Paper Group ANR 1207
Interactive Classification by Asking Informative Questions. SpatialFlow: Bridging All Tasks for Panoptic Segmentation. A Software to Detect OCC Emotion, Big-Five Personality and Hofstede Cultural Dimensions of Pedestrians from Video Sequences. The surprising little effectiveness of cooperative algorithms in parallel problem solving. Understanding C …
Interactive Classification by Asking Informative Questions
| Title | Interactive Classification by Asking Informative Questions |
| Authors | Lili Yu, Howard Chen, Sida Wang, Yoav Artzi, Tao Lei |
| Abstract | Natural language systems often rely on a single, potentially ambiguous input to make one final prediction, which may simplify the problem but degrade end user experience. Instead of making predictions with the natural language query only, we ask the user for additional information using a small number of binary and multiple-choice questions in order to better help users accomplish their goals while minimizing their effort. At each turn, our system decides between asking the most informative question or making the final classification prediction. Our approach enables bootstrapping the system using simple crowdsourcing annotations without expensive human-to-human interaction data. Evaluation demonstrates that our method substantially increases classification accuracy, while effectively balancing the number of questions with the improvement to final accuracy. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03598v1 |
| https://arxiv.org/pdf/1911.03598v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-classification-by-asking-1 |
| Repo | |
| Framework | |
SpatialFlow: Bridging All Tasks for Panoptic Segmentation
| Title | SpatialFlow: Bridging All Tasks for Panoptic Segmentation |
| Authors | Qiang Chen, Anda Cheng, Xiangyu He, Peisong Wang, Jian Cheng |
| Abstract | Object location is fundamental to panoptic segmentation as it is related to all things and stuff. How to integrate object location in both thing and stuff segmentation is a crucial problem. In this paper, we propose object spatial information flows to achieve this objective. More importantly, we design four parallel sub-networks for sub-tasks in panoptic segmentation, which leads to the preferable adaptation of object spatial information. With sub-networks, the flows can bridge all tasks together by delivering the object’s spatial context from the box regression task to others. They can also provide clues for segmenting both things and stuff, which helps the network better understand the whole image. Upon the sub-networks and the flows, we present a location-aware and unified framework for panoptic segmentation, denoted as SpatialFlow. We perform a detailed ablation study on each component and conduct extensive experiments to prove the effectiveness of Our SpatialFlow. Furthermore, we achieve state-of-the-art results, which are $47.3$ PQ and $62.5$ PQ respectively on MS-COCO and Cityscapes panoptic benchmarks. |
| Tasks | Instance Segmentation, Object Detection, Panoptic Segmentation, Semantic Segmentation |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08787v2 |
| https://arxiv.org/pdf/1910.08787v2.pdf | |
| PWC | https://paperswithcode.com/paper/spatialflow-bridging-all-tasks-for-panoptic |
| Repo | |
| Framework | |
A Software to Detect OCC Emotion, Big-Five Personality and Hofstede Cultural Dimensions of Pedestrians from Video Sequences
| Title | A Software to Detect OCC Emotion, Big-Five Personality and Hofstede Cultural Dimensions of Pedestrians from Video Sequences |
| Authors | Rodolfo Migon Favaretto, Victor Araujo, Soraia Raupp Musse, Felipe Vilanova, Angelo Brandelli Costa |
| Abstract | This paper presents a video analysis application to detect personality, emotion and cultural aspects from pedestrians in video sequences, along with a visualizer of features. The proposed model considers a series of characteristics of the pedestrians and the crowd, such as number and size of groups, distances, speeds, among others, and performs the mapping of these characteristics in personalities, emotions and cultural aspects, considering the Cultural Dimensions of Hofstede (HCD), the Big-Five Personality Model (OCEAN) and the OCC Emotional Model. The main hypothesis is that there is a relationship between so-called intrinsic human variables (such as emotion) and the way people behave in space and time. The software was tested in a set of videos from different countries and results seem promising in order to identify these three different levels of psychological traits in the filmed sequences. In addition, the data of the people present in the videos can be seen in a crowd viewer. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06484v1 |
| https://arxiv.org/pdf/1908.06484v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-software-to-detect-occ-emotion-big-five |
| Repo | |
| Framework | |
The surprising little effectiveness of cooperative algorithms in parallel problem solving
| Title | The surprising little effectiveness of cooperative algorithms in parallel problem solving |
| Authors | Sandro M. Reia, Larissa F. Aquino, José F. Fontanari |
