arXiv subjects

Wen Wang

Publications and source records attributed to Wen Wang.

At least 199 records · Page 11Linked to original sources

arXiv2020

TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient.

cs.CV↗

arXiv2020

Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection

With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performance of subsequent applications, such as machine translation, dialogue systems, and so forth. In this paper, we propose a Controllable Time-delay Transformer (CT-Transformer) model that jointly completes the punctuation prediction and disfluency detection tasks in real time. The CT-Transformer model facilitates freezing partial outputs with controllable time delay to fulfill the real-time constraints in partial decoding required by subsequent applications. We further propose a fast decoding strategy to minimize latency while maintaining competitive performance. Experimental results on the IWSLT2011 benchmark dataset and an in-house Chinese annotated dataset demonstrate that the proposed approach outperforms the previous state-of-the-art models on F-scores and achieves a competitive inference speed.

cs.CL↗

arXiv2020

Sequential Neural Networks for Noetic End-to-End Response Selection

The noetic end-to-end response selection challenge as one track in the 7th Dialog System Technology Challenges (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context. This paper presents our systems that are ranked top 1 on both datasets under this challenge, one focused and small (Advising) and the other more diverse and large (Ubuntu). Previous state-of-the-art models use hierarchy-based (utterance-level and token-level) neural networks to explicitly model the interactions among different turns' utterances for context modeling. In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection. Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection. In addition to ranking top 1 in the challenge, the proposed model outperforms all previous models, including state-of-the-art hierarchy-based models, on two large-scale public multi-turn response selection benchmark datasets.

cs.CL↗

arXiv2020

Transfer Learning for Context-Aware Spoken Language Understanding

Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly improves SLU performance for multi-turn dialogues. However, collecting a large-scale human-labeled multi-turn dialogue corpus for the target domains is complex and costly. To reduce dependency on the collection and annotation effort, we propose a Context Encoding Language Transformer (CELT) model facilitating exploiting various context information for SLU. We explore different transfer learning approaches to reduce dependency on data collection and annotation. In addition to unsupervised pre-training using large-scale general purpose unlabeled corpora, such as Wikipedia, we explore unsupervised and supervised adaptive training approaches for transfer learning to benefit from other in-domain and out-of-domain dialogue corpora. Experimental results demonstrate that the proposed model with the proposed transfer learning approaches achieves significant improvement on the SLU performance over state-of-the-art models on two large-scale single-turn dialogue benchmarks and one large-scale multi-turn dialogue benchmark.

cs.CL↗

arXiv2020

A Comprehensive Study on Temporal Modeling for Online Action Detection

Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules: a frame-level feature extractor which is usually based on pre-trained deep Convolutional Neural Networks (CNNs), a temporal modeling module, and an action classifier. Among them, the temporal modeling module is crucial which aggregates discriminative information from historical and current features. Though many temporal modeling methods have been developed for OAD and other topics, their effects are lack of investigation on OAD fairly. This paper aims to provide a comprehensive study on temporal modeling for OAD including four meta types of temporal modeling methods, \ie temporal pooling, temporal convolution, recurrent neural networks, and temporal attention, and uncover some good practices to produce a state-of-the-art OAD system. Many of them are explored in OAD for the first time, and extensively evaluated with various hyper parameters. Furthermore, based on our comprehensive study, we present several hybrid temporal modeling methods, which outperform the recent state-of-the-art methods with sizable margins on THUMOS-14 and TVSeries.

cs.HC↗

arXiv2019

A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification

In this work, a discriminatively learned CNN embedding is proposed for remote sensing image scene classification. Our proposed siamese network simultaneously computes the classification loss function and the metric learning loss function of the two input images. Specifically, for the classification loss, we use the standard cross-entropy loss function to predict the classes of the images. For the metric learning loss, our siamese network learns to map the intra-class and inter-class input pairs to a feature space where intra-class inputs are close and inter-class inputs are separated by a margin. Concretely, for remote sensing image scene classification, we would like to map images from the same scene to feature vectors that are close, and map images from different scenes to feature vectors that are widely separated. Experiments are conducted on three different remote sensing image datasets to evaluate the effectiveness of our proposed approach. The results demonstrate that the proposed method achieves an excellent classification performance.

cs.CV↗

arXiv2019

Sequential Attention-based Network for Noetic End-to-End Response Selection

The noetic end-to-end response selection challenge as one track in Dialog System Technology Challenges 7 (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context. This paper describes our systems that are ranked the top on both datasets under this challenge, one focused and small (Advising) and the other more diverse and large (Ubuntu). Previous state-of-the-art models use hierarchy-based (utterance-level and token-level) neural networks to explicitly model the interactions among different turns' utterances for context modeling. In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection. Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection. In addition to ranking the top in the challenge, the proposed model outperforms all previous models, including state-of-the-art hierarchy-based models, and achieves new state-of-the-art performances on two large-scale public multi-turn response selection benchmark datasets.

