Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their ...sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVis, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows users to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We show several use cases of the tool for analyzing specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis. We characterize the domain, the different stakeholders, and their goals and tasks. Long-term usage data after putting the tool online revealed great interest in the machine learning community.
This article details two approaches to compute barycenters of measures using 1-D Wasserstein distances along radial projections of the input measures. The first method makes use of the Radon ...transform of the measures, and the second is the solution of a convex optimization problem over the space of measures. We show several properties of these barycenters and explain their relationship. We show numerical approximation schemes based on a discrete Radon transform and on the resolution of a non-convex optimization problem. We explore the respective merits and drawbacks of each approach on applications to two image processing problems: color transfer and texture mixing.
Extending image processing techniques to videos is a non-trivial task; applying processing independently to each video frame often leads to temporal inconsistencies, and explicitly encoding temporal ...consistency requires algorithmic changes. We describe a more general approach to temporal consistency. We propose a gradient-domain technique that is blind to the particular image processing algorithm. Our technique takes a series of processed frames that suffers from flickering and generates a temporally-consistent video sequence. The core of our solution is to infer the temporal regularity from the original unprocessed video, and use it as a temporal consistency guide to stabilize the processed sequence. We formally characterize the frequency properties of our technique, and demonstrate, in practice, its ability to stabilize a wide range of popular image processing techniques including enhancement and stylization of color and tone, intrinsic images, and depth estimation.
This survey gives an overview of the current state of the art in GPU techniques for interactive large‐scale volume visualization. Modern techniques in this field have brought about a sea change in ...how interactive visualization and analysis of giga‐, tera‐ and petabytes of volume data can be enabled on GPUs. In addition to combining the parallel processing power of GPUs with out‐of‐core methods and data streaming, a major enabler for interactivity is making both the computational and the visualization effort proportional to the amount and resolution of data that is actually visible on screen, i.e. ‘output‐sensitive’ algorithms and system designs. This leads to recent output‐sensitive approaches that are ‘ray‐guided’, ‘visualization‐driven’ or ‘display‐aware’. In this survey, we focus on these characteristics and propose a new categorization of GPU‐based large‐scale volume visualization techniques based on the notions of actual output‐resolution visibility and the current working set of volume bricks—the current subset of data that is minimally required to produce an output image of the desired display resolution. Furthermore, we discuss the differences and similarities of different rendering and data traversal strategies in volume rendering by putting them into a common context—the notion of address translation. For our purposes here, we view parallel (distributed) visualization using clusters as an orthogonal set of techniques that we do not discuss in detail but that can be used in conjunction with what we present in this survey.
This survey gives an overview of the current state of the art in GPU techniques for interactive large‐scale volume visualization. Modern techniques in this field have brought about a sea change in how interactive visualization and analysis of giga‐, tera‐ and petabytes of volume data can be enabled on GPUs. In addition to combining the parallel processing power of GPUs with out‐of‐core methods and data streaming, a major enabler for interactivity is making both the computational and the visualization effort proportional to the amount and resolution of data that is actually visible on screen, i.e. ‘output‐sensitive’ algorithms and system designs. This leads to recent output‐sensitive approaches that are ‘ray‐guided’, ‘visualization‐driven or ‘display‐aware’. In this survey, we focus on these characteristics and propose a new categorization of GPU‐based large‐scale volume visualization techniques based on the notions of actual output‐resolution visibility and the current working set of volume bricks—the current subset of data that is minimally required to produce an output image of the desired display resolution.
We present HiGlass, an open source visualization tool built on web technologies that provides a rich interface for rapid, multiplex, and multiscale navigation of 2D genomic maps alongside 1D genomic ...tracks, allowing users to combine various data types, synchronize multiple visualization modalities, and share fully customizable views with others. We demonstrate its utility in exploring different experimental conditions, comparing the results of analyses, and creating interactive snapshots to share with collaborators and the broader public. HiGlass is accessible online at http://higlass.io and is also available as a containerized application that can be run on any platform.
