July 27, 2019

3239 words 16 mins read

Paper Group ANR 741

Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking. Few-Shot Adversarial Domain Adaptation. Exploring Human-like Attention Supervision in Visual Question Answering. Network Vector: Distributed Representations of Networks with Global Context. Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation …

Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking


Title	Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Authors	Laura Leal-Taixé, Anton Milan, Konrad Schindler, Daniel Cremers, Ian Reid, Stefan Roth
Abstract	Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. We present a benchmark for Multiple Object Tracking launched in the late 2014, with the goal of creating a framework for the standardized evaluation of multiple object tracking methods. This paper collects the two releases of the benchmark made so far, and provides an in-depth analysis of almost 50 state-of-the-art trackers that were tested on over 11000 frames. We show the current trends and weaknesses of multiple people tracking methods, and provide pointers of what researchers should be focusing on to push the field forward.
Tasks	Multiple Object Tracking, Multiple People Tracking, Object Tracking
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02781v1
PDF	http://arxiv.org/pdf/1704.02781v1.pdf
PWC	https://paperswithcode.com/paper/tracking-the-trackers-an-analysis-of-the
Repo
Framework

Few-Shot Adversarial Domain Adaptation


Title	Few-Shot Adversarial Domain Adaptation
Authors	Saeid Motiian, Quinn Jones, Seyed Mehdi Iranmanesh, Gianfranco Doretto
Abstract	This work provides a framework for addressing the problem of supervised domain adaptation with deep models. The main idea is to exploit adversarial learning to learn an embedded subspace that simultaneously maximizes the confusion between two domains while semantically aligning their embedding. The supervised setting becomes attractive especially when there are only a few target data samples that need to be labeled. In this few-shot learning scenario, alignment and separation of semantic probability distributions is difficult because of the lack of data. We found that by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes, it is possible to effectively address the supervised adaptation problem. In addition, the approach has a high speed of adaptation, i.e. it requires an extremely low number of labeled target training samples, even one per category can be effective. We then extensively compare this approach to the state of the art in domain adaptation in two experiments: one using datasets for handwritten digit recognition, and one using datasets for visual object recognition.
Tasks	Domain Adaptation, Few-Shot Learning, Handwritten Digit Recognition, Object Recognition
Published	2017-11-05
URL	http://arxiv.org/abs/1711.02536v1
PDF	http://arxiv.org/pdf/1711.02536v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-adversarial-domain-adaptation
Repo
Framework

Exploring Human-like Attention Supervision in Visual Question Answering


Title	Exploring Human-like Attention Supervision in Visual Question Answering
Authors	Tingting Qiao, Jianfeng Dong, Duanqing Xu
Abstract	Attention mechanisms have been widely applied in the Visual Question Answering (VQA) task, as they help to focus on the area-of-interest of both visual and textual information. To answer the questions correctly, the model needs to selectively target different areas of an image, which suggests that an attention-based model may benefit from an explicit attention supervision. In this work, we aim to address the problem of adding attention supervision to VQA models. Since there is a lack of human attention data, we first propose a Human Attention Network (HAN) to generate human-like attention maps, training on a recently released dataset called Human ATtention Dataset (VQA-HAT). Then, we apply the pre-trained HAN on the VQA v2.0 dataset to automatically produce the human-like attention maps for all image-question pairs. The generated human-like attention map dataset for the VQA v2.0 dataset is named as Human-Like ATtention (HLAT) dataset. Finally, we apply human-like attention supervision to an attention-based VQA model. The experiments show that adding human-like supervision yields a more accurate attention together with a better performance, showing a promising future for human-like attention supervision in VQA.
Tasks	Question Answering, Visual Question Answering
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06308v1
PDF	http://arxiv.org/pdf/1709.06308v1.pdf
PWC	https://paperswithcode.com/paper/exploring-human-like-attention-supervision-in
Repo
Framework

Network Vector: Distributed Representations of Networks with Global Context


Title	Network Vector: Distributed Representations of Networks with Global Context
Authors	Hao Wu, Kristina Lerman
Abstract	We propose a neural embedding algorithm called Network Vector, which learns distributed representations of nodes and the entire networks simultaneously. By embedding networks in a low-dimensional space, the algorithm allows us to compare networks in terms of structural similarity and to solve outstanding predictive problems. Unlike alternative approaches that focus on node level features, we learn a continuous global vector that captures each node’s global context by maximizing the predictive likelihood of random walk paths in the network. Our algorithm is scalable to real world graphs with many nodes. We evaluate our algorithm on datasets from diverse domains, and compare it with state-of-the-art techniques in node classification, role discovery and concept analogy tasks. The empirical results show the effectiveness and the efficiency of our algorithm.
Tasks	Node Classification
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02448v1
PDF	http://arxiv.org/pdf/1709.02448v1.pdf
PWC	https://paperswithcode.com/paper/network-vector-distributed-representations-of
Repo
Framework

