This paper proposes an unified framework for efficiently spotting scene text in videos. The method localizes and tracks text in each frame, and recognizes each tracked text stream one-time. Specifically, we first train a spatial-temporal text detector for localizing text regions in the sequential frames. Secondly, a well-designed text tracker is trained for grouping the localized text regions into corresponding cropped text streams. To efficiently spot video text, we recognize each tracked text stream one-time with a text region quality scoring mechanism instead of identifying the cropped text regions one-by-one. Experiments on two public benchmarks demonstrate that our method achieves impressive performance.
Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems. This paper studied an optimal divisible load distribution sequencing problem using a machine learning framework. The problem is to decide the optimal sequence to distribute divisible load to processors in order to achieve minimum finishing time. The scheduling is performed in a resource-sharing system where each physical processor is virtualized to multiple virtual processors. A reinforcement learning method called Multi-armed bandit (MAB) is used for our problem. We first provide a naive solution using the MAB algorithm and then several optimizations are performed. Various numerical tests are conducted. Our algorithm shows an increasing performance during the training progress and the global optimum will be acheived when the sample size is large enough.
Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations. However, the generated training data typically contain massive noise, and may result in poor performances with the vanilla supervised learning. In this paper, we propose to conduct multi-instance learning with a novel Cross-relation Cross-bag Selective Attention (C$^2$SA), which leads to noise-robust training for distant supervised relation extractor. Specifically, we employ the sentence-level selective attention to reduce the effect of noisy or mismatched sentences, while the correlation among relations were captured to improve the quality of attention weights. Moreover, instead of treating all entity-pairs equally, we try to pay more attention to entity-pairs with a higher quality. Similarly, we adopt the selective attention mechanism to achieve this goal. Experiments with two types of relation extractor demonstrate the superiority of the proposed approach over the state-of-the-art, while further ablation studies verify our intuitions and demonstrate the effectiveness of our proposed two techniques.
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well. In this paper, we propose to synthesize visual features based on an auto-encoder framework paired with bi-adversarial networks respectively for visual and semantic modalities to reinforce the visual-semantic interactions with a bi-directional alignment, which ensures the synthesized visual features to fit the real visual distribution and to be highly related to the semantics. The encoder aims at synthesizing real-like visual features while the decoder forces both the real and the synthesized visual features to be more related to the class semantics. To further capture the discriminative information of the synthesized visual features, both the real and synthesized visual features are forced to be classified into the correct classes via a classification network. Experimental results on four benchmark datasets show that the proposed approach is particularly competitive on both the traditional ZSL and the generalized ZSL tasks.
This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of intervals of multiple actions. Specifically, we first assemble video clips according to class labels by an attention mechanism that learns class-variable attention weights and thus helps the noise relieving from background or other actions. Secondly, we build temporal relationship between actions by feeding the assembled features into an enhanced recurrent neural network. Finally, we transform the output of recurrent neural network into the corresponding action distribution. In order to generate more precise temporal proposals, we design a score term called segregated temporal gradient-weighted class activation mapping (ST-GradCAM) fused with attention weights. Experiments on THUMOS'14 and ActivityNet1.3 datasets show that our approach outperforms the state-of-the-art weakly-supervised method, and performs at par with the fully-supervised counterparts.
Retweet prediction is a challenging problem in social media sites (SMS). In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees. Unlike previous studies, we learn user preference ranking model from their past retweeted image tweets in SMS. We first propose heterogeneous image retweet modeling network (IRM) that exploits users' past retweeted image tweets with associated contexts, their following relations in SMS and preference of their followees. We then develop a novel attentional multi-faceted ranking network learning framework with textually guided multi-modal neural networks for the proposed heterogenous IRM network to learn the joint image tweet representations and user preference representations for prediction task. The extensive experiments on a large-scale dataset from Twitter site shows that our method achieves better performance than other state-of-the-art solutions to the problem.
We propose a novel attentive sequence to sequence translator (ASST) for clip localization in videos by natural language descriptions. We make two contributions. First, we propose a bi-directional Recurrent Neural Network (RNN) with a finely calibrated vision-language attentive mechanism to comprehensively understand the free-formed natural language descriptions. The RNN parses natural language descriptions in two directions, and the attentive model attends every meaningful word or phrase to each frame, thereby resulting in a more detailed understanding of video content and description semantics. Second, we design a hierarchical architecture for the network to jointly model language descriptions and video content. Given a video-description pair, the network generates a matrix representation, i.e., a sequence of vectors. Each vector in the matrix represents a video frame conditioned by the description. The 2D representation not only preserves the temporal dependencies of frames but also provides an effective way to perform frame-level video-language matching. The hierarchical architecture exploits video content with multiple granularities, ranging from subtle details to global context. Integration of the multiple granularities yields a robust representation for multi-level video-language abstraction. We validate the effectiveness of our ASST on two large-scale datasets. Our ASST outperforms the state-of-the-art by $4.28\%$ in Rank$@1$ on the DiDeMo dataset. On the Charades-STA dataset, we significantly improve the state-of-the-art by $13.41\%$ in Rank$@1,IoU=0.5$.
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved. In this paper, we intend to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information. We do this within an encoder-decoder sequence learning framework that integrates the following data: 1) offline geographical and social attributes. For example, the geographical structure of roads or public social events such as national celebrations; 2) road intersection information. In general, traffic congestion occurs at major junctions; 3) online crowd queries. For example, when many online queries issued for the same destination due to a public performance, the traffic around the destination will potentially become heavier at this location after a while. Qualitative and quantitative experiments on a real-world dataset from Baidu have demonstrated the effectiveness of our framework.
Multi-label learning problems have manifested themselves in various machine learning applications. The key to successful multi-label learning algorithms lies in the exploration of inter-label correlations, which usually incur great computational cost. Another notable factor in multi-label learning is that the label vectors are usually extremely sparse, especially when the candidate label vocabulary is very large and only a few instances are assigned to each category. Recently, a label space transformation (LST) framework has been proposed targeting these challenges. However, current methods based on LST usually suffer from information loss in the label space dimension reduction process and fail to address the sparsity problem effectively. In this paper, we propose a distribution-based label space transformation (DLST) model. By defining the distribution based on the similarity of label vectors, a more comprehensive label structure can be captured. Then, by minimizing KL-divergence of two distributions, the information of the original label space can be approximately preserved in the latent space. Consequently, multi-label classifier trained using the dense latent codes yields better performance. The leverage of distribution enables DLST to fill out additional information about the label correlations. This endows DLST the capability to handle label set sparsity and training data sparsity in multi-label learning problems. With the optimal latent code, a kernel logistic regression function is learned for the mapping from feature space to the latent space. Then ML-KNN is employed to recover the original label vector from the transformed latent code. Extensive experiments on several benchmark datasets demonstrate that DLST not only achieves high classification performance but also is computationally more efficient.
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer or sampled based on their priority measured by temporal-difference (TD) error. However, these approaches do not fully take into consideration the intrinsic characteristics of transition distribution in the state space and could result in redundant and unnecessary TD updates, slowing down the convergence of the learning procedure. To overcome this problem, we propose a novel state distribution-aware sampling method to balance the replay times for transitions with skew distribution, which takes into account both the occurrence frequencies of transitions and the uncertainty of state-action values. Consequently, our approach could reduce the unnecessary TD updates and increase the TD updates for state-action value with more uncertainty, making the experience replay more effective and efficient. Extensive experiments are conducted on both classic control tasks and Atari 2600 games based on OpenAI gym platform and the experimental results demonstrate the effectiveness of our approach in comparison with the standard DQN approach.