Both the colonial and post-independence eras in Cameroon have been characterized by repressive public policies regarding freedom of speech and expression, with strict surveillance on cinematographic expression. In 1934, for example, the French government passed the Laval Decree to prevent cinema from spreading “subversive” or anti-colonial messages. The decree also required the French government’s permission before shooting or showing films in French colonies. The subsequent neo-colonial state, established in 1960, worked hand in glove with the former colonial masters, and it can be argued that this neo-colonial state has survived to the present day. Within a national context characterized by dictatorship, human rights abuses, cultural belligerence/emasculation, poverty, and above all, press censorship, this paper sets out to demonstrate that filmmakers such as Alphonse Beni, Jean Marie Teno, Jean Pierre Bekolo, and Basseck Ba Khobio successfully employ several forms of militant cinema techniques and aesthetics to lend their voices to an oppressed Cameroonian and African society. While filmic approaches like the anti-documentary (Teno) and the Mevungu (Bekolo) are more overt in their deconstructionist agenda, others like “sly civility” (Beni) and “Subtle Deconstruction” (Ba Kobhio) are more veiled, in the register of what James Scott calls “hidden transcripts”. These hidden transcripts here refer to codified stylistic and narrative techniques constructed by oppressed groups as they speak against the injustice of repressive apparatuses or power structures, serving as a means to protest against hegemonic forces while evading their surveillance. From a post-colonial perspective, this paper analyses films from the aforementioned Cameroonian filmmakers, as well as existing literature on Cameroonian cinema. The objective is to shed light on how these committed filmmakers denounce neo-colonialism, dictatorship and cultural alienation on one hand, and the government’s incompetence and insensitivity to the plight of the masses on the other.
Recent advancements in portrait video generation have been noteworthy. However, existing methods rely heavily on human priors and pre-trained generative models, Motion representations based on human priors may introduce unrealistic motion, while methods relying on pre-trained generative models often suffer from inefficient inference. To address these challenges, we propose Semantic Latent Motion (SeMo), a compact and expressive motion representation. Leveraging this representation, our approach achieve both high-quality visual results and efficient inference. SeMo follows an effective three-step framework: Abstraction, Reasoning, and Generation. First, in the Abstraction step, we use a carefully designed Masked Motion Encoder, which leverages a self-supervised learning paradigm to compress the subject's motion state into a compact and abstract latent motion (1D token). Second, in the Reasoning step, we efficiently generate motion sequences based on the driving audio signal. Finally, in the Generation step, the motion dynamics serve as conditional information to guide the motion decoder in synthesizing realistic transitions from reference frame to target video. Thanks to the compact and expressive nature of Semantic Latent Motion, our method achieves efficient motion representation and high-quality video generation. User studies demonstrate that our approach surpasses state-of-the-art models with an 81% win rate in realism. Extensive experiments further highlight its strong compression capability, reconstruction quality, and generative potential.
Stylized motion generation is actively studied in computer graphics, especially benefiting from the rapid advances in diffusion models. The goal of this task is to produce a novel motion respecting both the motion content and the desired motion style, e.g., ``walking in a loop like a Monkey''. Existing research attempts to address this problem via motion style transfer or conditional motion generation. They typically embed the motion style into a latent space and guide the motion implicitly in a latent space as well. Despite the progress, their methods suffer from low interpretability and control, limited generalization to new styles, and fail to produce motions other than ``walking'' due to the strong bias in the public stylization dataset. In this paper, we propose to solve the stylized motion generation problem from a new perspective of reasoning-composition-generation, based on our observations: i) human motion can often be effectively described using natural language in a body-part centric manner, ii) LLMs exhibit a strong ability to understand and reason about human motion, and iii) human motion has an inherently compositional nature, facilitating the new motion content or style generation via effective recomposing. We thus propose utilizing body-part text space as an intermediate representation, and present SMooGPT, a fine-tuned LLM, acting as a reasoner, composer, and generator when generating the desired stylized motion. Our method executes in the body-part text space with much higher interpretability, enabling fine-grained motion control, effectively resolving potential conflicts between motion content and style, and generalizes well to new styles thanks to the open-vocabulary ability of LLMs. Comprehensive experiments and evaluations, and a user perceptual study, demonstrate the effectiveness of our approach, especially under the pure text-driven stylized motion generation.