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation


Title	Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
Authors	Ganbin Zhou, Ping Luo, Rongyu Cao, Yijun Xiao, Fen Lin, Bo Chen, Qing He
Abstract	Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentence-tree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2Tree framework outperforms baseline methods over 11.15% increase of acceptance ratio.
Tasks
Published	2017-04-30
URL	http://arxiv.org/abs/1705.00321v4
PDF	http://arxiv.org/pdf/1705.00321v4.pdf
PWC	https://paperswithcode.com/paper/tree-structured-neural-machine-for
Repo
Framework

Memory Augmented Neural Networks with Wormhole Connections


Title	Memory Augmented Neural Networks with Wormhole Connections
Authors	Caglar Gulcehre, Sarath Chandar, Yoshua Bengio
Abstract	Recent empirical results on long-term dependency tasks have shown that neural networks augmented with an external memory can learn the long-term dependency tasks more easily and achieve better generalization than vanilla recurrent neural networks (RNN). We suggest that memory augmented neural networks can reduce the effects of vanishing gradients by creating shortcut (or wormhole) connections. Based on this observation, we propose a novel memory augmented neural network model called TARDIS (Temporal Automatic Relation Discovery in Sequences). The controller of TARDIS can store a selective set of embeddings of its own previous hidden states into an external memory and revisit them as and when needed. For TARDIS, memory acts as a storage for wormhole connections to the past to propagate the gradients more effectively and it helps to learn the temporal dependencies. The memory structure of TARDIS has similarities to both Neural Turing Machines (NTM) and Dynamic Neural Turing Machines (D-NTM), but both read and write operations of TARDIS are simpler and more efficient. We use discrete addressing for read/write operations which helps to substantially to reduce the vanishing gradient problem with very long sequences. Read and write operations in TARDIS are tied with a heuristic once the memory becomes full, and this makes the learning problem simpler when compared to NTM or D-NTM type of architectures. We provide a detailed analysis on the gradient propagation in general for MANNs. We evaluate our models on different long-term dependency tasks and report competitive results in all of them.
Tasks
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08718v1
PDF	http://arxiv.org/pdf/1701.08718v1.pdf
PWC	https://paperswithcode.com/paper/memory-augmented-neural-networks-with
Repo
Framework

Team Formation for Scheduling Educational Material in Massive Online Classes


Title	Team Formation for Scheduling Educational Material in Massive Online Classes
Authors	Sanaz Bahargam, Dóra Erdos, Azer Bestavros, Evimaria Terzi
Abstract	Whether teaching in a classroom or a Massive Online Open Course it is crucial to present the material in a way that benefits the audience as a whole. We identify two important tasks to solve towards this objective, 1 group students so that they can maximally benefit from peer interaction and 2 find an optimal schedule of the educational material for each group. Thus, in this paper, we solve the problem of team formation and content scheduling for education. Given a time frame d, a set of students S with their required need to learn different activities T and given k as the number of desired groups, we study the problem of finding k group of students. The goal is to teach students within time frame d such that their potential for learning is maximized and find the best schedule for each group. We show this problem to be NP-hard and develop a polynomial algorithm for it. We show our algorithm to be effective both on synthetic as well as a real data set. For our experiments, we use real data on students’ grades in a Computer Science department. As part of our contribution, we release a semi-synthetic dataset that mimics the properties of the real data.
Tasks
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08762v1
PDF	http://arxiv.org/pdf/1703.08762v1.pdf
PWC	https://paperswithcode.com/paper/team-formation-for-scheduling-educational
Repo
Framework

Leveraging Patient Similarity and Time Series Data in Healthcare Predictive Models


Title	Leveraging Patient Similarity and Time Series Data in Healthcare Predictive Models
Authors	Mohammad Amin Morid, Olivia R. Liu Sheng, Samir Abdelrahman
Abstract	Patient time series classification faces challenges in high degrees of dimensionality and missingness. In light of patient similarity theory, this study explores effective temporal feature engineering and reduction, missing value imputation, and change point detection methods that can afford similarity-based classification models with desirable accuracy enhancement. We select a piecewise aggregation approximation method to extract fine-grain temporal features and propose a minimalist method to impute missing values in temporal features. For dimensionality reduction, we adopt a gradient descent search method for feature weight assignment. We propose new patient status and directional change definitions based on medical knowledge or clinical guidelines about the value ranges for different patient status levels, and develop a method to detect change points indicating positive or negative patient status changes. We evaluate the effectiveness of the proposed methods in the context of early Intensive Care Unit mortality prediction. The evaluation results show that the k-Nearest Neighbor algorithm that incorporates methods we select and propose significantly outperform the relevant benchmarks for early ICU mortality prediction. This study makes contributions to time series classification and early ICU mortality prediction via identifying and enhancing temporal feature engineering and reduction methods for similarity-based time series classification.
Tasks	Change Point Detection, Dimensionality Reduction, Feature Engineering, Imputation, Mortality Prediction, Time Series, Time Series Classification
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07498v3
PDF	http://arxiv.org/pdf/1704.07498v3.pdf
PWC	https://paperswithcode.com/paper/leveraging-patient-similarity-and-time-series
Repo
Framework

