Paper Group ANR 353
A Stronger Foundation for Computer Science and P=NP. IMU2Face: Real-time Gesture-driven Facial Reenactment. A Deep Recurrent Framework for Cleaning Motion Capture Data. Enabling Embodied Analogies in Intelligent Music Systems. Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs. Metrics for Deep Generative Models. C …
A Stronger Foundation for Computer Science and P=NP
| Title | A Stronger Foundation for Computer Science and P=NP |
| Authors | Mark Inman |
| Abstract | This article describes a Turing machine which can solve for $\beta^{'}$ which is RE-complete. RE-complete problems are proven to be undecidable by Turing’s accepted proof on the Entscheidungsproblem. Thus, constructing a machine which decides over $\beta^{'}$ implies inconsistency in ZFC. We then discover that unrestricted use of the axiom of substitution can lead to hidden assumptions in a certain class of proofs by contradiction. These hidden assumptions create an implied axiom of incompleteness for ZFC. Later, we offer a restriction on the axiom of substitution by introducing a new axiom which prevents impredicative tautologies from producing theorems. Our discovery in regards to these foundational arguments, disproves the SPACE hierarchy theorem which allows us to solve the P vs NP problem using a TIME-SPACE equivalence oracle. |
| Tasks | |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05714v2 |
| http://arxiv.org/pdf/1708.05714v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-stronger-foundation-for-computer-science |
| Repo | |
| Framework | |
IMU2Face: Real-time Gesture-driven Facial Reenactment
| Title | IMU2Face: Real-time Gesture-driven Facial Reenactment |
| Authors | Justus Thies, Michael Zollhöfer, Matthias Nießner |
| Abstract | We present IMU2Face, a gesture-driven facial reenactment system. To this end, we combine recent advances in facial motion capture and inertial measurement units (IMUs) to control the facial expressions of a person in a target video based on intuitive hand gestures. IMUs are omnipresent, since modern smart-phones, smart-watches and drones integrate such sensors, e.g., for changing the orientation of the screen content, counting steps, or for flight stabilization. Face tracking and reenactment is based on the state-of-the-art real-time Face2Face facial reenactment system. Instead of transferring facial expressions from a source to a target actor, we employ an IMU to track the hand gestures of a source actor and use its orientation to modify the target actor’s expressions. |
| Tasks | Motion Capture |
| Published | 2017-12-18 |
| URL | http://arxiv.org/abs/1801.01446v1 |
| http://arxiv.org/pdf/1801.01446v1.pdf | |
| PWC | https://paperswithcode.com/paper/imu2face-real-time-gesture-driven-facial |
| Repo | |
| Framework | |
A Deep Recurrent Framework for Cleaning Motion Capture Data
| Title | A Deep Recurrent Framework for Cleaning Motion Capture Data |
| Authors | Utkarsh Mall, G. Roshan Lal, Siddhartha Chaudhuri, Parag Chaudhuri |
| Abstract | We present a deep, bidirectional, recurrent framework for cleaning noisy and incomplete motion capture data. It exploits temporal coherence and joint correlations to infer adaptive filters for each joint in each frame. A single model can be trained to denoise a heterogeneous mix of action types, under substantial amounts of noise. A signal that has both noise and gaps is preprocessed with a second bidirectional network that synthesizes missing frames from surrounding context. The approach handles a wide variety of noise types and long gaps, does not rely on knowledge of the noise distribution, and operates in a streaming setting. We validate our approach through extensive evaluations on noise both in joint angles and in joint positions, and show that it improves upon various alternatives. |
| Tasks | Motion Capture |
| Published | 2017-12-09 |
| URL | http://arxiv.org/abs/1712.03380v1 |
| http://arxiv.org/pdf/1712.03380v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-recurrent-framework-for-cleaning |
| Repo | |
| Framework | |
Enabling Embodied Analogies in Intelligent Music Systems
| Title | Enabling Embodied Analogies in Intelligent Music Systems |
| Authors | Fabio Paolizzo |
| Abstract | The present methodology is aimed at cross-modal machine learning and uses multidisciplinary tools and methods drawn from a broad range of areas and disciplines, including music, systematic musicology, dance, motion capture, human-computer interaction, computational linguistics and audio signal processing. Main tasks include: (1) adapting wisdom-of-the-crowd approaches to embodiment in music and dance performance to create a dataset of music and music lyrics that covers a variety of emotions, (2) applying audio/language-informed machine learning techniques to that dataset to identify automatically the emotional content of the music and the lyrics, and (3) integrating motion capture data from a Vicon system and dancers performing on that music. |
| Tasks | Motion Capture |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.00334v1 |
| http://arxiv.org/pdf/1712.00334v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-embodied-analogies-in-intelligent |