This paper introduces Motion Personalization, a new task that generates personalized motions aligned with text descriptions using several basic motions containing Persona. To support this novel task, we introduce a new large-scale motion dataset called PerMo (PersonaMotion), which captures the unique personas of multiple actors. We also propose a multi-modal finetuning method of a pretrained motion diffusion model called PersonaBooth. PersonaBooth addresses two main challenges: i) A significant distribution gap between the persona-focused PerMo dataset and the pretraining datasets, which lack persona-specific data, and ii) the difficulty of capturing a consistent persona from the motions vary in content (action type). To tackle the dataset distribution gap, we introduce a persona token to accept new persona features and perform multi-modal adaptation for both text and visuals during finetuning. To capture a consistent persona, we incorporate a contrastive learning technique to enhance intra-cohesion among samples with the same persona. Furthermore, we introduce a context-aware fusion mechanism to maximize the integration of persona cues from multiple input motions. PersonaBooth outperforms state-of-the-art motion style transfer methods, establishing a new benchmark for motion personalization.
Ahmad Mohamad El‐Maissi, Moustafa Moufid Kassem, Fadzli Mohamed Nazri
Over the last decade, the notion of community resilience, which encompasses planning for, opposing, absorbing, and quickly recovering from disruptive occurrences, has gained momentum across the world. Critical Infrastructures (CI) are seen as critical to attaining success in today's densely populated countries. Such infrastructures must be robust in the face of multi-hazard catastrophes by implementing appropriate disaster management and recovery plans. Given these facts, it is critical to establish a new methodological perspective with an integrated system for effective disaster management of CI, as well as an intelligent application that will aid in the construction of more resilient and sustainable cities and communities. This perspective proposes a holistic gaming scenario application for assessing the vulnerability and accessibility of critical infrastructures during multi-hazard events, with a primary focus on conducting an integrated assessment for critical infrastructures and their assets. Mainly, the perspective includes a holistic gaming scenario application that will aid in accurately quantifying geographical spatial information and integrating big data into predictive and prescriptive management tools using virtual reality. • Conducting Integrated Assessment Models for evaluating vulnerability of Critical Infrastructures. • Inducing Digital Technologies during Multi-Hazard Incidents for improving Natural hazard assessment models. • Developing an open-world gaming scenario that is considered with high visual motion pictures and scenes.
