Handwritten mathematical expression recognition aims to automatically generate LaTeX sequences from given images. Currently, attention-based encoder-decoder models are widely used in this task. They typically generate target sequences in a left-to-right (L2R) manner, leaving the right-to-left (R2L) contexts unexploited. In this paper, we propose an Attention aggregation based Bi-directional Mutual learning Network (ABM) which consists of one shared encoder and two parallel inverse decoders (L2R and R2L). The two decoders are enhanced via mutual distillation, which involves one-to-one knowledge transfer at each training step, making full use of the complementary information from two inverse directions. Moreover, in order to deal with mathematical symbols in diverse scales, an Attention Aggregation Module (AAM) is proposed to effectively integrate multi-scale coverage attentions. Notably, in the inference phase, given that the model already learns knowledge from two inverse directions, we only use the L2R branch for inference, keeping the original parameter size and inference speed. Extensive experiments demonstrate that our proposed approach achieves the recognition accuracy of 56.85 % on CROHME 2014, 52.92 % on CROHME 2016, and 53.96 % on CROHME 2019 without data augmentation and model ensembling, substantially outperforming the state-of-the-art methods. The source code is available in https://github.com/XH-B/ABM.
With the advent of Transformer, which was used in translation models in 2017, attention-based architectures began to attract attention. Furthermore, after the emergence of BERT, which strengthened the NLU-specific encoder part, which is a part of the Transformer, and the GPT architecture, which strengthened the NLG-specific decoder part, various methodologies, data, and models for learning the Pretrained Language Model began to appear. Furthermore, in the past three years, various Pretrained Language Models specialized for Korean have appeared. In this paper, we intend to numerically and qualitatively compare and analyze various Korean PLMs released to the public.
Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or discretizing latent variables, this paper investigates how an increasing model expressiveness has benefits and impacts on the VAE-VC. Specifically, we first analyze VAE-VC from a rate-distortion perspective, and point out that model expressiveness is significant for VAE-VC because rate and distortion reflect similarity and naturalness of converted speeches. Based on the analysis, we propose a novel VC method using a deep hierarchical VAE, which has high model expressiveness as well as having fast conversion speed thanks to its non-autoregressive decoder. Also, our analysis reveals another problem that similarity can be degraded when the latent variable of VAEs has redundant information. We address the problem by controlling the information contained in the latent variable using $\beta$-VAE objective. In the experiment using VCTK corpus, the proposed method achieved mean opinion scores higher than 3.5 on both naturalness and similarity in inter-gender settings, which are higher than the scores of existing autoencoder-based VC methods.
Traffic forecasting is important in intelligent transportation systems of webs and beneficial to traffic safety, yet is very challenging because of the complex and dynamic spatio-temporal dependencies in real-world traffic systems. Prior methods use the pre-defined or learnable static graph to extract spatial correlations. However, the static graph-based methods fail to mine the evolution of the traffic network. Researchers subsequently generate the dynamic graph for each time slice to reflect the changes of spatial correlations, but they follow the paradigm of independently modeling spatio-temporal dependencies, ignoring the cross-time spatial influence. In this paper, we propose a novel cross-time dynamic graph-based deep learning model, named CDGNet, for traffic forecasting. The model is able to effectively capture the cross-time spatial dependence between each time slice and its historical time slices by utilizing the cross-time dynamic graph. Meanwhile, we design a gating mechanism to sparse the cross-time dynamic graph, which conforms to the sparse spatial correlations in the real world. Besides, we propose a novel encoder-decoder architecture to incorporate the cross-time dynamic graph-based GCN for multi-step traffic forecasting. Experimental results on three real-world public traffic datasets demonstrate that CDGNet outperforms the state-of-the-art baselines. We additionally provide a qualitative study to analyze the effectiveness of our architecture.
While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer in the typical encoder-decoder framework for image restoration, resulting from heavy self-attention computation load and inefficient communications across different depth (scales) of layers. In this paper, we present a deep and effective Transformer-based network for image restoration, termed as U2-Former, which is able to employ Transformer as the core operation to perform image restoration in a deep encoding and decoding space. Specifically, it leverages the nested U-shaped structure to facilitate the interactions across different layers with different scales of feature maps. Furthermore, we optimize the computational efficiency for the basic Transformer block by introducing a feature-filtering mechanism to compress the token representation. Apart from the typical supervision ways for image restoration, our U2-Former also performs contrastive learning in multiple aspects to further decouple the noise component from the background image. Extensive experiments on various image restoration tasks, including reflection removal, rain streak removal and dehazing respectively, demonstrate the effectiveness of the proposed U2-Former.
Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language ("cross-modal") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders, concurrent to the Transformer's overwhelming success in many other vision-language tasks. Adopting a different approach in this work, we show that significantly better cross-modal alignments can be achieved through the early fusion of linguistic and visual features in intermediate layers of a vision Transformer encoder network. By conducting cross-modal feature fusion in the visual feature encoding stage, we can leverage the well-proven correlation modeling power of a Transformer encoder for excavating helpful multi-modal context. This way, accurate segmentation results are readily harvested with a light-weight mask predictor. Without bells and whistles, our method surpasses the previous state-of-the-art methods on RefCOCO, RefCOCO+, and G-Ref by large margins.
Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face synthesis. In this work, we investigated how face masks can help the training of VAEs for face reconstruction, by restricting the learning to the pixels selected by the face mask. An evaluation of the proposal using the celebA dataset shows that the reconstructed images are enhanced with the face masks, especially when SSIM loss is used either with l1 or l2 loss functions. We noticed that the inclusion of a decoder for face mask prediction in the architecture affected the performance for l1 or l2 loss functions, while this was not the case for the SSIM loss. Besides, SSIM perceptual loss yielded the crispest samples between all hypotheses tested, although it shifts the original color of the image, making the usage of the l1 or l2 losses together with SSIM helpful to solve this issue.
Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn. Creative sketch image generation is a challenging vision problem, where the task is to generate diverse, yet realistic creative sketches possessing the unseen composition of the visual-world objects. Here, we propose a novel coarse-to-fine two-stage framework, DoodleFormer, that decomposes the creative sketch generation problem into the creation of coarse sketch composition followed by the incorporation of fine-details in the sketch. We introduce graph-aware transformer encoders that effectively capture global dynamic as well as local static structural relations among different body parts. To ensure diversity of the generated creative sketches, we introduce a probabilistic coarse sketch decoder that explicitly models the variations of each sketch body part to be drawn. Experiments are performed on two creative sketch datasets: Creative Birds and Creative Creatures. Our qualitative, quantitative and human-based evaluations show that DoodleFormer outperforms the state-of-the-art on both datasets, yielding realistic and diverse creative sketches. On Creative Creatures, DoodleFormer achieves an absolute gain of 25 in terms of Fr`echet inception distance (FID) over the state-of-the-art. We also demonstrate the effectiveness of DoodleFormer for related applications of text to creative sketch generation and sketch completion.
Most of the existing bi-modal (RGB-D and RGB-T) salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cross-modal information integration. The inherent local connectivity of the convolution operation constrains the performance of the convolution-based methods to a ceiling. In this work, we rethink these tasks from the perspective of global information alignment and transformation. Specifically, the proposed \underline{c}ross-mod\underline{a}l \underline{v}iew-mixed transform\underline{er} (CAVER) cascades several cross-modal integration units to construct a top-down transformer-based information propagation path. CAVER treats the multi-scale and multi-modal feature integration as a sequence-to-sequence context propagation and update process built on a novel view-mixed attention mechanism. Besides, considering the quadratic complexity w.r.t. the number of input tokens, we design a parameter-free patch-wise token re-embedding strategy to simplify operations. Extensive experimental results on RGB-D and RGB-T SOD datasets demonstrate that such a simple two-stream encoder-decoder framework can surpass recent state-of-the-art methods when it is equipped with the proposed components. Code and pretrained models will be available at \href{https://github.com/lartpang/CAVER}{the link}.
Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at https://github.com/WangTaoAs/PFD_Net
Recently, data-driven inertial navigation approaches have demonstrated their capability of using well-trained neural networks to obtain accurate position estimates from inertial measurement units (IMU) measurements. In this paper, we propose a novel robust Contextual Transformer-based network for Inertial Navigation~(CTIN) to accurately predict velocity and trajectory. To this end, we first design a ResNet-based encoder enhanced by local and global multi-head self-attention to capture spatial contextual information from IMU measurements. Then we fuse these spatial representations with temporal knowledge by leveraging multi-head attention in the Transformer decoder. Finally, multi-task learning with uncertainty reduction is leveraged to improve learning efficiency and prediction accuracy of velocity and trajectory. Through extensive experiments over a wide range of inertial datasets~(e.g. RIDI, OxIOD, RoNIN, IDOL, and our own), CTIN is very robust and outperforms state-of-the-art models.
In the computer vision community, great progresses have been achieved in salient object detection from natural scene images (NSI-SOD); by contrast, salient object detection in optical remote sensing images (RSI-SOD) remains to be a challenging emerging topic. The unique characteristics of optical RSIs, such as scales, illuminations and imaging orientations, bring significant differences between NSI-SOD and RSI-SOD. In this paper, we propose a novel Multi-Content Complementation Network (MCCNet) to explore the complementarity of multiple content for RSI-SOD. Specifically, MCCNet is based on the general encoder-decoder architecture, and contains a novel key component named Multi-Content Complementation Module (MCCM), which bridges the encoder and the decoder. In MCCM, we consider multiple types of features that are critical to RSI-SOD, including foreground features, edge features, background features, and global image-level features, and exploit the content complementarity between them to highlight salient regions over various scales in RSI features through the attention mechanism. Besides, we comprehensively introduce pixel-level, map-level and metric-aware losses in the training phase. Extensive experiments on two popular datasets demonstrate that the proposed MCCNet outperforms 23 state-of-the-art methods, including both NSI-SOD and RSI-SOD methods. The code and results of our method are available at https://github.com/MathLee/MCCNet.