| Repo | |
| Framework | |
Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs
| Title | Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs |
| Authors | Thanuja Dharmasiri, Andrew Spek, Tom Drummond |
| Abstract | Understanding the 3D structure of a scene is of vital importance, when it comes to developing fully autonomous robots. To this end, we present a novel deep learning based framework that estimates depth, surface normals and surface curvature by only using a single RGB image. To the best of our knowledge this is the first work to estimate surface curvature from colour using a machine learning approach. Additionally, we demonstrate that by tuning the network to infer well designed features, such as surface curvature, we can achieve improved performance at estimating depth and normals.This indicates that network guidance is still a useful aspect of designing and training a neural network. We run extensive experiments where the network is trained to infer different tasks while the model capacity is kept constant resulting in different feature maps based on the tasks at hand. We outperform the previous state-of-the-art benchmarks which jointly estimate depths and surface normals while predicting surface curvature in parallel. |
| Tasks | |
| Published | 2017-06-23 |
| URL | http://arxiv.org/abs/1706.07593v1 |
| http://arxiv.org/pdf/1706.07593v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-prediction-of-depths-normals-and |
| Repo | |
| Framework | |
Metrics for Deep Generative Models
| Title | Metrics for Deep Generative Models |
| Authors | Nutan Chen, Alexej Klushyn, Richard Kurle, Xueyan Jiang, Justin Bayer, Patrick van der Smagt |
| Abstract | Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source—the latent space—to samples from a more complex distribution represented by a dataset. While the manifold hypothesis implies that the density induced by a dataset contains large regions of low density, the training criterions of VAEs and GANs will make the latent space densely covered. Consequently points that are separated by low-density regions in observation space will be pushed together in latent space, making stationary distances poor proxies for similarity. We transfer ideas from Riemannian geometry to this setting, letting the distance between two points be the shortest path on a Riemannian manifold induced by the transformation. The method yields a principled distance measure, provides a tool for visual inspection of deep generative models, and an alternative to linear interpolation in latent space. In addition, it can be applied for robot movement generalization using previously learned skills. The method is evaluated on a synthetic dataset with known ground truth; on a simulated robot arm dataset; on human motion capture data; and on a generative model of handwritten digits. |
| Tasks | Motion Capture |
| Published | 2017-11-03 |
| URL | http://arxiv.org/abs/1711.01204v2 |
| http://arxiv.org/pdf/1711.01204v2.pdf | |
| PWC | https://paperswithcode.com/paper/metrics-for-deep-generative-models |
| Repo | |
| Framework | |
CAMREP- Concordia Action and Motion Repository
| Title | CAMREP- Concordia Action and Motion Repository |
| Authors | Kaustubha Mendhurwar, Qing Gu, Vladimir de la Cruz, Sudhir Mudur, Tiberiu Popa |
| Abstract | Action recognition, motion classification, gait analysis and synthesis are fundamental problems in a number of fields such as computer graphics, bio-mechanics and human computer interaction that generate a large body of research. This type of data is complex because it is inherently multidimensional and has multiple modalities such as video, motion capture data, accelerometer data, etc. While some of this data, such as monocular video are easy to acquire, others are much more difficult and expensive such as motion capture data or multi-view video. This creates a large barrier of entry in the research community for data driven research. We have embarked on creating a new large repository of motion and action data (CAMREP) consisting of several motion and action databases. What makes this database unique is that we use a variety of modalities, enabling multi-modal analysis. Presently, the size of datasets varies with some having a large number of subjects while others having smaller numbers. We have also acquired long capture sequences in a number of cases, making some datasets rather large. |
| Tasks | Motion Capture, Temporal Action Localization |
| Published | 2017-10-06 |
| URL | http://arxiv.org/abs/1710.02566v1 |
| http://arxiv.org/pdf/1710.02566v1.pdf | |
| PWC | https://paperswithcode.com/paper/camrep-concordia-action-and-motion-repository |
| Repo | |
| Framework | |
A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment
| Title | A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment |
| Authors | Akshay Rangesh, Kevan Yuen, Ravi Kumar Satzoda, Rakesh Nattoji Rajaram, Pujitha Gunaratne, Mohan M. Trivedi |