Human motion stylization aims to revise the style of an input motion while keeping its content unaltered. Unlike existing works that operate directly in pose space, we leverage the latent space of pretrained autoencoders as a more expressive and robust representation for motion extraction and infusion. Building upon this, we present a novel generative model that produces diverse stylization results of a single motion (latent) code. During training, a motion code is decomposed into two coding components: a deterministic content code, and a probabilistic style code adhering to a prior distribution; then a generator massages the random combination of content and style codes to reconstruct the corresponding motion codes. Our approach is versatile, allowing the learning of probabilistic style space from either style labeled or unlabeled motions, providing notable flexibility in stylization as well. In inference, users can opt to stylize a motion using style cues from a reference motion or a label. Even in the absence of explicit style input, our model facilitates novel re-stylization by sampling from the unconditional style prior distribution. Experimental results show that our proposed stylization models, despite their lightweight design, outperform the state-of-the-art in style reenactment, content preservation, and generalization across various applications and settings. Project Page: https://murrol.github.io/GenMoStyle
The emergence of diffusion models has greatly propelled the progress in image and video generation. Recently, some efforts have been made in controllable video generation, including text-to-video generation and video motion control, among which camera motion control is an important topic. However, existing camera motion control methods rely on training a temporal camera module, and necessitate substantial computation resources due to the large amount of parameters in video generation models. Moreover, existing methods pre-define camera motion types during training, which limits their flexibility in camera control. Therefore, to reduce training costs and achieve flexible camera control, we propose COMD, a novel training-free video motion transfer model, which disentangles camera motions and object motions in source videos and transfers the extracted camera motions to new videos. We first propose a one-shot camera motion disentanglement method to extract camera motion from a single source video, which separates the moving objects from the background and estimates the camera motion in the moving objects region based on the motion in the background by solving a Poisson equation. Furthermore, we propose a few-shot camera motion disentanglement method to extract the common camera motion from multiple videos with similar camera motions, which employs a window-based clustering technique to extract the common features in temporal attention maps of multiple videos. Finally, we propose a motion combination method to combine different types of camera motions together, enabling our model a more controllable and flexible camera control. Extensive experiments demonstrate that our training-free approach can effectively decouple camera-object motion and apply the decoupled camera motion to a wide range of controllable video generation tasks, achieving flexible and diverse camera motion control.
We consider the Kepler two-body problem in the presence of a cosmological constant Lambda. Several dimensionless parameters characterizing the possible orbit typologies are used to identify open and closed trajectories. The qualitative picture of the two-body motion is described and critical parameters of the problem are found.
Large language models (LLMs) are, by design, inherently capable of multi-task learning: through a unified next-token prediction paradigm, they can naturally address a wide variety of downstream tasks. Prior work in the motion domain has demonstrated some generality by adapting LLMs via a Motion Tokenizer coupled with an autoregressive Transformer to generate and understand human motion. However, this generality remains limited in scope and yields only modest performance gains. We introduce VersatileMotion, a unified multimodal motion LLM that combines a novel motion tokenizer, integrating VQ-VAE with flow matching, and an autoregressive transformer backbone to seamlessly support at least nine distinct motion-related tasks. VersatileMotion is the first method to handle single-agent and multi-agent motions in a single framework and enable cross-modal conversion between motion, text, music, and speech, achieving state-of-the-art performance on seven of these tasks. Each sequence in MotionHub may include one or more of the following annotations: natural-language captions, music or audio clips, speech transcripts, and multi-agent interaction data. To facilitate evaluation, we define and release benchmark splits covering nine core tasks. Extensive experiments demonstrate the superior performance, versatility, and potential of VersatileMotion as a foundational model for future understanding and generation of motion.
Joaquim Ortiz-Haro, Wolfgang Hönig, Valentin N. Hartmann
et al.
Rapidly-exploring Random Trees (RRT) and its variations have emerged as a robust and efficient tool for finding collision-free paths in robotic systems. However, adding dynamic constraints makes the motion planning problem significantly harder, as it requires solving two-value boundary problems (computationally expensive) or propagating random control inputs (uninformative). Alternatively, Iterative Discontinuity Bounded A* (iDb-A*), introduced in our previous study, combines search and optimization iteratively. The search step connects short trajectories (motion primitives) while allowing a bounded discontinuity between the motion primitives, which is later repaired in the trajectory optimization step. Building upon these foundations, in this paper, we present iDb-RRT, a sampling-based kinodynamic motion planning algorithm that combines motion primitives and trajectory optimization within the RRT framework. iDb-RRT is probabilistically complete and can be implemented in forward or bidirectional mode. We have tested our algorithm across a benchmark suite comprising 30 problems, spanning 8 different systems, and shown that iDb-RRT can find solutions up to 10x faster than previous methods, especially in complex scenarios that require long trajectories or involve navigating through narrow passages.
Nikos Athanasiou, Alpár Cseke, Markos Diomataris
et al.
