Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences. However, these methods still suffer from immediate or delayed repetitions in generated paragraphs because (i) the entanglement of syntax and semantics distracts the topic vector from attending pertinent visual regions; (ii) there are few constraints or rewards for learning long-range transitions. In this paper, we propose a bypass network that separately models semantics and linguistic syntax of preceding sentences. Specifically, the proposed model consists of two main modules, i.e. a topic transition module and a sentence generation module. The former takes previous semantic vectors as queries and applies attention mechanism on regional features to acquire the next topic vector, which reduces immediate repetition by eliminating linguistics. The latter decodes the topic vector and the preceding syntax state to produce the following sentence. To further reduce delayed repetition in generated paragraphs, we devise a replacement-based reward for the REINFORCE training. Comprehensive experiments on the widely used benchmark demonstrate the superiority of the proposed model over the state of the art for coherence while maintaining high accuracy.
Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to attribute perturbations and out-of-distribution compositions during inference. We ascribe the bottleneck to a failure of exploring the intrinsic semantic hierarchy of visual concepts, e.g. \{red, blue,...\} $\in$ `color' subspace yet cube $\in$ `shape'. In this paper, we propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces (i.e. visual superordinates). With only natural visual question answering data, our model first acquires the semantic hierarchy from a linguistic view, and then explores mutually exclusive visual superordinates under the guidance of linguistic hierarchy. In addition, a quasi-center visual concept clustering and a superordinate shortcut learning schemes are proposed to enhance the discrimination and independence of concepts within each visual superordinate. Experiments demonstrate the superiority of the proposed framework under diverse settings, which increases the overall answering accuracy relatively by 7.5\% on reasoning with perturbations and 15.6\% on compositional generalization tests.
Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to capture, process, and share high resolution, high frame rate (HFR) videos across the Internet nearly instantaneously. Being able to monitor and control the quality of these streamed videos can enable the delivery of more enjoyable content and perceptually optimized rate control. Accordingly, there is a pressing need to develop VQA models that can be deployed at enormous scales. While some recent effects have been applied to full-reference (FR) analysis of variable frame rate and HFR video quality, the development of no-reference (NR) VQA algorithms targeting frame rate variations has been little studied. Here, we propose a first-of-a-kind blind VQA model for evaluating HFR videos, which we dub the Framerate-Aware Video Evaluator w/o Reference (FAVER). FAVER uses extended models of spatial natural scene statistics that encompass space-time wavelet-decomposed video signals, to conduct efficient frame rate sensitive quality prediction. Our extensive experiments on several HFR video quality datasets show that FAVER outperforms other blind VQA algorithms at a reasonable computational cost. To facilitate reproducible research and public evaluation, an implementation of FAVER is being made freely available online: \url{https://github.com/uniqzheng/HFR-BVQA}.
Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to have a bias on the limited vocabulary of the training set, which is called vocabulary reliance. In this paper, we propose a novel Visual-Semantic Decoupling Network (VSDN) to address the problem. Our VSDN contains a Visual Decoder (VD) and a Semantic Decoder (SD) to learn purer visual and semantic feature representation respectively. Besides, a Semantic Encoder (SE) is designed to match SD, which can be pre-trained together by additional inexpensive large vocabulary via a simple word correction task. Thus the semantic feature is more unbiased and precise to guide the visual feature alignment and enrich the final character representation. Experiments show that our method achieves state-of-the-art or competitive results on the standard benchmarks, and outperforms the popular baseline by a large margin under circumstances where the training set has a small size of vocabulary.
Aspect-based sentiment analysis (ABSA) is an emerging fine-grained sentiment analysis task that aims to extract aspects, classify corresponding sentiment polarities and find opinions as the causes of sentiment. The latest research tends to solve the ABSA task in a unified way with end-to-end frameworks. Yet, these frameworks get fine-tuned from downstream tasks without any task-adaptive modification. Specifically, they do not use task-related knowledge well or explicitly model relations between aspect and opinion terms, hindering them from better performance. In this paper, we propose SentiPrompt to use sentiment knowledge enhanced prompts to tune the language model in the unified framework. We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets. Experimental results demonstrate that our approach can outperform strong baselines on Triplet Extraction, Pair Extraction, and Aspect Term Extraction with Sentiment Classification by a notable margin.
