujiwara

To build a cross-modal latent space between 3D human motion and language, acquiring large-scale and high-quality human motion data is crucial. However, unlike the abundance of image data, the scarcity of motion data has limited the performance of existing motion-language models. To counter this, we introduce "motion patches", a new representation of motion sequences, and propose using Vision Transformers (ViT) as motion encoders via transfer learning, aiming to extract useful knowledge from the image domain and apply it to the motion domain. These motion patches, created by dividing and sorting skeleton joints based on body parts in motion sequences, are robust to varying skeleton structures, and can be regarded as color image patches in ViT. We find that transfer learning with pre-trained weights of ViT obtained through training with 2D image data can boost the performance of motion analysis, presenting a promising direction for addressing the issue of limited motion data. Our extensive experiments show that the proposed motion patches, used jointly with ViT, achieve state-of-the-art performance in the benchmarks of text-to-motion retrieval, and other novel challenging tasks, such as cross-skeleton recognition, zero-shot motion classification, and human interaction recognition, which are currently impeded by the lack of data.

Youliang Zhang, Ronghui Li, Yachao Zhang et al.

Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending this capability to high-difficulty motions remains an open challenge. This can be attributed to some flawed motion clips in video-based motion capture results and the inherent complexity in modeling high-difficulty motions. Therefore, sensing the advantage of segmentation in localizing human body, we introduce a mask-based motion correction module (MCM) that leverages motion context and video mask to repair flawed motions, producing imitation-friendly motions; and propose a physics-based motion transfer module (PTM), which employs a pretrain and adapt approach for motion imitation, improving physical plausibility with the ability to handle in-the-wild and challenging motions. Our approach is designed as a plug-and-play module to physically refine the video motion capture results, including high-difficulty in-the-wild motions. Finally, to validate our approach, we collected a challenging in-the-wild test set to establish a benchmark, and our method has demonstrated effectiveness on both the new benchmark and existing public datasets.https://physicalmotionrestoration.github.io

Tianshuo Xu, Zhifei Chen, Leyi Wu et al.

Recent advances in video generation have shown promise for generating future scenarios, critical for planning and control in autonomous driving and embodied intelligence. However, real-world applications demand more than visually plausible predictions; they require reasoning about object motions based on explicitly defined boundary conditions, such as initial scene image and partial object motion. We term this capability Boundary Conditional Motion Reasoning. Current approaches either neglect explicit user-defined motion constraints, producing physically inconsistent motions, or conversely demand complete motion inputs, which are rarely available in practice. Here we introduce Motion Dreamer, a two-stage framework that explicitly separates motion reasoning from visual synthesis, addressing these limitations. Our approach introduces instance flow, a sparse-to-dense motion representation enabling effective integration of partial user-defined motions, and the motion inpainting strategy to robustly enable reasoning motions of other objects. Extensive experiments demonstrate that Motion Dreamer significantly outperforms existing methods, achieving superior motion plausibility and visual realism, thus bridging the gap towards practical boundary conditional motion reasoning. Our webpage is available: https://envision-research.github.io/MotionDreamer/.

António Baía Reis, Guida Mendes, Inês Rebanda Coelho et al.

Winnie Yanjing Wu

This paper critically analyzes the Apple TV+ series Pachinko (2022) to comprehend its cross-historical and cross-regional metanarrative unfolding from the organization of temporality, spatiality, and language. As the TV adaptation of Min Jin Lee’s eponymous novel, Pachinko depicts a family’s migration journey from Korea to Japan after the 1910s and emphasizes their suffering from systemic discrimination against temporary Korean residents. Produced by talents from Korea, Japan, and the United States, Pachinko displays strong hybridization that combines American TV conventions with a distinct East Asian culture and history. The hybridized, multicultural, and multilingual background of the production necessitates a transnational and interdisciplinary framework to analyze its critical success and cultural implications. Expanding Harvey’s notion of time-space compression, the paper conceptualizes the temporal and spatial experience of watching a transnational production via global streaming as a mirrored experience of migrant life. It tackles television dramas as a strategy to understand contemporary migration and globalization by first outlining the evolutionary trajectory of television, and then identifying the movements, mobility, and the transnational cultural flows in Pachinko. Moreover, this paper analyzes the linguistic aspects of Pachinko, particularly in translation and multilingualism, to establish a connection between language and cultural identities. Inquiring into previous literature on translation, this paper also seeks to understand the complexity of communicating in multiple languages, both literally and metaphorically. Finally, this paper examines how migration and migrants are reimagined in Pachinko at a time when national borders and cultural and linguistic barriers are quickly eroded by global streaming TV.

Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda et al.

Pose and motion priors are crucial for recovering realistic and accurate human motion from noisy observations. Substantial progress has been made on pose and shape estimation from images, and recent works showed impressive results using priors to refine frame-wise predictions. However, a lot of motion priors only model transitions between consecutive poses and are used in time-consuming optimization procedures, which is problematic for many applications requiring real-time motion capture. We introduce Motion-DVAE, a motion prior to capture the short-term dependencies of human motion. As part of the dynamical variational autoencoder (DVAE) models family, Motion-DVAE combines the generative capability of VAE models and the temporal modeling of recurrent architectures. Together with Motion-DVAE, we introduce an unsupervised learned denoising method unifying regression- and optimization-based approaches in a single framework for real-time 3D human pose estimation. Experiments show that the proposed approach reaches competitive performance with state-of-the-art methods while being much faster.

Dibyendu Das, Yuanjie Lu, Erion Plaku et al.

When facing a new motion-planning problem, most motion planners solve it from scratch, e.g., via sampling and exploration or starting optimization from a straight-line path. However, most motion planners have to experience a variety of planning problems throughout their lifetimes, which are yet to be leveraged for future planning. In this paper, we present a simple but efficient method called Motion Memory, which allows different motion planners to accelerate future planning using past experiences. Treating existing motion planners as either a closed or open box, we present a variety of ways that Motion Memory can contribute to reduce the planning time when facing a new planning problem. We provide extensive experiment results with three different motion planners on three classes of planning problems with over 30,000 problem instances and show that planning speed can be significantly reduced by up to 89% with the proposed Motion Memory technique and with increasing past planning experiences.

Thomas Schatz

Xiaogang Peng, Yaodi Shen, Haoran Wang et al.

Multi-person motion prediction remains a challenging problem, especially in the joint representation learning of individual motion and social interactions. Most prior methods only involve learning local pose dynamics for individual motion (without global body trajectory) and also struggle to capture complex interaction dependencies for social interactions. In this paper, we propose a novel Social-Aware Motion Transformer (SoMoFormer) to effectively model individual motion and social interactions in a joint manner. Specifically, SoMoFormer extracts motion features from sub-sequences in displacement trajectory space to effectively learn both local and global pose dynamics for each individual. In addition, we devise a novel social-aware motion attention mechanism in SoMoFormer to further optimize dynamics representations and capture interaction dependencies simultaneously via motion similarity calculation across time and social dimensions. On both short- and long-term horizons, we empirically evaluate our framework on multi-person motion datasets and demonstrate that our method greatly outperforms state-of-the-art methods of single- and multi-person motion prediction. Code will be made publicly available upon acceptance.

Mathieu Marsot, Stefanie Wuhrer, Jean-Sebastien Franco et al.

We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion based on a single latent code, with encouraging results for many tasks. Extending these methods to longer motion with various duration and framerate is all but straightforward as one latent code proves inefficient to encode longer term variability. Our hypothesis is that long motions are better represented as a succession of actions than in a single block. By leveraging a sequence-to-sequence architecture, we propose a model that simultaneously learns a temporal segmentation of motion and a prior on the motion segments. To provide flexibility with temporal resolution and motion duration, our representation is continuous in time and can be queried for any timestamp. We show experimentally that our method leads to a significant improvement over state-of-the-art motion priors on a spatio-temporal completion task on sparse pointclouds. Code will be made available upon publication.

