Convolutional Neural Networks need the construction of informative features, which are determined by channel-wise and spatial-wise information at the network's layers. In this research, we focus on bringing in a novel solution that uses sophisticated optimization for enhancing both the spatial and channel components inside each layer's receptive field. Capsule Networks were used to understand the spatial association between features in the feature map. Standalone capsule networks have shown good results on comparatively simple datasets than on complex datasets as a result of the inordinate amount of feature information. Thus, to tackle this issue, we have proposed ME-CapsNet by introducing deeper convolutional layers to extract important features before passing through modules of capsule layers strategically to improve the performance of the network significantly. The deeper convolutional layer includes blocks of Squeeze-Excitation networks which use a stochastic sampling approach for progressively reducing the spatial size thereby dynamically recalibrating the channels by reconstructing their interdependencies without much loss of important feature information. Extensive experimentation was done using commonly used datasets demonstrating the efficiency of the proposed ME-CapsNet, which clearly outperforms various research works by achieving higher accuracy with minimal model complexity in complex datasets.
The choice of modeling units affects the performance of the acoustic modeling and plays an important role in automatic speech recognition (ASR). In mandarin scenarios, the Chinese characters represent meaning but are not directly related to the pronunciation. Thus only considering the writing of Chinese characters as modeling units is insufficient to capture speech features. In this paper, we present a novel method involves with multi-level modeling units, which integrates multi-level information for mandarin speech recognition. Specifically, the encoder block considers syllables as modeling units, and the decoder block deals with character modeling units. During inference, the input feature sequences are converted into syllable sequences by the encoder block and then converted into Chinese characters by the decoder block. This process is conducted by a unified end-to-end model without introducing additional conversion models. By introducing InterCE auxiliary task, our method achieves competitive results with CER of 4.1%/4.6% and 4.6%/5.2% on the widely used AISHELL-1 benchmark without a language model, using the Conformer and the Transformer backbones respectively.
As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. Our dataset represents a wider variety of image caption styles annotated by trained people from different backgrounds. We present a quantitative and qualitative analysis of the dataset and the baseline evaluation of the recent models in Bangla image captioning. We investigate the effect of text augmentation and demonstrate that an adaptive attention-based model combined with text augmentation using Contextualized Word Replacement (CWR) outperforms all state-of-the-art models for Bangla image captioning. We also present this dataset's multipurpose nature, especially on machine translation for Bangla-English and English-Bangla. This dataset and all the models will be useful for further research.
Deep-learning based techniques have contributed to the remarkable progress in the field of automatic image quality assessment (IQA). Existing IQA methods are designed to measure the quality of an image in terms of Mean Opinion Score (MOS) at the image-level (i.e. the whole image) or at the patch-level (dividing the image into multiple units and measuring quality of each patch). Some applications may require assessing the quality at the pixel-level (i.e. MOS value for each pixel), however, this is not possible in case of existing techniques as the spatial information is lost owing to their network structures. This paper proposes an IQA algorithm that can measure the MOS at the pixel-level, in addition to the image-level MOS. The proposed algorithm consists of three core parts, namely: i) Local IQA; ii) Region of Interest (ROI) prediction; iii) High-level feature embedding. The Local IQA part outputs the MOS at the pixel-level, or pixel-by-pixel MOS - we term it 'pMOS'. The ROI prediction part outputs weights that characterize the relative importance of region when calculating the image-level IQA. The high-level feature embedding part extracts high-level image features which are then embedded into the Local IQA part. In other words, the proposed algorithm yields three outputs: the pMOS which represents MOS for each pixel, the weights from the ROI indicating the relative importance of region, and finally the image-level MOS that is obtained by the weighted sum of pMOS and ROI values. The image-level MOS thus obtained by utilizing pMOS and ROI weights shows superior performance compared to the existing popular IQA techniques. In addition, visualization results indicate that predicted pMOS and ROI outputs are reasonably aligned with the general principles of the human visual system (HVS).
In this paper, we briefly introduce our submission to the Valence-Arousal Estimation Challenge of the 3rd Affective Behavior Analysis in-the-wild (ABAW) competition. Our method utilizes the multi-modal information, i.e., the visual and audio information, and employs a temporal encoder to model the temporal context in the videos. Besides, a smooth processor is applied to get more reasonable predictions, and a model ensemble strategy is used to improve the performance of our proposed method. The experiment results show that our method achieves 65.55% ccc for valence and 70.88% ccc for arousal on the validation set of the Aff-Wild2 dataset, which prove the effectiveness of our proposed method.