With the availability of high dimensional genetic biomarkers, it is of interest to identify heterogeneous effects of these predictors on patients' survival, along with proper statistical inference. Censored quantile regression has emerged as a powerful tool for detecting heterogeneous effects of covariates on survival outcomes. To our knowledge, there is little work available to draw inference on the effects of high dimensional predictors for censored quantile regression. This paper proposes a novel procedure to draw inference on all predictors within the framework of global censored quantile regression, which investigates covariate-response associations over an interval of quantile levels, instead of a few discrete values. The proposed estimator combines a sequence of low dimensional model estimates that are based on multi-sample splittings and variable selection. We show that, under some regularity conditions, the estimator is consistent and asymptotically follows a Gaussian process indexed by the quantile level. Simulation studies indicate that our procedure can properly quantify the uncertainty of the estimates in high dimensional settings. We apply our method to analyze the heterogeneous effects of SNPs residing in lung cancer pathways on patients' survival, using the Boston Lung Cancer Survival Cohort, a cancer epidemiology study on the molecular mechanism of lung cancer.
One of the most commonly performed manipulation in a human's daily life is pouring. Many factors have an effect on target accuracy, including pouring velocity, rotation angle, geometric of the source, and the receiving containers. This paper presents an approach to increase the repeatability and accuracy of the robotic manipulator by estimating the change in the amount of water of the pouring cup to a sequence of pouring actions using multiple layers of the deep recurrent neural network, especially gated recurrent units (GRU). The proposed GRU model achieved a validation mean squared error as low as 1e-4 (lbf) for the predicted value of weight f(t). This paper contains a comprehensive evaluation and analysis of numerous experiments with various designs of recurrent neural networks and hyperparameters fine-tuning.
Automated cooking machine is a goal for the future. The main aim is to make the cooking process easier, safer, and create human welfare. To allow robots to accurately perform the cooking activities, it is important for them to understand the cooking environment and recognize the objects, especially correctly identifying the state of the cooking objects. This will significantly improve the correctness of the following cooking recipes. In this project, several parts of the experiment were conducted to design a robust deep convolutional neural network for classifying the state of the cooking objects from scratch. The model is evaluated by using various techniques, such as adjusting architecture layers, tuning key hyperparameters, and using different optimization techniques to maximize the accuracy of state classification.
This paper targets the task of language-based moment localization. The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, and then match them with the given query to determine the target moment. However, candidate moments generated with a fixed temporal granularity may be suboptimal to handle the large variation in moment lengths. To this end, we propose a novel multi-stage Progressive Localization Network (PLN) which progressively localizes the target moment in a coarse-to-fine manner. Specifically, each stage of PLN has a localization branch, and focuses on candidate moments that are generated with a specific temporal granularity. The temporal granularities of candidate moments are different across the stages. Moreover, we devise a conditional feature manipulation module and an upsampling connection to bridge the multiple localization branches. In this fashion, the later stages are able to absorb the previously learned information, thus facilitating the more fine-grained localization. Extensive experiments on three public datasets demonstrate the effectiveness of our proposed PLN for language-based moment localization and its potential for localizing short moments in long videos.
Low-Rank Matrix Recovery (LRMR) has recently been applied to saliency detection by decomposing image features into a low-rank component associated with background and a sparse component associated with visual salient regions. Despite its great potential, existing LRMR-based saliency detection methods seldom consider the inter-relationship among elements within these two components, thus are prone to generating scattered or incomplete saliency maps. In this paper, we introduce a novel and efficient LRMR-based saliency detection model under a coarse-to-fine framework to circumvent this limitation. First, we roughly measure the saliency of image regions with a baseline LRMR model that integrates a $\ell_1$-norm sparsity constraint and a Laplacian regularization smooth term. Given samples from the coarse saliency map, we then learn a projection that maps image features to refined saliency values, to significantly sharpen the object boundaries and to preserve the object entirety. We evaluate our framework against existing LRMR based methods on three benchmark datasets. Experimental results validate the superiority of our method as well as the effectiveness of our suggested coarse-to-fine framework, especially for images containing multiple objects.