Most existing Visual Question Answering (VQA) systems tend to overly rely on language bias and hence fail to reason from the visual clue. To address this issue, we propose a novel Language-Prior Feedback (LPF) objective function, to re-balance the proportion of each answer's loss value in the total VQA loss. The LPF firstly calculates a modulating factor to determine the language bias using a question-only branch. Then, the LPF assigns a self-adaptive weight to each training sample in the training process. With this reweighting mechanism, the LPF ensures that the total VQA loss can be reshaped to a more balanced form. By this means, the samples that require certain visual information to predict will be efficiently used during training. Our method is simple to implement, model-agnostic, and end-to-end trainable. We conduct extensive experiments and the results show that the LPF (1) brings a significant improvement over various VQA models, (2) achieves competitive performance on the bias-sensitive VQA-CP v2 benchmark.
Despite great progress in video-based 3D human pose estimation, it is still challenging to learn a discriminative single-pose representation from redundant sequences. To this end, we propose a novel Transformer-based architecture, called Lifting Transformer, for 3D human pose estimation to lift a sequence of 2D joint locations to a 3D pose. Specifically, a vanilla Transformer encoder (VTE) is adopted to model long-range dependencies of 2D pose sequences. To reduce redundancy of the sequence and aggregate information from local context, fully-connected layers in the feed-forward network of VTE are replaced with strided convolutions to progressively reduce the sequence length. The modified VTE is termed as strided Transformer encoder (STE) and it is built upon the outputs of VTE. STE not only significantly reduces the computation cost but also effectively aggregates information to a single-vector representation in a global and local fashion. Moreover, a full-to-single supervision scheme is employed at both the full sequence scale and single target frame scale, applying to the outputs of VTE and STE, respectively. This scheme imposes extra temporal smoothness constraints in conjunction with the single target frame supervision. The proposed architecture is evaluated on two challenging benchmark datasets, namely, Human3.6M and HumanEva-I, and achieves state-of-the-art results with much fewer parameters.
In the classroom environment, search tools are the means for students to access Web resources. The perspectives of students, researchers, and industry practitioners lead the ongoing research debate in this area. In this article, we argue in favor of incorporating a new voice into this debate: teachers. We showcase the value of involving teachers in all aspects related to the design of search tools for the classroom; from the beginning till the end. Driven by our research experience designing, developing, and evaluating new tools to support children's information discovery in the classroom, we share insights on the role of the experts-in-the-loop, i.e., teachers who provide the connection between search tools and students. And yes, in our case, always involving a teacher as a research partner.
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper, we ask several questions: What contexts do human translators use to resolve ambiguous words? Are models paying large amounts of attention to the same context? What if we explicitly train them to do so? To answer these questions, we introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context words for 14K translations that professional translators found useful for pronoun disambiguation. Using SCAT, we perform an in-depth analysis of the context used to disambiguate, examining positional and lexical characteristics of the supporting words. Furthermore, we measure the degree of alignment between the model's attention scores and the supporting context from SCAT, and apply a guided attention strategy to encourage agreement between the two.
Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories of fine-grained GZSL methods. The global feature exploring EL or FS methods do not explore fine distinction as they ignore local details. And, the local detail exploring EL or FS methods either neglect direct attribute guidance or global information. Consequently, neither method performs well. In this paper, we propose to explore global and direct attribute-supervised local visual features for both EL and FS categories in an integrated manner for fine-grained GZSL. The proposed integrated network has an EL sub-network and a FS sub-network. Consequently, the proposed integrated network can be tested in two ways. We propose a novel two-step dense attention mechanism to discover attribute-guided local visual features. We introduce new mutual learning between the sub-networks to exploit mutually beneficial information for optimization. Moreover, to reduce bias towards the source domain during testing, we propose to compute source-target class similarity based on mutual information and transfer-learn the target classes. We demonstrate that our proposed method outperforms contemporary methods on benchmark datasets.