Ayu Sartika Br Siregar, Endang Golis L Tobing, Nur Rizka Fitri et al.

Given the importance of vocabulary, teachers must ensure teaching media that can help students learn English vocabulary more easily. In addition, it must equip them to learn in an interesting way so that they are more enthusiastic about the coaching and studying process. One of the many learning media that can be applied for learning English is video. Thus, this study will explain how animated media can help with vocabulary learning for early childhood and the uses and benefits of animated media. This study uses document analysis as the main way to generate arguments in this article, such as Teaching English documents, articles, and books, and document articles from national and international online publications. Based on the research, it may be evident that the software of lively motion pictures contributes to students' vocabulary mastery. The results showed that students can easily recognize the given words because they learn by using animated videos because they can not only display written words but also pictures.

Orhan Sunar

discussions, motion pictures, surgical demonstrations on colour closed circuit television and temporal bone work with Zeiss Microscope. The lectures and demonstrations will be in English. Special emphasis will be given to the technique of preservation of the posterior bony canal wall, (Posterior Tympanotomy, Intact Canal Wall Technique), early endoscopic diagnosis of recurrent disease, reconstruction of posterior bony canal wall and ossicular repair.

Tuo Feng, Dongbing Gu

Recently end-to-end unsupervised deep learning methods have demonstrated an impressive performance for visual depth and ego-motion estimation tasks. These data-based learning methods do not rely on the same limiting assumptions that geometry-based methods do. The encoder–decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of generative adversarial nets (GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation—stacked generative adversarial network. It consists of a stack of GAN layers, of which the lowest layer estimates the depth and ego-motion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. We select the most commonly used KITTI data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation.

Laísi Catharina da Silva Barbalho Braz, Aliete Cristina Gomes Dias Pedrosa da Cunha Oliveira, Arthur Barbalho Braz et al.

Introduction: In addition to its entertainment role, cinema has a strong relationship with history and a significant social appeal, as it provides the possibility of discussing the matters of society in a dynamic way. Important historical facts such as wars, technological development and pandemics have become recurrent themes on the screens, since they impact various social groups. By the same token, the theme of sexually transmitted infections has been extensively explored in motion pictures, portraying the origins of diseases, their impact on the social environment, and how the health-disease process unfolds. Objective: This study aimed to perform a critical analysis of audiovisual works that bring syphilis in its plot, in order to identify and discuss the evolution of the health-disease process throughout history, as well as its representation in the cinematic perspective. Methods: A descriptive analysis of audiovisual works was carried out along with a bibliographic search. Results: The corpus of the study consisted of four films, the feature films: “La Pelle”, by Liliana Cavani; “Miss Evers’ Boys”, by Joseph Sargent; “Heleno: O Príncipe Maldito”, by José Henrique Fonseca; and “Dr. Ehrlich’s Magic Bullet”, by William Dieterle. In all four works, we have different perspectives of the same health problem, but in different scenarios. Conclusion: Reflecting about these scenarios, as well as the real world, helps us to understand and search for what each of the represented groups’ needs in order to face the disease more objectively and effectively.

Dan Hendrycks, Andy Zou, Mantas Mazeika et al.

In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, prediction consistency, resilience to adversaries, calibrated uncertainty estimates, and the ability to detect anomalous inputs. However, improving performance towards these goals is often a balancing act that today's methods cannot achieve without sacrificing performance on other safety axes. For instance, adversarial training improves adversarial robustness but sharply degrades other classifier performance metrics. Similarly, strong data augmentation and regularization techniques often improve OOD robustness but harm anomaly detection, raising the question of whether a Pareto improvement on all existing safety measures is possible. To meet this challenge, we design a new data augmentation strategy utilizing the natural structural complexity of pictures such as fractals, which outperforms numerous baselines, is near Pareto-optimal, and roundly improves safety measures.