The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. In this paper, we address both challenges. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text, introducing the new MotionFix dataset. Access to this data allows us to train a conditional diffusion model, TMED, that takes both the source motion and the edit text as input. We develop several baselines to evaluate our model, comparing it against models trained solely on text-motion pair datasets, and demonstrate the superior performance of our model trained on triplets. We also introduce new retrieval-based metrics for motion editing, establishing a benchmark on the evaluation set of MotionFix. Our results are promising, paving the way for further research in fine-grained motion generation. Code, models, and data are available at https://motionfix.is.tue.mpg.de/ .
Objectives. The paper considers a satellite with an optoelectronic payload designed to take pictures of the Earth’s surface. The work sets out to develop a mathematical model for determining the dependencies between the state vector of the satellite, the state vector of the point being imaged on the Earth’s surface, and the distribution fields of the velocity vectors and accelerations of the motion of the image along the focal plane of the optoelectronic payload.Methods. The method is based on double differentiation of the photogrammetry equation when applied to a survey of the Earth’s surface from space. For modeling the orbital and angular motion of the satellite, differential equations with numerical integration were used. The motion parameters of the Earth’s surface were calculated based on the Standards of Fundamental Astronomy software library.Results. Differential equations of motion of the image were obtained. Verification of the developed mathematical model was carried out. The motion of the considered satellite was simulated in orbital orientation mode using an image velocity compensation model. The distribution fields of velocity vectors and accelerations of motion of the image of the Earth’s surface were constructed. The residual motion of the field of image following compensation was investigated.Conclusions. The proposed mathematical model can be used both with an optoelectronic payload when modeling shooting modes and estimating image displacements at the design stage of a satellite, as well as at the satellite operation stage when incorporating the presented model in the onboard satellite software. The presented dependencies can also be used to construct an image transformation matrix, both when restoring an image and when obtaining a super-resolution.
Das Thema “kulturelles Erbe und Nachhaltigkeit” des “World Summit of Arts Education in Funchal.Madeira.Portugal” im März 2023 gab den Impuls, ein künstlerisches Forschungsprojekt “4 questions about nature” vor Ort zu entwickeln, um Beziehungen zwischen persönlichen Orten, Natur und Nachhaltigkeit aufdecken zu können. Die ortsbezogene künstlerische Forschungsmethode des Displacements, des In-Beziehung-Setzens von unterschiedlichen Positionen zu einem Thema wie Nachhaltigkeit, ermöglicht es, divergente Aspekte auch ungewöhnlich assoziativ miteinander zu vernetzen, um neue Perspektiven aufzeigen zu können. Mit Michel Foucault (1967) wird der Raum als ein Netzwerk verstanden, welches aus vielen Orten besteht. Orte stehen in Beziehung zueinander und erhalten neben ihrer physischen auch eine diskursive Bedeutung durch Geschichten, welche Menschen an Orten erleben und über Orte erzählen. Mit dem Forschungsprojekt wurden diese Geschichten erkundet, indem zehn Menschen interviewt wurden. Das Besondere an diesen Interviews war, dass die Antworten zu einer Art Ortskarte aus Schrift und Bild skizziert wurden. Derart sind zehn ortsbezogene Karten entstanden, welche nach ihrem Lesen zu einer “Landkarte der Beziehungen zwischen persönlichen Orten–Natur–Nachhaltigkeit” als künstlerisches Ergebnis der Erforschung transformiert wurden. Mit dem künstlerischen Forschungsprojekt wird die bislang vernachlässigte kulturelle Dimension von Nachhaltigkeit mit dem Motiv aufgezeigt, das Drei-Säulen-Modell (Ökolologie, Ökonomie, Soziales) von Nachhaltigkeit um die kulturelle Dimension [...].
