Paper Group ANR 129
Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion. A PAC RL Algorithm for Episodic POMDPs. Geometric Hypergraph Learning for Visual Tracking. A Universal Update-pacing Framework For Visual Tracking. Forward Stagewise Additive Model for Collaborative Multiview Boosting. PAC-Bayesian Analysis for a two-step …
Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion
| Title | Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion |
| Authors | Dinesh Jayaraman, Kristen Grauman |
| Abstract | Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we first show how a recurrent neural network-based system may be trained to perform end-to-end learning of motion policies suited for this “active recognition” setting. Further, we hypothesize that active vision requires an agent to have the capacity to reason about the effects of its motions on its view of the world. To verify this hypothesis, we attempt to induce this capacity in our active recognition pipeline, by simultaneously learning to forecast the effects of the agent’s motions on its internal representation of the environment conditional on all past views. Results across two challenging datasets confirm both that our end-to-end system successfully learns meaningful policies for active category recognition, and that “learning to look ahead” further boosts recognition performance. |
| Tasks | |
| Published | 2016-04-30 |
| URL | http://arxiv.org/abs/1605.00164v2 |
| http://arxiv.org/pdf/1605.00164v2.pdf | |
| PWC | https://paperswithcode.com/paper/look-ahead-before-you-leap-end-to-end-active |
| Repo | |
| Framework | |
A PAC RL Algorithm for Episodic POMDPs
| Title | A PAC RL Algorithm for Episodic POMDPs |
| Authors | Zhaohan Daniel Guo, Shayan Doroudi, Emma Brunskill |
| Abstract | Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially observable RL algorithm with a polynomial bound on the number of episodes on which the algorithm may not achieve near-optimal performance. Our algorithm is suitable for an important class of episodic POMDPs. Our approach builds on recent advances in method of moments for latent variable model estimation. |
| Tasks | |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.08062v2 |
| http://arxiv.org/pdf/1605.08062v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-pac-rl-algorithm-for-episodic-pomdps |
| Repo | |
| Framework | |
Geometric Hypergraph Learning for Visual Tracking
| Title | Geometric Hypergraph Learning for Visual Tracking |
| Authors | Dawei Du, Honggang Qi, Longyin Wen, Qi Tian, Qingming Huang, Siwei Lyu |
| Abstract | Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames. However, most graph based trackers consider pairwise geometric relations between local parts. They do not make full use of the target’s intrinsic structure, thereby making the representation easily disturbed by errors in pairwise affinities when large deformation and occlusion occur. In this paper, we propose a geometric hypergraph learning based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in consecutive frames. Then visual tracking is formulated as the mode-seeking problem on the hypergraph in which vertices represent correspondence hypotheses and hyperedges describe high-order geometric relations. Besides, a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hypergraph for more robustness and scalability. The experiments are carried out on two challenging datasets (VOT2014 and Deform-SOT) to demonstrate that the proposed method performs favorable against other existing trackers. |
| Tasks | Visual Tracking |
| Published | 2016-03-18 |
| URL | http://arxiv.org/abs/1603.05930v1 |
| http://arxiv.org/pdf/1603.05930v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-hypergraph-learning-for-visual |
| Repo | |
| Framework | |
A Universal Update-pacing Framework For Visual Tracking
| Title | A Universal Update-pacing Framework For Visual Tracking |
| Authors | Zexi Hu, Yuefang Gao, Dong Wang, Xuhong Tian |
| Abstract | This paper proposes a novel framework to alleviate the model drift problem in visual tracking, which is based on paced updates and trajectory selection. Given a base tracker, an ensemble of trackers is generated, in which each tracker’s update behavior will be paced and then traces the target object forward and backward to generate a pair of trajectories in an interval. Then, we implicitly perform self-examination based on trajectory pair of each tracker and select the most robust tracker. The proposed framework can effectively leverage temporal context of sequential frames and avoid to learn corrupted information. Extensive experiments on the standard benchmark suggest that the proposed framework achieves superior performance against state-of-the-art trackers. |
| Tasks | Visual Tracking |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00132v1 |
| http://arxiv.org/pdf/1603.00132v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-universal-update-pacing-framework-for |
| Repo | |
| Framework | |
Forward Stagewise Additive Model for Collaborative Multiview Boosting
| Title | Forward Stagewise Additive Model for Collaborative Multiview Boosting |
