Diverse Motion Stylization for Multiple Style Domains via Spatial-Temporal Graph-Based Generative Model

This paper presents a novel deep learning-based framework for translating a motion into various styles within multiple domains. Our framework is a single set of generative adversarial networks that learns stylistic features from a collection of unpaired motion clips with style labels to support mapping between multiple style domains. We construct a spatio-temporal graph to model a motion sequence and employ the spatial-temporal graph convolution networks (ST-GCN) to extract stylistic properties along spatial and temporal dimensions. Through spatial-temporal modeling, our framework shows improved style translation results between significantly different actions and on a long motion sequence containing multiple actions. In addition, we first develop a mapping network for motion stylization that maps a random noise to style, which allows for generating diverse stylization results without using reference motions. Through various experiments, we demonstrate the ability of our method to generate improved results in terms of visual quality, stylistic diversity, and content preservation.

Horizontal connectivity in V1 : Prediction of coherence in contour and motion integration

This study demonstrates the functional importance of the Surround context relayed laterally in V1 by the horizontal connectivity, in controlling the latency and the gain of the cortical response to the feedforward visual drive. We report here four main findings : 1) a centripetal apparent motion sequence results in a shortening of the spiking latency of V1 cells, when the orientation of the local inducer and the global motion axis are both co-aligned with the RF orientation preference; 2) this contextual effects grows with visual flow speed, peaking at 150-250 degrees per second until matching the propagation speed of horizontal connectivity (0.15-0.25 mm/ms); 3) For this speed range, axial sensitivity of V1 cells is tilted by 90 degrees to become co-aligned with the orientation preference axis; 4) the modulation strength by the surround context correlates with the spatiotemporal coherence of the apparent motion flow. Our results suggest an internally-generated binding process, linking local (orientation /position) and global (motion/direction) features as early as V1. This long-range diffusion process constitutes a plausible substrate in V1 of the human psychophysical bias in speed estimate for collinear motion. Since demonstrated in the anesthetized cat, this novel form of contextual control of the cortical transfer function is a built-in property in V1, whose expression does not require behavioral attention and top-down control from higher cortical areas. We propose that horizontal connectivity participates to the propagation of an internal prediction wave, linking contour co-alignment and global axial motion at an apparent speed in the range of saccadic-like eye-movements.

The Effect of Sense of Movement in Audiovisual Media: A Study on Kineticism as a Formant of Expression in Globo News’ Institutional Motion Sequence Intolerância

This article analyzes the Brazilian cable television channel Globo News’ institutional motion sequence Intolerância. Israeli designer, Noma Bar, illustrated and directed Intolerância, which reveals in its discursive structures how the gaze of a Latin American country hegemonic media on the identity conflicts between West and East is aligned with Western powers. In the wake of Floch’s theoretical developments in plastic semiotics and Bergson’s postulations on the mechanism of the philosophy-centered filmmaking movement, this study aims to consider kineticism as a constitutive formant of visuality in audiovisual texts. The analyzed motion sequence is a notably exemplary object of establishing such hypothesis.

Emotion Transfer for 3D Hand and Full Body Motion Using StarGAN

In this paper, we propose a new data-driven framework for 3D hand and full-body motion emotion transfer. Specifically, we formulate the motion synthesis task as an image-to-image translation problem. By presenting a motion sequence as an image representation, the emotion can be transferred by our framework using StarGAN. To evaluate our proposed method’s effectiveness, we first conducted a user study to validate the perceived emotion from the captured and synthesized hand motions. We further evaluate the synthesized hand and full body motions qualitatively and quantitatively. Experimental results show that our synthesized motions are comparable to the captured motions and those created by an existing method in terms of naturalness and visual quality.

Personogenesis Through Imitating Human Behavior in a Humanoid Robot “Alter3”

In this study, we report the investigations conducted on the mimetic behavior of a new humanoid robot called Alter3. Alter3 autonomously imitates the motions of a person in front of it and stores the motion sequences in its memory. Alter3 also uses a self-simulator to simulate its own motions before executing them and generates a self-image. If the visual perception (of a person's motion being imitated) and the imitating self-image differ significantly, Alter3 retrieves a motion sequence closer to the target motion from its memory and executes it. We investigate how this mimetic behavior develops interacting with human, by analyzing memory dynamics and information flow between Alter3 and a interacting person. One important observation from this study is that when Alter3 fails to imitate a person's motion, the person tend to imitate Alter3 instead. This tendency is quantified by the alternation of the direction of information flow. This spontaneous role-switching behavior between a human and Alter3 is a way to initiate personality formation (i.e., personogenesis) in Alter3.

Scrambling the skin: A psychophysical study of adaptation to scrambled tactile apparent motion

An age-old hypothesis proposes that object motion across the receptor surface organizes sensory maps (Lotze, 19th century). Skin patches learn their relative positions from the order in which they are stimulated during motion events. We propose that reversing the local motion within a global motion sequence (‘motion scrambling’) provides a good test for this idea, and present results of the first experiment implementing the paradigm. We used 6-point apparent motion along the forearm. In the Scrambled sequence, two middle locations were touched in reversed order (1-2-4-3-5-6, followed by 6-5-3-4-2-1, in a continuous loop). This created a double U-turn within an otherwise constant-velocity motion, as if skin patches 3 and 4 physically swapped locations. The control condition, Orderly, proceeded at constant velocity at inter-stimulus onset interval of 120 ms. The 26.4-minute conditioning (delivered in twenty-four 66-s bouts) was interspersed with testing of perceived motion direction between the two middle tactors presented on their own (sequence 3–4 or 4–3). Our twenty participants reported motion direction. Direction discrimination was degraded following exposure to Scrambled pattern and was 0.31 d’ weaker than following Orderly conditioning (p = .007). Consistent with the proposed role of motion, this could be the beginning of re-learning of relative positions. An alternative explanation is that greater speed adaptation occurred in the Scrambled pattern, raising direction threshold. In future studies, longer conditioning should tease apart the two explanations: our re-mapping hypothesis predicts an overall reversal in perceived motion direction between critical locations (for either motion direction), whereas the speed adaptation alternative predicts chance-level performance at worst, without reversing.

High-Speed Autonomous Robotic Assembly Using In-Hand Manipulation and Re-Grasping

This paper presents an autonomous robotic assembly system for Soma cube blocks, which, after observing the individual blocks and their assembled shape, quickly plans and executes the assembly motion sequence that picks up each block and incrementally build the target shape. A multi stage planner is used to find the suitable assembly solutions, assembly sequences and grip sequences considering various constraints, and re-grasping is used when the block target pose is not directly realizable or the block pose is ambiguous. The suggested system is implemented for a commercial UR5e robotic arm and a novel two degrees of freedom (DOF) gripper capable of in-hand manipulation, which further speeds up the manipulation speed. It was experimentally validated through a public competitive demonstration, where the suggested system completed all assembly tasks reliably with outstanding performance.

Metaphors of motion and philosophies of process: A practitioner’s perspective in contemporary motion design

Contemporary motion design has become ubiquitous across all platforms of the modern media landscape, and yet even the term itself enjoys little cultural awareness and has attracted notably less scholarly attention. Like the motion graphics tradition out of which it evolved, it is an inherently hybrid practice that draws upon the histories and techniques of a broad spectrum of time-based media and, in spite of its unreservedly commercial aims, is both deeply rooted in and a concentrated distillation of experimental animation practices in particular. Drawing upon my own recent experience designing a motion sequence for a documentary feature film, this article explores the unique aesthetic qualities and metaphors of motion that characterize motion design, and ultimately seeks to define it as a distinct discipline in its own right.