Asymmetric Learning Vector Quantization for Efficient Nearest Neighbor Classification in Dynamic Time Warping Spaces


Title	Asymmetric Learning Vector Quantization for Efficient Nearest Neighbor Classification in Dynamic Time Warping Spaces
Authors	Brijnesh Jain, David Schultz
Abstract	The nearest neighbor method together with the dynamic time warping (DTW) distance is one of the most popular approaches in time series classification. This method suffers from high storage and computation requirements for large training sets. As a solution to both drawbacks, this article extends learning vector quantization (LVQ) from Euclidean spaces to DTW spaces. The proposed LVQ scheme uses asymmetric weighted averaging as update rule. Empirical results exhibited superior performance of asymmetric generalized LVQ (GLVQ) over other state-of-the-art prototype generation methods for nearest neighbor classification.
Tasks	Quantization, Time Series, Time Series Classification
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08403v1
PDF	http://arxiv.org/pdf/1703.08403v1.pdf
PWC	https://paperswithcode.com/paper/asymmetric-learning-vector-quantization-for
Repo
Framework

Methods for Mapping Forest Disturbance and Degradation from Optical Earth Observation Data: a Review


Title	Methods for Mapping Forest Disturbance and Degradation from Optical Earth Observation Data: a Review
Authors	Manuela Hirschmugl, Heinz Gallaun, Matthias Dees, Pawan Datta, Janik Deutscher, Nikos Koutsias, Mathias Schardt
Abstract	Purpose of review: This paper presents a review of the current state of the art in remote sensing based monitoring of forest disturbances and forest degradation from optical Earth Observation data. Part one comprises an overview of currently available optical remote sensing sensors, which can be used for forest disturbance and degradation mapping. Part two reviews the two main categories of existing approaches: classical image-to-image change detection and time series analysis. Recent findings: With the launch of the Sentinel-2a satellite and available Landsat imagery, time series analysis has become the most promising but also most demanding category of degradation mapping approaches. Four time series classification methods are distinguished. The methods are explained and their benefits and drawbacks are discussed. A separate chapter presents a number of recent forest degradation mapping studies for two different ecosystems: temperate forests with a geographical focus on Europe and tropical forests with a geographical focus on Africa. Summary: The review revealed that a wide variety of methods for the detection of forest degradation is already available. Today, the main challenge is to transfer these approaches to high resolution time series data from multiple sensors. Future research should also focus on the classification of disturbance types and the development of robust up-scalable methods to enable near real time disturbance mapping in support of operational reactive measures.
Tasks	Time Series, Time Series Analysis, Time Series Classification
Published	2017-01-10
URL	http://arxiv.org/abs/1701.02470v4
PDF	http://arxiv.org/pdf/1701.02470v4.pdf
PWC	https://paperswithcode.com/paper/methods-for-mapping-forest-disturbance-and
Repo
Framework

Model-Independent Online Learning for Influence Maximization


Title	Model-Independent Online Learning for Influence Maximization
Authors	Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks Lakshmanan, Mark Schmidt
Abstract	We consider influence maximization (IM) in social networks, which is the problem of maximizing the number of users that become aware of a product by selecting a set of “seed” users to expose the product to. While prior work assumes a known model of information diffusion, we propose a novel parametrization that not only makes our framework agnostic to the underlying diffusion model, but also statistically efficient to learn from data. We give a corresponding monotone, submodular surrogate function, and show that it is a good approximation to the original IM objective. We also consider the case of a new marketer looking to exploit an existing social network, while simultaneously learning the factors governing information propagation. For this, we propose a pairwise-influence semi-bandit feedback model and develop a LinUCB-based bandit algorithm. Our model-independent analysis shows that our regret bound has a better (as compared to previous work) dependence on the size of the network. Experimental evaluation suggests that our framework is robust to the underlying diffusion model and can efficiently learn a near-optimal solution.
Tasks
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00557v2
PDF	http://arxiv.org/pdf/1703.00557v2.pdf
PWC	https://paperswithcode.com/paper/model-independent-online-learning-for
Repo
Framework