| Abstract | Recent progress in autonomous and semi-autonomous driving has been made possible in part through an assortment of sensors that provide the intelligent agent with an enhanced perception of its surroundings. It has been clear for quite some while now that for intelligent vehicles to function effectively in all situations and conditions, a fusion of different sensor technologies is essential. Consequently, the availability of synchronized multi-sensory data streams are necessary to promote the development of fusion based algorithms for low, mid and high level semantic tasks. In this paper, we provide a comprehensive description of LISA-A: our heavily sensorized, full-surround testbed capable of providing high quality data from a slew of synchronized and calibrated sensors such as cameras, LIDARs, radars, and the IMU/GPS. The vehicle has recorded over 100 hours of real world data for a very diverse set of weather, traffic and daylight conditions. All captured data is accurately calibrated and synchronized using timestamps, and stored safely in high performance servers mounted inside the vehicle itself. Details on the testbed instrumentation, sensor layout, sensor outputs, calibration and synchronization are described in this paper. |
| Tasks | Autonomous Driving, Calibration |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07502v4 |
| http://arxiv.org/pdf/1709.07502v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-multimodal-full-surround-vehicular-testbed |
| Repo | |
| Framework | |
Regularities and Irregularities in Order Flow Data
| Title | Regularities and Irregularities in Order Flow Data |
| Authors | Martin Theissen, Sebastian M. Krause, Thomas Guhr |
| Abstract | We identify and analyze statistical regularities and irregularities in the recent order flow of different NASDAQ stocks, focusing on the positions where orders are placed in the orderbook. This includes limit orders being placed outside of the spread, inside the spread and (effective) market orders. We find that limit order placement inside the spread is strongly determined by the dynamics of the spread size. Most orders, however, arrive outside of the spread. While for some stocks order placement on or next to the quotes is dominating, deeper price levels are more important for other stocks. As market orders are usually adjusted to the quote volume, the impact of market orders depends on the orderbook structure, which we find to be quite diverse among the analyzed stocks as a result of the way limit order placement takes place. |
| Tasks | |
| Published | 2017-02-14 |
| URL | http://arxiv.org/abs/1702.04289v1 |
| http://arxiv.org/pdf/1702.04289v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularities-and-irregularities-in-order-flow |
| Repo | |
| Framework | |
An Automated Auto-encoder Correlation-based Health-Monitoring and Prognostic Method for Machine Bearings
| Title | An Automated Auto-encoder Correlation-based Health-Monitoring and Prognostic Method for Machine Bearings |
| Authors | Ramin M. Hasani, Guodong Wang, Radu Grosu |
| Abstract | This paper studies an intelligent ultimate technique for health-monitoring and prognostic of common rotary machine components, particularly bearings. During a run-to-failure experiment, rich unsupervised features from vibration sensory data are extracted by a trained sparse auto-encoder. Then, the correlation of the extracted attributes of the initial samples (presumably healthy at the beginning of the test) with the succeeding samples is calculated and passed through a moving-average filter. The normalized output is named auto-encoder correlation-based (AEC) rate which stands for an informative attribute of the system depicting its health status and precisely identifying the degradation starting point. We show that AEC technique well-generalizes in several run-to-failure tests. AEC collects rich unsupervised features form the vibration data fully autonomous. We demonstrate the superiority of the AEC over many other state-of-the-art approaches for the health monitoring and prognostic of machine bearings. |
| Tasks | |
| Published | 2017-03-18 |
| URL | http://arxiv.org/abs/1703.06272v1 |
| http://arxiv.org/pdf/1703.06272v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automated-auto-encoder-correlation-based |
| Repo | |
| Framework | |
Boosting the Actor with Dual Critic
| Title | Boosting the Actor with Dual Critic |
| Authors | Bo Dai, Albert Shaw, Niao He, Lihong Li, Le Song |
| Abstract | This paper proposes a new actor-critic-style algorithm called Dual Actor-Critic or Dual-AC. It is derived in a principled way from the Lagrangian dual form of the Bellman optimality equation, which can be viewed as a two-player game between the actor and a critic-like function, which is named as dual critic. Compared to its actor-critic relatives, Dual-AC has the desired property that the actor and dual critic are updated cooperatively to optimize the same objective function, providing a more transparent way for learning the critic that is directly related to the objective function of the actor. We then provide a concrete algorithm that can effectively solve the minimax optimization problem, using techniques of multi-step bootstrapping, path regularization, and stochastic dual ascent algorithm. We demonstrate that the proposed algorithm achieves the state-of-the-art performances across several benchmarks. |