Matrix completion has attracted a lot of attention in many fields including statistics, applied mathematics and electrical engineering. Most of works focus on the independent sampling models under which the individual observed entries are sampled independently. Motivated by applications in the integration of multiple (point-wise mutual information) PMI matrices, we propose the model {\bf B}lockwise missing {\bf E}mbedding {\bf L}earning {\bf T}ransformer (BELT) to treat row-wise/column-wise missingness. Specifically, our proposed method aims at efficient matrix recovery when every pair of matrices from multiple sources has an overlap. We provide theoretical justification for the proposed BELT method. Simulation studies show that the method performs well in finite sample under a variety of configurations. The method is applied to integrate several PMI matrices built by EHR data and Chinese medical text data, which enables us to construct a comprehensive embedding set for CUI and Chinese with high quality.
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large magnitude of perturbation noises but has minimal modification of image semantics, the former is critical to the effectiveness of its generated adversarial samples due to the existence of 'domain gaps'. Specifically, FAA decomposes images into multiple frequency components (FCs) and generates adversarial samples by just perturbating certain FCs that capture little semantic information. With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation. Extensive experiments over multiple domain adaptation tasks show that RDA can work with different computer vision tasks with superior performance.
We present a biologically inspired design for swarm foraging based on ant's pheromone deployment, where the swarm is assumed to have very restricted capabilities. The robots do not require global or relative position measurements and the swarm is fully decentralized and needs no infrastructure in place. Additionally, the system only requires one-hop communication over the robot network, we do not make any assumptions about the connectivity of the communication graph and the transmission of information and computation is scalable versus the number of agents. This is done by letting the agents in the swarm act as foragers or as guiding agents (beacons). We present experimental results computed for a swarm of Elisa-3 robots on a simulator, and show how the swarm self-organizes to solve a foraging problem over an unknown environment, converging to trajectories around the shortest path. At last, we discuss the limitations of such a system and propose how the foraging efficiency can be increased.
Late gadolinium enhancement magnetic resonance imaging (LGE MRI) is commonly used to visualize and quantify left atrial (LA) scars. The position and extent of scars provide important information of the pathophysiology and progression of atrial fibrillation (AF). Hence, LA scar segmentation and quantification from LGE MRI can be useful in computer-assisted diagnosis and treatment stratification of AF patients. Since manual delineation can be time-consuming and subject to intra- and inter-expert variability, automating this computing is highly desired, which nevertheless is still challenging and under-researched. This paper aims to provide a systematic review on computing methods for LA cavity, wall, scar and ablation gap segmentation and quantification from LGE MRI, and the related literature for AF studies. Specifically, we first summarize AF-related imaging techniques, particularly LGE MRI. Then, we review the methodologies of the four computing tasks in detail, and summarize the validation strategies applied in each task. Finally, the possible future developments are outlined, with a brief survey on the potential clinical applications of the aforementioned methods. The review shows that the research into this topic is still in early stages. Although several methods have been proposed, especially for LA segmentation, there is still large scope for further algorithmic developments due to performance issues related to the high variability of enhancement appearance and differences in image acquisition.
The interest in demographic information retrieval based on text data has increased in the research community because applications have shown success in different sectors such as security, marketing, heath-care, and others. Recognition and identification of demographic traits such as gender, age, location, or personality based on text data can help to improve different marketing strategies. For instance it makes it possible to segment and to personalize offers, thus products and services are exposed to the group of greatest interest. This type of technology has been discussed widely in documents from social media. However, the methods have been poorly studied in data with a more formal structure, where there is no access to emoticons, mentions, and other linguistic phenomena that are only present in social media. This paper proposes the use of recurrent and convolutional neural networks, and a transfer learning strategy for gender recognition in documents that are written in informal and formal languages. Models are tested in two different databases consisting of Tweets and call-center conversations. Accuracies of up to 75\% are achieved for both databases. The results also indicate that it is possible to transfer the knowledge from a system trained on a specific type of expressions or idioms such as those typically used in social media into a more formal type of text data, where the amount of data is more scarce and its structure is completely different.