Learning what matters - Sampling interesting patterns


Title	Learning what matters - Sampling interesting patterns
Authors	Vladimir Dzyuba, Matthijs van Leeuwen
Abstract	In the field of exploratory data mining, local structure in data can be described by patterns and discovered by mining algorithms. Although many solutions have been proposed to address the redundancy problems in pattern mining, most of them either provide succinct pattern sets or take the interests of the user into account-but not both. Consequently, the analyst has to invest substantial effort in identifying those patterns that are relevant to her specific interests and goals. To address this problem, we propose a novel approach that combines pattern sampling with interactive data mining. In particular, we introduce the LetSIP algorithm, which builds upon recent advances in 1) weighted sampling in SAT and 2) learning to rank in interactive pattern mining. Specifically, it exploits user feedback to directly learn the parameters of the sampling distribution that represents the user’s interests. We compare the performance of the proposed algorithm to the state-of-the-art in interactive pattern mining by emulating the interests of a user. The resulting system allows efficient and interleaved learning and sampling, thus user-specific anytime data exploration. Finally, LetSIP demonstrates favourable trade-offs concerning both quality-diversity and exploitation-exploration when compared to existing methods.
Tasks	Learning-To-Rank
Published	2017-02-07
URL	http://arxiv.org/abs/1702.01975v2
PDF	http://arxiv.org/pdf/1702.01975v2.pdf
PWC	https://paperswithcode.com/paper/learning-what-matters-sampling-interesting
Repo
Framework

Who Said What: Modeling Individual Labelers Improves Classification


Title	Who Said What: Modeling Individual Labelers Improves Classification
Authors	Melody Y. Guan, Varun Gulshan, Andrew M. Dai, Geoffrey E. Hinton
Abstract	Data are often labeled by many different experts with each expert only labeling a small fraction of the data and each data point being labeled by several experts. This reduces the workload on individual experts and also gives a better estimate of the unobserved ground truth. When experts disagree, the standard approaches are to treat the majority opinion as the correct label or to model the correct label as a distribution. These approaches, however, do not make any use of potentially valuable information about which expert produced which label. To make use of this extra information, we propose modeling the experts individually and then learning averaging weights for combining them, possibly in sample-specific ways. This allows us to give more weight to more reliable experts and take advantage of the unique strengths of individual experts at classifying certain types of data. Here we show that our approach leads to improvements in computer-aided diagnosis of diabetic retinopathy. We also show that our method performs better than competing algorithms by Welinder and Perona (2010), and by Mnih and Hinton (2012). Our work offers an innovative approach for dealing with the myriad real-world settings that use expert opinions to define labels for training.
Tasks
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08774v2
PDF	http://arxiv.org/pdf/1703.08774v2.pdf
PWC	https://paperswithcode.com/paper/who-said-what-modeling-individual-labelers
Repo
Framework

A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization


Title	A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization
Authors	Xinyu Hua, Lu Wang
Abstract	We study the problem of domain adaptation for neural abstractive summarization. We make initial efforts in investigating what information can be transferred to a new domain. Experimental results on news stories and opinion articles indicate that neural summarization model benefits from pre-training based on extractive summaries. We also find that the combination of in-domain and out-of-domain setup yields better summaries when in-domain data is insufficient. Further analysis shows that, the model is capable to select salient content even trained on out-of-domain data, but requires in-domain data to capture the style for a target domain.
Tasks	Abstractive Text Summarization, Domain Adaptation
Published	2017-07-21
URL	http://arxiv.org/abs/1707.07062v1
PDF	http://arxiv.org/pdf/1707.07062v1.pdf
PWC	https://paperswithcode.com/paper/a-pilot-study-of-domain-adaptation-effect-for
Repo
Framework

Generalized linear mixing model accounting for endmember variability


Title	Generalized linear mixing model accounting for endmember variability
Authors	Tales Imbiriba, Ricardo Augusto Borsoi, José Carlos Moreira Bermudez
Abstract	Endmember variability is an important factor for accurately unveiling vital information relating the pure materials and their distribution in hyperspectral images. Recently, the extended linear mixing model (ELMM) has been proposed as a modification of the linear mixing model (LMM) to consider endmember variability effects resulting mainly from illumination changes. In this paper, we further generalize the ELMM leading to a new model (GLMM) to account for more complex spectral distortions where different wavelength intervals can be affected unevenly. We also extend the existing methodology to jointly estimate the variability and the abundances for the GLMM. Simulations with real and synthetic data show that the unmixing process can benefit from the extra flexibility introduced by the GLMM.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07723v1
PDF	http://arxiv.org/pdf/1710.07723v1.pdf
PWC	https://paperswithcode.com/paper/generalized-linear-mixing-model-accounting
Repo
Framework