This work targets a novel text-driven whole-body motion generation task, which takes a given textual description as input and aims at generating high-quality, diverse, and coherent facial expressions, hand gestures, and body motions simultaneously. Previous works on text-driven motion generation tasks mainly have two limitations: they ignore the key role of fine-grained hand and face controlling in vivid whole-body motion generation, and lack a good alignment between text and motion. To address such limitations, we propose a Text-aligned whOle-body Motion generATiOn framework, named HumanTOMATO, which is the first attempt to our knowledge towards applicable holistic motion generation in this research area. To tackle this challenging task, our solution includes two key designs: (1) a Holistic Hierarchical VQ-VAE (aka H$^2$VQ) and a Hierarchical-GPT for fine-grained body and hand motion reconstruction and generation with two structured codebooks; and (2) a pre-trained text-motion-alignment model to help generated motion align with the input textual description explicitly. Comprehensive experiments verify that our model has significant advantages in both the quality of generated motions and their alignment with text.
This note aims at clarifying some mathematical aspects of what is known in Physics as \emph{Picture Changing Operator} (PCO). In particular, we want to show that PCOs are chain maps between the complex of differential forms (or superforms) and the complex of integral forms on a given supermanifold. We comment on the construction of (super)symmetric PCOs in terms of chain homotopies and we provide some physically relevant examples of applications.
The murder of George Floyd in 2020 drew new attention to the discourse surrounding representation in North America. Western sports leagues have been at the forefront of race conversations during this time, but the dialogue extends to popular sports films as well. Through a critical discourse analysis, this MRP argues that there are several insights to be learned from the digital afterlives of three sports films. This study first outlines examples of how the White saviour trope is enacted in Glory Road (2006) and The Blind Side (2009), and how the academically poor performing Black student-athlete trope is performed in Coach Carter (2005). Next, it explores the digital afterlives of these films today, specifically on Twitter. The findings suggest that each film occupies a significant space in the lives of its viewers. The digital afterlives provide insights into the importance of education in the athlete-student relationship, racism of the past and how much has or has not changed, the formation of the family unit, and the issues that arise from using films as a teaching tool for Black pain. The digital afterlives of these films create space for a discussion about these insights, which is significant during a time of cancel culture as this culture contributes to the demise of critical thinking with its emphasis on turning the cheek to something that does not agree with one’s ideologies rather than responsibly and cognitively interacting with contrary views. To help stop this close-minded cycle and foster an understanding for how to critically examine films and other media texts, a media literacy assignment for middle school students accompanies this MRP.<div><br></div><div> Keywords: Black, athletes, sports films, tropes, stereotypes, representation, race, digital afterlife, Twitter, media literacy, Coach Carter, Glory Road, The Blind Side</div>
We consider the free motion of a point particle inside a circular billiard with periodically moving boundary, with the assumption that the collisions of the particle with the boundary are elastic so that the energy of the particle is not preserved. It is known that if the motion of the boundary is regular enough then the energy is bounded due to the existence of invariant curves. We show that it is nevertheless possible that the motion of the particle is chaotic, also under regularity assumptions for the moving boundary. More precisely, we show that there exists a class of functions describing the motion of the boundary for which the billiard map admits invariant probability measures with positive metric entropy. The proof relies on variational techniques based on Aubry-Mather theory.
Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category. This paper, on the other hand, considers a relativelynew problem, which could be thought of as an inverse of actionrecognition: given a prescribed action type, we aim to generateplausible human motion sequences in 3D. Importantly, the set ofgenerated motions are expected to maintain itsdiversityto be ableto explore the entire action-conditioned motion space; meanwhile,each sampled sequence faithfully resembles anaturalhuman bodyarticulation dynamics. Motivated by these objectives, we followthe physics law of human kinematics by adopting the Lie Algebratheory to represent thenaturalhuman motions; we also propose atemporal Variational Auto-Encoder (VAE) that encourages adiversesampling of the motion space. A new 3D human motion dataset, HumanAct12, is also constructed. Empirical experiments overthree distinct human motion datasets (including ours) demonstratethe effectiveness of our approach.