We introduce MedMNIST v2, a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into a small ...size of 28 × 28 (2D) or 28 × 28 × 28 (3D) with the corresponding classification labels so that no background knowledge is required for users. Covering primary data modalities in biomedical images, MedMNIST v2 is designed to perform classification on lightweight 2D and 3D images with various dataset scales (from 100 to 100,000) and diverse tasks (binary/multi-class, ordinal regression, and multi-label). The resulting dataset, consisting of 708,069 2D images and 9,998 3D images in total, could support numerous research/educational purposes in biomedical image analysis, computer vision, and machine learning. We benchmark several baseline methods on MedMNIST v2, including 2D/3D neural networks and open-source/commercial AutoML tools. The data and code are publicly available at https://medmnist.com/ .
Interactive intrinsic video editing Bonneel, Nicolas; Sunkavalli, Kalyan; Tompkin, James ...
ACM transactions on graphics,
11/2014, Letnik:
33, Številka:
6
Journal Article
Recenzirano
Odprti dostop
Separating a photograph into its reflectance and illumination intrinsic images is a fundamentally ambiguous problem, and state-of-the-art algorithms combine sophisticated reflectance and illumination ...priors with user annotations to create plausible results. However, these algorithms cannot be easily extended to videos for two reasons: first, näively applying algorithms designed for single images to videos produce results that are temporally incoherent; second, effectively specifying user annotations for a video requires interactive feedback, and current approaches are orders of magnitudes too slow to support this. We introduce a fast and temporally consistent algorithm to decompose video sequences into their reflectance and illumination components. Our algorithm uses a hybrid
ℓ
2
ℓ
p
formulation that separates image gradients into smooth illumination and sparse reflectance gradients using look-up tables. We use a multi-scale parallelized solver to reconstruct the reflectance and illumination from these gradients while enforcing spatial and temporal reflectance constraints and user annotations. We demonstrate that our algorithm automatically produces reasonable results, that can be interactively refined by users, at rates that are two orders of magnitude faster than existing tools, to produce high-quality decompositions for challenging real-world video sequences. We also show how these decompositions can be used for a number of video editing applications including recoloring, retexturing, illumination editing, and lighting-aware compositing.
Example-based video color grading Bonneel, Nicolas; Sunkavalli, Kalyan; Paris, Sylvain ...
ACM transactions on graphics,
07/2013, Letnik:
32, Številka:
4
Journal Article
Recenzirano
Odprti dostop
In most professional cinema productions, the color palette of the movie is painstakingly adjusted by a team of skilled colorists -- through a process referred to as
color grading
-- to achieve a ...certain visual look. The time and expertise required to grade a video makes it difficult for amateurs to manipulate the colors of their own video clips. In this work, we present a method that allows a user to transfer the color palette of a model video clip to their own video sequence. We estimate a per-frame color transform that maps the color distributions in the input video sequence to that of the model video clip. Applying this transformation naively leads to artifacts such as bleeding and flickering. Instead, we propose a novel differential-geometry-based scheme that interpolates these transformations in a manner that minimizes their curvature, similarly to curvature flows. In addition, we automatically determine a set of keyframes that best represent this interpolated transformation curve, and can be used subsequently, to manually refine the color grade. We show how our method can successfully transfer color palettes between videos for a range of visual styles and a number of input video clips.
Network visualizations are commonly used to analyze relationships in various contexts, such as social, biological, and geographical interactions. To efficiently explore a network visualization, the ...user needs to quickly navigate to different parts of the network and analyze local details. Recent advancements in display and interaction technologies inspire new visions for improved visualization and interaction design. Past research into network design has identified some key benefits to visualizing networks in 3D versus 2D. However, little work has been done to study the impact of varying levels of embodied interaction on network analysis. We present a controlled user study that compared four network visualization environments featuring conditions and hardware that leveraged different amounts of embodiment and visual perception ranging from a 2D visualization desktop environment with a standard mouse to a 3D visualization virtual reality environment. We measured the accuracy, speed, perceived workload, and preferences of 20 participants as they completed three network analytic tasks, each of which required unique navigation and substantial effort to complete. For the task that required participants to iterate over the entire visualization rather than focus on a specific area, we found that participants were more accurate using a VR HMD and a trackball mouse than conventional desktop settings. From a workload perspective, VR was generally considered the least mentally demanding and least frustrating to use in two of our three tasks. It was also preferred and ranked as the most effective and visually appealing condition overall. However, using VR to compare two side-by-side networks was difficult, and it was similar to or slower than other conditions in two of the three tasks. Overall, the accuracy and workload advantages of conditions with greater embodiment in specific tasks suggest promising opportunities to create more effective environments in which to analyze network visualizations.