| Abstract | Biological and cultural inspired optimization algorithms are nowadays part of the basic toolkit of a great many research domains. By mimicking processes in nature and animal societies, these general-purpose search algorithms promise to deliver optimal or near-optimal solutions using hardly any information on the optimization problems they are set to tackle. Here we study the performances of a cultural-inspired algorithm – the imitative learning search – as well as of asexual and sexual variants of evolutionary algorithms in finding the global maxima of NK-fitness landscapes. The main performance measure is the total number of agent updates required by the algorithms to find those global maxima and the baseline performance, which establishes the worth of the cooperative algorithms, is set by the blind search in which the agents explore the problem space (binary strings) by flipping randomly chosen bits. We find that even for smooth landscapes that exhibit a single maximum, the evolutionary algorithms do not perform much better than the blind search due to the stochastic effects of the genetic roulette. The imitative learning is immune to this effect thanks to the deterministic choice of the fittest string in the population, which is used as a model for imitation. The tradeoff is that it is more prone to be trapped in local maxima than the evolutionary algorithms in the case of mildly rugged landscapes. In fact, in the case of rugged landscapes with a not too low density of local maxima, the blind search beats the cooperative algorithms regardless of whether the task is to find the global maximum or to find the fittest state within a given runtime. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03347v1 |
| https://arxiv.org/pdf/1912.03347v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-surprising-little-effectiveness-of |
| Repo | |
| Framework | |
Understanding Cyber Athletes Behaviour Through a Smart Chair: CS:GO and Monolith Team Scenario
| Title | Understanding Cyber Athletes Behaviour Through a Smart Chair: CS:GO and Monolith Team Scenario |
| Authors | Anton Smerdov, Anastasia Kiskun, Rostislav Shaniiazov, Andrey Somov, Evgeny Burnaev |
| Abstract | eSports is the rapidly developing multidisciplinary domain. However, research and experimentation in eSports are in the infancy. In this work, we propose a smart chair platform - an unobtrusive approach to the collection of data on the eSports athletes and data further processing with machine learning methods. The use case scenario involves three groups of players: `cyber athletes’ (Monolith team), semi-professional players and newbies all playing CS:GO discipline. In particular, we collect data from the accelerometer and gyroscope integrated in the chair and apply machine learning algorithms for the data analysis. Our results demonstrate that the professional athletes can be identified by their behaviour on the chair while playing the game. | |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06407v1 |
| https://arxiv.org/pdf/1908.06407v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-cyber-athletes-behaviour |
| Repo | |
| Framework | |
A Mask-RCNN Baseline for Probabilistic Object Detection
| Title | A Mask-RCNN Baseline for Probabilistic Object Detection |
| Authors | Phil Ammirato, Alexander C. Berg |
| Abstract | The Probabilistic Object Detection Challenge evaluates object detection methods using a new evaluation measure, Probability-based Detection Quality (PDQ), on a new synthetic image dataset. We present our submission to the challenge, a fine-tuned version of Mask-RCNN with some additional post-processing. Our method, submitted under username pammirato, is currently second on the leaderboard with a score of 21.432, while also achieving the highest spatial quality and average overall quality of detections. We hope this method can provide some insight into how detectors designed for mean average precision (mAP) evaluation behave under PDQ, as well as a strong baseline for future work. |
| Tasks | Object Detection |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03621v2 |
| https://arxiv.org/pdf/1908.03621v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-mask-rcnn-baseline-for-probabilistic-object |
| Repo | |
| Framework | |
Conversational Emotion Analysis via Attention Mechanisms
| Title | Conversational Emotion Analysis via Attention Mechanisms |
| Authors | Zheng Lian, Jianhua Tao, Bin Liu, Jian Huang |
| Abstract | Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the fusion of the acoustic and lexical features. Then these fusion representations are fed into the self-attention based bi-directional gated recurrent unit (GRU) layer to capture long-term contextual information. To imitate real interaction patterns of different speakers, speaker embeddings are also utilized as additional inputs to distinguish the speaker identities during conversational dialogs. To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that our method shows absolute 2.42% performance improvement over the state-of-the-art strategies. |
| Tasks | Emotion Recognition |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11263v1 |
| https://arxiv.org/pdf/1910.11263v1.pdf | |
| PWC | https://paperswithcode.com/paper/conversational-emotion-analysis-via-attention |
| Repo | |
| Framework | |
Belief and plausibility measures for D numbers
| Title | Belief and plausibility measures for D numbers |
| Authors | Xinyang Deng |
| Abstract | As a generalization of Dempster-Shafer theory, D number theory provides a framework to deal with uncertain information with non-exclusiveness and incompleteness. However, some basic concepts in D number theory are not well defined. In this note, the belief and plausibility measures for D numbers have been proposed, and basic properties of these measures have been revealed as well. |
| Tasks | |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.00109v1 |
| https://arxiv.org/pdf/1912.00109v1.pdf | |