cs.CL↗

arXiv2019

Polymeric Liquid Layer Densified by Surface Acoustic Wave

With the application of surface acoustic wave (SAW) of 39.5 MHz to a model polymer liquid film,polyisobutylene, deposited on the solid substrates, the liquid film is densified, proved by the decrease of film thickness and the increase of refractive index, measured by ellipsometry. Rotational motion of fluorescent probes doped inside the liquid film, measured by polarization-resolved single molecule fluorescence microscopy, is retarded and the dynamical heterogeneity is reduced. It is demonstrated that the application of SAW of high frequency makes the thin polymeric liquid film densified and more dynamically homogeneous.

physics.app-ph↗

arXiv2019

Automated Curriculum Learning for Turn-level Spoken Language Understanding with Weak Supervision

We propose a learning approach for turn-level spoken language understanding, which facilitates a user to speak one or more utterances compositionally in a turn for completing a task (e.g., voice ordering). A typical pipelined approach for these understanding tasks requires non-trivial annotation effort for developing its multiple components. Also, the pipeline is difficult to port to a new domain or scale up. To address these problems, we propose an end-to-end statistical model with weak supervision. We employ randomized beam search with memory augmentation (RBSMA) to solve complicated problems for which long promising trajectories are usually difficult to explore. Furthermore, considering the diversity of problem complexity, we explore automated curriculum learning (CL) for weak supervision to accelerate exploration and learning. We evaluate the proposed approach on real-world user logs of a commercial voice ordering system. Results demonstrate that when trained on a small number of end-to-end annotated sessions collected with low cost, our model performs comparably to the deployed pipelined system, saving the development labor over an order of magnitude. The RBSMA algorithm improves the test set accuracy by 7.8% relative compared to the standard beam search. Automated CL leads to better generalization and further improves the test set accuracy by 5% relative.

cs.CL↗

arXiv2019

Attention: A Big Surprise for Cross-Domain Person Re-Identification

In this paper, we focus on model generalization and adaptation for cross-domain person re-identification (Re-ID). Unlike existing cross-domain Re-ID methods, leveraging the auxiliary information of those unlabeled target-domain data, we aim at enhancing the model generalization and adaptation by discriminative feature learning, and directly exploiting a pre-trained model to new domains (datasets) without any utilization of the information from target domains. To address the discriminative feature learning problem, we surprisingly find that simply introducing the attention mechanism to adaptively extract the person features for every domain is of great effectiveness. We adopt two popular type of attention mechanisms, long-range dependency based attention and direct generation based attention. Both of them can perform the attention via spatial or channel dimensions alone, even the combination of spatial and channel dimensions. The outline of different attentions are well illustrated. Moreover, we also incorporate the attention results into the final output of model through skip-connection to improve the features with both high and middle level semantic visual information. In the manner of directly exploiting a pre-trained model to new domains, the attention incorporation method truly could enhance the model generalization and adaptation to perform the cross-domain person Re-ID. We conduct extensive experiments between three large datasets, Market-1501, DukeMTMC-reID and MSMT17. Surprisingly, introducing only attention can achieve state-of-the-art performance, even much better than those cross-domain Re-ID methods utilizing auxiliary information from the target domain.

cs.CV↗

arXiv2019

The General Pair-based Weighting Loss for Deep Metric Learning

Deep metric learning aims at learning the distance metric between pair of samples, through the deep neural networks to extract the semantic feature embeddings where similar samples are close to each other while dissimilar samples are farther apart. A large amount of loss functions based on pair distances have been presented in the literature for guiding the training of deep metric learning. In this paper, we unify them in a general pair-based weighting loss function, where the minimizing objective loss is just the distances weighting of informative pairs. The general pair-based weighting loss includes two main aspects, (1) samples mining and (2) pairs weighting. Samples mining aims at selecting the informative positive and negative pair sets to exploit the structured relationship of samples in a mini-batch and also reduce the number of non-trivial pairs. Pair weighting aims at assigning different weights for different pairs according to the pair distances for discriminatively training the network. We detailedly review those existing pair-based losses inline with our general loss function, and explore some possible methods from the perspective of samples mining and pairs weighting. Finally, extensive experiments on three image retrieval datasets show that our general pair-based weighting loss obtains new state-of-the-art performance, demonstrating the effectiveness of the pair-based samples mining and pairs weighting for deep metric learning.

cs.CV↗

arXiv2019

BERT for Joint Intent Classification and Slot Filling

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

cs.CL↗

arXiv2019

Frequency-modulated continuous-wave laser distance measurement system using Fabry- Perot cavity as measuring reference