| Authors | Avisek Lahiri, Biswajit Paria, Prabir Kumar Biswas |
| Abstract | Multiview assisted learning has gained significant attention in recent years in supervised learning genre. Availability of high performance computing devices enables learning algorithms to search simultaneously over multiple views or feature spaces to obtain an optimum classification performance. The paper is a pioneering attempt of formulating a mathematical foundation for realizing a multiview aided collaborative boosting architecture for multiclass classification. Most of the present algorithms apply multiview learning heuristically without exploring the fundamental mathematical changes imposed on traditional boosting. Also, most of the algorithms are restricted to two class or view setting. Our proposed mathematical framework enables collaborative boosting across any finite dimensional view spaces for multiclass learning. The boosting framework is based on forward stagewise additive model which minimizes a novel exponential loss function. We show that the exponential loss function essentially captures difficulty of a training sample space instead of the traditional `1/0’ loss. The new algorithm restricts a weak view from over learning and thereby preventing overfitting. The model is inspired by our earlier attempt on collaborative boosting which was devoid of mathematical justification. The proposed algorithm is shown to converge much nearer to global minimum in the exponential loss space and thus supersedes our previous algorithm. The paper also presents analytical and numerical analysis of convergence and margin bounds for multiview boosting algorithms and we show that our proposed ensemble learning manifests lower error bound and higher margin compared to our previous model. Also, the proposed model is compared with traditional boosting and recent multiview boosting algorithms. | |
| Tasks | Multiview Learning |
| Published | 2016-08-05 |
| URL | http://arxiv.org/abs/1608.01874v1 |
| http://arxiv.org/pdf/1608.01874v1.pdf | |
| PWC | https://paperswithcode.com/paper/forward-stagewise-additive-model-for |
| Repo | |
| Framework | |
PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach
| Title | PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach |
| Authors | Anil Goyal, Emilie Morvant, Pascal Germain, Massih-Reza Amini |
| Abstract | We study a two-level multiview learning with more than two views under the PAC-Bayesian framework. This approach, sometimes referred as late fusion, consists in learning sequentially multiple view-specific classifiers at the first level, and then combining these view-specific classifiers at the second level. Our main theoretical result is a generalization bound on the risk of the majority vote which exhibits a term of diversity in the predictions of the view-specific classifiers. From this result it comes out that controlling the trade-off between diversity and accuracy is a key element for multiview learning, which complements other results in multiview learning. Finally, we experiment our principle on multiview datasets extracted from the Reuters RCV1/RCV2 collection. |
| Tasks | Multiview Learning |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07240v3 |
| http://arxiv.org/pdf/1606.07240v3.pdf | |
| PWC | https://paperswithcode.com/paper/pac-bayesian-analysis-for-a-two-step |
| Repo | |
| Framework | |
Position and Vector Detection of Blind Spot motion with the Horn-Schunck Optical Flow
| Title | Position and Vector Detection of Blind Spot motion with the Horn-Schunck Optical Flow |
| Authors | Stephen Yu, Mike Wu |
| Abstract | The proposed method uses live image footage which, based on calculations of pixel motion, decides whether or not an object is in the blind-spot. If found, the driver is notified by a sensory light or noise built into the vehicle’s CPU. The new technology incorporates optical vectors and flow fields rather than expensive radar-waves, creating cheaper detection systems that retain the needed accuracy while adapting to the current processor speeds. |
| Tasks | Optical Flow Estimation |
| Published | 2016-03-24 |
| URL | http://arxiv.org/abs/1603.07625v1 |
| http://arxiv.org/pdf/1603.07625v1.pdf | |
| PWC | https://paperswithcode.com/paper/position-and-vector-detection-of-blind-spot |
| Repo | |
| Framework | |
Temporal Network Analysis of Literary Texts
| Title | Temporal Network Analysis of Literary Texts |
| Authors | Sandra D. Prado, Silvio R. Dahmen, Ana L. C. Bazzan, Padraig Mac Carron, Ralph Kenna |
| Abstract | We study temporal networks of characters in literature focusing on “Alice’s Adventures in Wonderland” (1865) by Lewis Carroll and the anonymous “La Chanson de Roland” (around 1100). The former, one of the most influential pieces of nonsense literature ever written, describes the adventures of Alice in a fantasy world with logic plays interspersed along the narrative. The latter, a song of heroic deeds, depicts the Battle of Roncevaux in 778 A.D. during Charlemagne’s campaign on the Iberian Peninsula. We apply methods recently developed by Taylor and coworkers \cite{Taylor+2015} to find time-averaged eigenvector centralities, Freeman indices and vitalities of characters. We show that temporal networks are more appropriate than static ones for studying stories, as they capture features that the time-independent approaches fail to yield. |