| PWC | https://paperswithcode.com/paper/belief-and-plausibility-measures-for-d |
| Repo | |
| Framework | |
Digitally Capturing Physical Prototypes During Early-Stage Engineering Design Projects for Initial Analysis of Project Output and Progression
| Title | Digitally Capturing Physical Prototypes During Early-Stage Engineering Design Projects for Initial Analysis of Project Output and Progression |
| Authors | Jorgen F. Erichsen, Heikki Sjöman, Martin Steinert, Torgeir Welo |
| Abstract | Aiming to help researchers capture output from the early stages of engineering design projects, this article presents a new research tool for digitally capturing physical prototypes. The motivation for this work is to collect observations that can aid in understanding prototyping in the early stages of engineering design projects, and this article investigates if and how digital capture of physical prototypes can be used for this purpose. Early-stage prototypes are usually rough and of low-fidelity and are thus often discarded or substantially modified through the projects. Hence, retrospective access to prototypes is a challenge when trying to gather accurate empirical data. To capture the prototypes developed through the early stages of a project, a new research tool has been developed for capturing prototypes through multi-view images, along with metadata describing by whom, why, when and where the prototypes were captured. Over the course of 17 months, this research tool has been used to capture more than 800 physical prototypes from 76 individual users across many projects. In this article, one project is shown in detail to demonstrate how this capturing system can gather empirical data for enriching engineering design project cases that focus on prototyping for concept generation. The authors also analyse the metadata provided by the system to give understanding into prototyping patterns in the projects. Lastly, through enabling digital capture of large quantities of data, the research tool presents the foundations for training artificial intelligence-based predictors and classifiers that can be used for analysis in engineering design research. |
| Tasks | |
| Published | 2019-04-26 |
| URL | https://arxiv.org/abs/1905.01950v2 |
| https://arxiv.org/pdf/1905.01950v2.pdf | |
| PWC | https://paperswithcode.com/paper/190501950 |
| Repo | |
| Framework | |
Orthogonal Gradient Descent for Continual Learning
| Title | Orthogonal Gradient Descent for Continual Learning |
| Authors | Mehrdad Farajtabar, Navid Azizan, Alex Mott, Ang Li |
| Abstract | Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks suffer from the problem of catastrophic forgetting; they forget how to solve previous tasks after being trained on a new task, despite having the essential capacity to solve both tasks if they were trained on both simultaneously. In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of the gradient updates to avoid forgetting previously-learned data. We present the Orthogonal Gradient Descent (OGD) method, which accomplishes this goal by projecting the gradients from new tasks onto a subspace in which the neural network output on previous task does not change and the projected gradient is still in a useful direction for learning the new task. Our approach utilizes the high capacity of a neural network more efficiently and does not require storing the previously learned data that might raise privacy concerns. Experiments on common benchmarks reveal the effectiveness of the proposed OGD method. |
| Tasks | Continual Learning |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.07104v1 |
| https://arxiv.org/pdf/1910.07104v1.pdf | |
| PWC | https://paperswithcode.com/paper/orthogonal-gradient-descent-for-continual |
| Repo | |
| Framework | |
Saliency Maps Generation for Automatic Text Summarization
| Title | Saliency Maps Generation for Automatic Text Summarization |
| Authors | David Tuckey, Krysia Broda, Alessandra Russo |
| Abstract | Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications. Our goal is to question the limits of these approaches on more complex tasks. In this paper we apply Layer-Wise Relevance Propagation (LRP) to a sequence-to-sequence attention model trained on a text summarization dataset. We obtain unexpected saliency maps and discuss the rightfulness of these “explanations”. We argue that we need a quantitative way of testing the counterfactual case to judge the truthfulness of the saliency maps. We suggest a protocol to check the validity of the importance attributed to the input and show that the saliency maps obtained sometimes capture the real use of the input features by the network, and sometimes do not. We use this example to discuss how careful we need to be when accepting them as explanation. |
| Tasks | Text Summarization |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05664v1 |
| https://arxiv.org/pdf/1907.05664v1.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-maps-generation-for-automatic-text |
| Repo | |
| Framework | |
A Spatial-temporal 3D Human Pose Reconstruction Framework
| Title | A Spatial-temporal 3D Human Pose Reconstruction Framework |
| Authors | X. T. Nguyen, T. D. Ngo, T. H. Le |