Frequency-modulated continuous-wave (FMCW) is a ranging technique that allows for high precision distance measurement over long distances. Scanning nonlinearity and range of the tunable laser are the main factors affecting the measurement accuracy. Frequency-sampling method is a recognized post-processing scheme to compensate the scanning nonlinearity. In this work, an FMCW laser distance measurement system using a high fineness Fabry-Perot (F-P) cavity as a sampling reference is demonstrated. The frequency of the resampled signal is calculated with a Hilbert transform. The high stability of the F-P cavity and the advantages of the Hilbert transform lead to a high measurement precision when an external cavity diode laser (ECDL) with a scanning range of tens of GHz is available. In this experiment, the scanning range of the ECDL is only 88 GHz, and a measurement uncertainty of 76.8 um (with coverage factor of k = 2) within a distance of 6.7 m is demonstrated.

physics.ins-det↗

arXiv2018

Early Stratification of Patients at Risk for Postoperative Complications after Elective Colectomy

Stratifying patients at risk for postoperative complications may facilitate timely and accurate workups and reduce the burden of adverse events on patients and the health system. Currently, a widely-used surgical risk calculator created by the American College of Surgeons, NSQIP, uses 21 preoperative covariates to assess risk of postoperative complications, but lacks dynamic, real-time capabilities to accommodate postoperative information. We propose a new Hidden Markov Model sequence classifier for analyzing patients' postoperative temperature sequences that incorporates their time-invariant characteristics in both transition probability and initial state probability in order to develop a postoperative "real-time" complication detector. Data from elective Colectomy surgery indicate that our method has improved classification performance compared to 8 other machine learning classifiers when using the full temperature sequence associated with the patients' length of stay. Additionally, within 44 hours after surgery, the performance of the model is close to that of full-length temperature sequence.

cs.LG↗

arXiv2018

Single-shot image retrieval through a multimode fiber using a genetic algorithm

In this letter, we present a genetic algorithm-based approach for image retrieval through a multimode fiber in a reference-less system. Due to mode interference, when an image is illuminated at one side of a multimode fiber, the transmitted light forms a noise-like speckle pattern at the other end. With the use of a prior-measured transmission matrix of the fiber, a speckle pattern is calculated using a random input mask. By optimizing the input mask to achieve a high correlation coefficient of experimental and calculated patterns, the input mask is optimized into an image with high similarity to the original image.

eess.IV↗

arXiv2018

A Universal Quantum Computing Virtual Machine

A medium-scale quantum computer with full universal quantum computing capability is necessary for various practical aims and testing applications. Here we report a 34-qubit quantum virtual machine (QtVM) based on a medium server. Our QtVM can run quantum assembly language with graphic interfaces. The QtVM is implemented with single qubit rotation gate, single to multiple controlled NOT gates to realize the universal quantum computation. Remarkably, it can realize a series of basic functions, such as, the "if" conditional programming language based on single-shot projective measurement results, "for" iteration programming language, build in arithmetic calculation. The measurement can be single-shot and arbitrary number of multi-shot types. In addition, there is in principle no limitation on number of logic gates implemented for quantum computation. By using QtVM, we demonstrate the simulation of dynamical quantum phase transition of transverse field Ising model by quantum circuits, where 34 qubits with one million gates are realized. We also show the realization of programmable Shor algorithm for factoring 15 and 35.

quant-ph↗

arXiv2018

Temporal Action Detection by Joint Identification-Verification

Temporal action detection aims at not only recognizing action category but also detecting start time and end time for each action instance in an untrimmed video. The key challenge of this task is to accurately classify the action and determine the temporal boundaries of each action instance. In temporal action detection benchmark: THUMOS 2014, large variations exist in the same action category while many similarities exist in different action categories, which always limit the performance of temporal action detection. To address this problem, we propose to use joint Identification-Verification network to reduce the intra-action variations and enlarge inter-action differences. The joint Identification-Verification network is a siamese network based on 3D ConvNets, which can simultaneously predict the action categories and the similarity scores for the input pairs of video proposal segments. Extensive experimental results on the challenging THUMOS 2014 dataset demonstrate the effectiveness of our proposed method compared to the existing state-of-art methods for temporal action detection in untrimmed videos.

cs.CV↗

arXiv2018

Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition

This paper explores the use of multi-view features and their discriminative transforms in a convolutional deep neural network (CNN) architecture for a continuous large vocabulary speech recognition task. Mel-filterbank energies and perceptually motivated forced damped oscillator coefficient (DOC) features are used after feature-space maximum-likelihood linear regression (fMLLR) transforms, which are combined and fed as a multi-view feature to a single CNN acoustic model. Use of multi-view feature representation demonstrated significant reduction in word error rates (WERs) compared to the use of individual features by themselves. In addition, when articulatory information was used as an additional input to a fused deep neural network (DNN) and CNN acoustic model, it was found to demonstrate further reduction in WER for the Switchboard subset and the CallHome subset (containing partly non-native accented speech) of the NIST 2000 conversational telephone speech test set, reducing the error rate by 12% relative to the baseline in both cases. This work shows that multi-view features in association with articulatory information can improve speech recognition robustness to spontaneous and non-native speech.

cs.CL↗