| Tasks | |
| Published | 2016-02-22 |
| URL | http://arxiv.org/abs/1602.07275v1 |
| http://arxiv.org/pdf/1602.07275v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-network-analysis-of-literary-texts |
| Repo | |
| Framework | |
Flies as Ship Captains? Digital Evolution Unravels Selective Pressures to Avoid Collision in Drosophila
| Title | Flies as Ship Captains? Digital Evolution Unravels Selective Pressures to Avoid Collision in Drosophila |
| Authors | Ali Tehrani-Saleh, Christoph Adami |
| Abstract | Flies that walk in a covered planar arena on straight paths avoid colliding with each other, but which of the two flies stops is not random. High-throughput video observations, coupled with dedicated experiments with controlled robot flies have revealed that flies utilize the type of optic flow on their retina as a determinant of who should stop, a strategy also used by ship captains to determine which of two ships on a collision course should throw engines in reverse. We use digital evolution to test whether this strategy evolves when collision avoidance is the sole penalty. We find that the strategy does indeed evolve in a narrow range of cost/benefit ratios, for experiments in which the “regressive motion” cue is error free. We speculate that these stringent conditions may not be sufficient to evolve the strategy in real flies, pointing perhaps to auxiliary costs and benefits not modeled in our study |
| Tasks | |
| Published | 2016-03-02 |
| URL | http://arxiv.org/abs/1603.00802v1 |
| http://arxiv.org/pdf/1603.00802v1.pdf | |
| PWC | https://paperswithcode.com/paper/flies-as-ship-captains-digital-evolution |
| Repo | |
| Framework | |
Characterization of experts in crowdsourcing platforms
| Title | Characterization of experts in crowdsourcing platforms |
| Authors | Amal Ben Rjab, Mouloud Kharoune, Zoltan Miklos, Arnaud Martin |
| Abstract | Crowdsourcing platforms enable to propose simple human intelligence tasks to a large number of participants who realise these tasks. The workers often receive a small amount of money or the platforms include some other incentive mechanisms, for example they can increase the workers reputation score, if they complete the tasks correctly. We address the problem of identifying experts among participants, that is, workers, who tend to answer the questions correctly. Knowing who are the reliable workers could improve the quality of knowledge one can extract from responses. As opposed to other works in the literature, we assume that participants can give partial or incomplete responses, in case they are not sure that their answers are correct. We model such partial or incomplete responses with the help of belief functions, and we derive a measure that characterizes the expertise level of each participant. This measure is based on precise and exactitude degrees that represent two parts of the expertise level. The precision degree reflects the reliability level of the participants and the exactitude degree reflects the knowledge level of the participants. We also analyze our model through simulation and demonstrate that our richer model can lead to more reliable identification of experts. |
| Tasks | |
| Published | 2016-09-30 |
| URL | http://arxiv.org/abs/1609.09748v1 |
| http://arxiv.org/pdf/1609.09748v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-of-experts-in-crowdsourcing |
| Repo | |
| Framework | |
BPCMont: Business Process Change Management Ontology
| Title | BPCMont: Business Process Change Management Ontology |
| Authors | Muhammad Fahad |
| Abstract | Change management for evolving collaborative business process development is crucial when the business logic, transections and workflow change due to changes in business strategies or organizational and technical environment. During the change implementation, business processes are analyzed and improved ensuring that they capture the proposed change and they do not contain any undesired functionalities or change side-effects. This paper presents Business Process Change Management approach for the efficient and effective implementation of change in the business process. The key technology behind our approach is our proposed Business Process Change Management Ontology (BPCMont) which is the main contribution of this paper. BPCMont, as a formalized change specification, helps to revert BP into a consistent state in case of system crash, intermediate conflicting stage or unauthorized change done, aid in change traceability in the new and old versions of business processes, change effects can be seen and estimated effectively, ease for Stakeholders to validate and verify change implementation, etc. |
| Tasks | |
| Published | 2016-02-13 |
| URL | http://arxiv.org/abs/1602.04376v1 |
| http://arxiv.org/pdf/1602.04376v1.pdf | |
| PWC | https://paperswithcode.com/paper/bpcmont-business-process-change-management |