Video captioning is a challenging task that necessitates a thorough comprehension of visual scenes. Existing methods follow a typical one-to-one mapping, which concentrates on a limited sample space while ignoring the intrinsic semantic associations between samples, resulting in rigid and uninformative expressions. To address this issue, we propose a novel and flexible framework, namely Support-set based Multi-modal Representation Enhancement (SMRE) model, to mine rich information in a semantic subspace shared between samples. Specifically, we propose a Support-set Construction (SC) module to construct a support-set to learn underlying connections between samples and obtain semantic-related visual elements. During this process, we design a Semantic Space Transformation (SST) module to constrain relative distance and administrate multi-modal interactions in a self-supervised way. Extensive experiments on MSVD and MSR-VTT datasets demonstrate that our SMRE achieves state-of-the-art performance.
Subspace clustering is to find underlying low-dimensional subspaces and cluster the data points correctly. In this paper, we propose a novel multi-view subspace clustering method. Most existing methods suffer from two critical issues. First, they usually adopt a two-stage framework and isolate the processes of affinity learning, multi-view information fusion and clustering. Second, they assume the data lies in a linear subspace which may fail in practice as most real-world datasets may have non-linearity structures. To address the above issues, in this paper we propose a novel Enriched Robust Multi-View Kernel Subspace Clustering framework where the consensus affinity matrix is learned from both multi-view data and spectral clustering. Due to the objective and constraints which is difficult to optimize, we propose an iterative optimization method which is easy to implement and can yield closed solution in each step. Extensive experiments have validated the superiority of our method over state-of-the-art clustering methods.
Many important questions (e.g. "How to eat healthier?") require conversation to establish context and explore in depth. However, conversational question answering (ConvQA) systems have long been stymied by scarce training data that is expensive to collect. To address this problem, we propose a new technique for synthetically generating diverse and high-quality dialog data: dialog inpainting. Our approach takes the text of any document and transforms it into a two-person dialog between the writer and an imagined reader: we treat sentences from the article as utterances spoken by the writer, and then use a dialog inpainter to predict what the imagined reader asked or said in between each of the writer's utterances. By applying this approach to passages from Wikipedia and the web, we produce WikiDialog and WebDialog, two datasets totalling 19 million diverse information-seeking dialogs -- 1,000x larger than the largest existing ConvQA dataset. Furthermore, human raters judge the answer adequacy and conversationality of WikiDialog to be as good or better than existing manually-collected datasets. Using our inpainted data to pre-train ConvQA retrieval systems, we significantly advance state-of-the-art across three benchmarks (QReCC, OR-QuAC, TREC CAsT) yielding up to 40% relative gains on standard evaluation metrics.
Conversational search is a relatively young area of research that aims at automating an information-seeking dialogue. In this paper we help to position it with respect to other research areas within conversational Artificial Intelligence (AI) by analysing the structural properties of an information-seeking dialogue. To this end, we perform a large-scale dialogue analysis of more than 150K transcripts from 15 publicly available dialogue datasets. These datasets were collected to inform different dialogue-based tasks including conversational search. We extract different patterns of mixed initiative from these dialogue transcripts and use them to compare dialogues of different types. Moreover, we contrast the patterns found in information-seeking dialogues that are being used for research purposes with the patterns found in virtual reference interviews that were conducted by professional librarians. The insights we provide (1) establish close relations between conversational search and other conversational AI tasks; and (2) uncover limitations of existing conversational datasets to inform future data collection tasks.
Recent progress in deep model-based reinforcement learning allows agents to be significantly more sample efficient by constructing world models of high-dimensional environments from visual observations, which enables agents to learn complex behaviours in summarized lower-dimensional spaces. Reusing knowledge from relevant previous tasks is another approach for achieving better data-efficiency, which becomes especially more likely when information of multiple previously learned tasks is accessible. We show that the simplified representations of environments resulting from world models provide for promising transfer learning opportunities, by introducing several methods that facilitate world model agents to benefit from multi-source transfer learning. Methods are proposed for autonomously extracting relevant knowledge from both multi-task and multi-agent settings as multi-source origins, resulting in substantial performance improvements compared to learning from scratch. We introduce two additional novel techniques that enable and enhance the proposed approaches respectively: fractional transfer learning and universal feature spaces from a universal autoencoder. We demonstrate that our methods enable transfer learning from different domains with different state, reward, and action spaces by performing extensive and challenging multi-domain experiments on Dreamer, the state-of-the-art world model based algorithm for visual continuous control tasks.