| Abstract | 3D human pose reconstruction from single-view camera is a difficult and challenging topic. Many approaches have been proposed, but almost focusing on frame-by-frame independently while inter-frames are highly correlated in a pose sequence. In contrast, we introduce a novel spatial-temporal 3D reconstruction framework that leverages both intra and inter frame relationships in consecutive 2D pose sequences. Orthogonal Matching Pursuit (OMP) algorithm, pre-trained Pose-angle Limits and Temporal Models have been implemented. We quantitatively compare our framework versus recent works on CMU motion capture dataset and Vietnamese traditional dance sequences. Our method outperforms others with 10 percent lower of Euclidean reconstruction error and robustness against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are smoother and more natural than others. |
| Tasks | 3D Reconstruction, Motion Capture |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02529v2 |
| http://arxiv.org/pdf/1901.02529v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-spatial-temporal-3d-human-pose |
| Repo | |
| Framework | |
Towards a Theory of Intentions for Human-Robot Collaboration
| Title | Towards a Theory of Intentions for Human-Robot Collaboration |
| Authors | Rocio Gomez, Mohan Sridharan, Heather Riley |
| Abstract | The architecture described in this paper encodes a theory of intentions based on the the key principles of non-procrastination, persistence, and automatically limiting reasoning to relevant knowledge and observations. The architecture reasons with transition diagrams of any given domain at two different resolutions, with the fine-resolution description defined as a refinement of, and hence tightly-coupled to, a coarse-resolution description. Non-monotonic logical reasoning with the coarse-resolution description computes an activity (i.e., plan) comprising abstract actions for any given goal. Each abstract action is implemented as a sequence of concrete actions by automatically zooming to and reasoning with the part of the fine-resolution transition diagram relevant to the current coarse-resolution transition and the goal. Each concrete action in this sequence is executed using probabilistic models of the uncertainty in sensing and actuation, and the corresponding fine-resolution outcomes are used to infer coarse-resolution observations that are added to the coarse-resolution history. The architecture’s capabilities are evaluated in the context of a simulated robot assisting humans in an office domain, on a physical robot (Baxter) manipulating tabletop objects, and on a wheeled robot (Turtlebot) moving objects to particular places or people. The experimental results indicate improvements in reliability and computational efficiency compared with an architecture that does not include the theory of intentions, and an architecture that does not include zooming for fine-resolution reasoning. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13275v1 |
| https://arxiv.org/pdf/1907.13275v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-theory-of-intentions-for-human |
| Repo | |
| Framework | |
Human few-shot learning of compositional instructions
| Title | Human few-shot learning of compositional instructions |
| Authors | Brenden M. Lake, Tal Linzen, Marco Baroni |
| Abstract | People learn in fast and flexible ways that have not been emulated by machines. Once a person learns a new verb “dax,” he or she can effortlessly understand how to “dax twice,” “walk and dax,” or “dax vigorously.” There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways. To better understand these distinctively human abilities, we study the compositional skills of people through language-like instruction learning tasks. Our results show that people can learn and use novel functional concepts from very few examples (few-shot learning), successfully applying familiar functions to novel inputs. People can also compose concepts in complex ways that go beyond the provided demonstrations. Two additional experiments examined the assumptions and inductive biases that people make when solving these tasks, revealing three biases: mutual exclusivity, one-to-one mappings, and iconic concatenation. We discuss the implications for cognitive modeling and the potential for building machines with more human-like language learning capabilities. |
| Tasks | Few-Shot Learning |
| Published | 2019-01-14 |
| URL | https://arxiv.org/abs/1901.04587v2 |
| https://arxiv.org/pdf/1901.04587v2.pdf | |
| PWC | https://paperswithcode.com/paper/human-few-shot-learning-of-compositional |
| Repo | |
| Framework | |
Adjustment Criteria for Recovering Causal Effects from Missing Data
| Title | Adjustment Criteria for Recovering Causal Effects from Missing Data |
| Authors | Mojdeh Saadati, Jin Tian |
| Abstract | Confounding bias, missing data, and selection bias are three common obstacles to valid causal inference in the data sciences. Covariate adjustment is the most pervasive technique for recovering casual effects from confounding bias. In this paper, we introduce a covariate adjustment formulation for controlling confounding bias in the presence of missing-not-at-random data and develop a necessary and sufficient condition for recovering causal effects using the adjustment. We also introduce an adjustment formulation for controlling both confounding and selection biases in the presence of missing data and develop a necessary and sufficient condition for valid adjustment. Furthermore, we present an algorithm that lists all valid adjustment sets and an algorithm that finds a valid adjustment set containing the minimum number of variables, which are useful for researchers interested in selecting adjustment sets with desired properties. |
| Tasks | Causal Inference |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01654v3 |
| https://arxiv.org/pdf/1907.01654v3.pdf | |
| PWC | https://paperswithcode.com/paper/adjustment-criteria-for-recovering-causal |
| Repo | |
| Framework | |