| Repo | |
| Framework | |
Feasibility Based Large Margin Nearest Neighbor Metric Learning
| Title | Feasibility Based Large Margin Nearest Neighbor Metric Learning |
| Authors | Babak Hosseini, Barbara Hammer |
| Abstract | Large margin nearest neighbor (LMNN) is a metric learner which optimizes the performance of the popular $k$NN classifier. However, its resulting metric relies on pre-selected target neighbors. In this paper, we address the feasibility of LMNN’s optimization constraints regarding these target points, and introduce a mathematical measure to evaluate the size of the feasible region of the optimization problem. We enhance the optimization framework of LMNN by a weighting scheme which prefers data triplets which yield a larger feasible region. This increases the chances to obtain a good metric as the solution of LMNN’s problem. We evaluate the performance of the resulting feasibility-based LMNN algorithm using synthetic and real datasets. The empirical results show an improved accuracy for different types of datasets in comparison to regular LMNN. |
| Tasks | Metric Learning |
| Published | 2016-10-18 |
| URL | http://arxiv.org/abs/1610.05710v2 |
| http://arxiv.org/pdf/1610.05710v2.pdf | |
| PWC | https://paperswithcode.com/paper/feasibility-based-large-margin-nearest |
| Repo | |
| Framework | |
Radon-Gabor Barcodes for Medical Image Retrieval
| Title | Radon-Gabor Barcodes for Medical Image Retrieval |
| Authors | Mina Nouredanesh, H. R. Tizhoosh, Ershad Banijamali, James Tung |
| Abstract | In recent years, with the explosion of digital images on the Web, content-based retrieval has emerged as a significant research area. Shapes, textures, edges and segments may play a key role in describing the content of an image. Radon and Gabor transforms are both powerful techniques that have been widely studied to extract shape-texture-based information. The combined Radon-Gabor features may be more robust against scale/rotation variations, presence of noise, and illumination changes. The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to introduce expressive binary features, called barcodes, for image annotation/tagging tasks. We propose two different techniques: Gabor-of-Radon-Image Barcodes (GRIBCs), and Guided-Radon-of-Gabor Barcodes (GRGBCs). For validation, we employ the IRMA x-ray dataset with 193 classes, containing 12,677 training images and 1,733 test images. A total error score as low as 322 and 330 were achieved for GRGBCs and GRIBCs, respectively. This corresponds to $\approx 81%$ retrieval accuracy for the first hit. |
| Tasks | Image Retrieval, Medical Image Retrieval |
| Published | 2016-09-16 |
| URL | http://arxiv.org/abs/1609.05118v1 |
| http://arxiv.org/pdf/1609.05118v1.pdf | |
| PWC | https://paperswithcode.com/paper/radon-gabor-barcodes-for-medical-image |
| Repo | |
| Framework | |
Symbolic Knowledge Extraction using Łukasiewicz Logics
| Title | Symbolic Knowledge Extraction using Łukasiewicz Logics |
| Authors | Carlos Leandro |
| Abstract | This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued {\L}ukasiewicz logic, wherein every connective can be defined by a neuron in an artificial network. This allowed the injection of first-order formulas into a network architecture, and also simplified symbolic rule extraction. For that we trained a neural networks using the Levenderg-Marquardt algorithm, where we restricted the knowledge dissemination in the network structure. This procedure reduces neural network plasticity without drastically damaging the learning performance, thus making the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language and simplifying the translation between symbolic and connectionist structures. We used this method for reverse engineering truth table and in extraction of formulas from real data sets. |
| Tasks | |
| Published | 2016-04-11 |
| URL | http://arxiv.org/abs/1604.03099v1 |
| http://arxiv.org/pdf/1604.03099v1.pdf | |
| PWC | https://paperswithcode.com/paper/symbolic-knowledge-extraction-using |
| Repo | |
| Framework | |
Large-Scale Reasoning with OWL
| Title | Large-Scale Reasoning with OWL |
| Authors | Michael Ruster |
| Abstract | With the growth of the Semantic Web in size and importance, more and more knowledge is stored in machine-readable formats such as the Web Ontology Language OWL. This paper outlines common approaches for efficient reasoning on large-scale data consisting of billions ($10^9$) of triples. Therefore, OWL and its sublanguages, as well as forward and backward chaining techniques are presented. The WebPIE reasoner is discussed in detail as an example for forward chaining using MapReduce for materialisation. Moreover, the QueryPIE reasoner is presented as a backward chaining/hybrid approach which uses query rewriting. Furthermore, an overview on other reasoners is given such as OWLIM and TrOWL. |
| Tasks | |
| Published | 2016-02-14 |
| URL | http://arxiv.org/abs/1602.04473v1 |
| http://arxiv.org/pdf/1602.04473v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-reasoning-with-owl |
| Repo | |
| Framework | |