| Tasks | |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1712.10282v1 |
| http://arxiv.org/pdf/1712.10282v1.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-the-actor-with-dual-critic |
| Repo | |
| Framework | |
Sequences, Items And Latent Links: Recommendation With Consumed Item Packs
| Title | Sequences, Items And Latent Links: Recommendation With Consumed Item Packs |
| Authors | Rachid Guerraoui, Erwan Le Merrer, Rhicheek Patra, Jean-Ronan Vigouroux |
| Abstract | Recommenders personalize the web content by typically using collaborative filtering to relate users (or items) based on explicit feedback, e.g., ratings. The difficulty of collecting this feedback has recently motivated to consider implicit feedback (e.g., item consumption along with the corresponding time). In this paper, we introduce the notion of consumed item pack (CIP) which enables to link users (or items) based on their implicit analogous consumption behavior. Our proposal is generic, and we show that it captures three novel implicit recommenders: a user-based (CIP-U), an item-based (CIP-I), and a word embedding-based (DEEPCIP), as well as a state-of-the-art technique using implicit feedback (FISM). We show that our recommenders handle incremental updates incorporating freshly consumed items. We demonstrate that all three recommenders provide a recommendation quality that is competitive with state-of-the-art ones, including one incorporating both explicit and implicit feedback. |
| Tasks | |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.06100v2 |
| http://arxiv.org/pdf/1711.06100v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequences-items-and-latent-links |
| Repo | |
| Framework | |
Visualizing and Exploring Dynamic High-Dimensional Datasets with LION-tSNE
| Title | Visualizing and Exploring Dynamic High-Dimensional Datasets with LION-tSNE |
| Authors | Andrey Boytsov, Francois Fouquet, Thomas Hartmann, Yves LeTraon |
| Abstract | T-distributed stochastic neighbor embedding (tSNE) is a popular and prize-winning approach for dimensionality reduction and visualizing high-dimensional data. However, tSNE is non-parametric: once visualization is built, tSNE is not designed to incorporate additional data into existing representation. It highly limits the applicability of tSNE to the scenarios where data are added or updated over time (like dashboards or series of data snapshots). In this paper we propose, analyze and evaluate LION-tSNE (Local Interpolation with Outlier coNtrol) - a novel approach for incorporating new data into tSNE representation. LION-tSNE is based on local interpolation in the vicinity of training data, outlier detection and a special outlier mapping algorithm. We show that LION-tSNE method is robust both to outliers and to new samples from existing clusters. We also discuss multiple possible improvements for special cases. We compare LION-tSNE to a comprehensive list of possible benchmark approaches that include multiple interpolation techniques, gradient descent for new data, and neural network approximation. |
| Tasks | Dimensionality Reduction, Outlier Detection |
| Published | 2017-08-16 |
| URL | http://arxiv.org/abs/1708.04983v1 |
| http://arxiv.org/pdf/1708.04983v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualizing-and-exploring-dynamic-high |
| Repo | |
| Framework | |
L1-norm Kernel PCA
| Title | L1-norm Kernel PCA |
| Authors | Cheolmin Kim, Diego Klabjan |
| Abstract | We present the first model and algorithm for L1-norm kernel PCA. While L2-norm kernel PCA has been widely studied, there has been no work on L1-norm kernel PCA. For this non-convex and non-smooth problem, we offer geometric understandings through reformulations and present an efficient algorithm where the kernel trick is applicable. To attest the efficiency of the algorithm, we provide a convergence analysis including linear rate of convergence. Moreover, we prove that the output of our algorithm is a local optimal solution to the L1-norm kernel PCA problem. We also numerically show its robustness when extracting principal components in the presence of influential outliers, as well as its runtime comparability to L2-norm kernel PCA. Lastly, we introduce its application to outlier detection and show that the L1-norm kernel PCA based model outperforms especially for high dimensional data. |
| Tasks | Outlier Detection |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.10152v1 |
| http://arxiv.org/pdf/1709.10152v1.pdf | |
| PWC | https://paperswithcode.com/paper/l1-norm-kernel-pca |
| Repo | |
| Framework | |
LVreID: Person Re-Identification with Long Sequence Videos
| Title | LVreID: Person Re-Identification with Long Sequence Videos |
| Authors | Jianing Li, Shiliang Zhang, Jingdong Wang, Wen Gao, Qi Tian |
| Abstract | This paper mainly establishes a large-scale Long sequence Video database for person re-IDentification (LVreID). |
| Tasks | Person Re-Identification |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07286v4 |
| http://arxiv.org/pdf/1712.07286v4.pdf | |
| PWC | https://paperswithcode.com/paper/lvreid-person-re-identification-with-long |
| Repo | |
| Framework | |