We propose a new information aggregation method which called Localized Feature Aggregation Module based on the similarity between the feature maps of an encoder and a decoder. The proposed method recovers positional information by emphasizing the similarity between decoder's feature maps with superior semantic information and encoder's feature maps with superior positional information. The proposed method can learn positional information more efficiently than conventional concatenation in the U-net and attention U-net. Additionally, the proposed method also uses localized attention range to reduce the computational cost. Two innovations contributed to improve the segmentation accuracy with lower computational cost. By experiments on the Drosophila cell image dataset and COVID-19 image dataset, we confirmed that our method outperformed conventional methods.
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descriptions shared between different classes, which act as strong priors for localizing object attributes that represent discriminative region features, enabling significant visual-semantic interaction. Although some attention-based models have attempted to learn such region features in a single image, the transferability and discriminative attribute localization of visual features are typically neglected. In this paper, we propose an attribute-guided Transformer network, termed TransZero, to refine visual features and learn attribute localization for discriminative visual embedding representations in ZSL. Specifically, TransZero takes a feature augmentation encoder to alleviate the cross-dataset bias between ImageNet and ZSL benchmarks, and improves the transferability of visual features by reducing the entangled relative geometry relationships among region features. To learn locality-augmented visual features, TransZero employs a visual-semantic decoder to localize the image regions most relevant to each attribute in a given image, under the guidance of semantic attribute information. Then, the locality-augmented visual features and semantic vectors are used to conduct effective visual-semantic interaction in a visual-semantic embedding network. Extensive experiments show that TransZero achieves the new state of the art on three ZSL benchmarks. The codes are available at: \url{https://github.com/shiming-chen/TransZero}.
Meme is an interesting word. Internet memes offer unique insights into the changes in our perception of the world, the media and our own lives. If you surf the Internet for long enough, you will see it somewhere on the Internet. With the rise of social media platforms and convenient image dissemination, Image Meme has gained fame. Image memes have become a kind of pop culture and they play an important role in communication over social media, blogs, and open messages. With the development of artificial intelligence and the widespread use of deep learning, Natural Language Processing (NLP) and Computer Vision (CV) can also be used to solve more problems in life, including meme generation. An Internet meme commonly takes the form of an image and is created by combining a meme template (image) and a caption (natural language sentence). In our project, we propose an end-to-end encoder-decoder architecture meme generator. For a given input sentence, we use the Meme template selection model to determine the emotion it expresses and select the image template. Then generate captions and memes through to the meme caption generator. Code and models are available at github
Machine-generated citation sentences can aid automated scientific literature review and assist article writing. Current methods in generating citation text were limited to single citation generation using the citing document and a cited document as input. However, in real-world situations, writers often summarize several studies in one sentence or discuss relevant information across the entire paragraph. In addition, multiple citation intents have been previously identified, implying that writers may need control over the intents of generated sentences to cover different scenarios. Therefore, this work focuses on generating multiple citations and releasing a newly collected dataset named CiteMI to drive the future research. We first build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs. Second, we incorporate the predicted citation intents into training for intent control. The experiments demonstrate that the proposed approaches provide much more comprehensive features for generating citation sentences.
Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent solution from the perspective of contrastive learning, which is a natural extension of previous works. We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture. CO2Sum applies contrastive learning on the encoder, which can help the model be aware of the factual information contained in the input article, or performs contrastive learning on the decoder, which makes the model to generate factual-correct output summary. What's more, these two schemes are orthogonal and can be combined to further improve faithfulness. Comprehensive experiments on public benchmarks demonstrate that CO2Sum improves the faithfulness on large pre-trained language models and reaches competitive results compared to other strong factual-consistent summarization baselines.
Traditionally, video conferencing is a widely adopted solution for telecommunication, but a lack of immersiveness comes inherently due to the 2D nature of facial representation. The integration of Virtual Reality (VR) in a communication/telepresence system through Head Mounted Displays (HMDs) promises to provide users a much better immersive experience. However, HMDs cause hindrance by blocking the facial appearance and expressions of the user. To overcome these issues, we propose a novel attention-enabled encoder-decoder architecture for HMD de-occlusion. We also propose to train our person-specific model using short videos (1-2 minutes) of the user, captured in varying appearances, and demonstrated generalization to unseen poses and appearances of the user. We report superior qualitative and quantitative results over state-of-the-art methods. We also present applications of this approach to hybrid video teleconferencing using existing animation and 3D face reconstruction pipelines.
In this paper, we investigate a novel and challenging task, namely controllable video captioning with an exemplar sentence. Formally, given a video and a syntactically valid exemplar sentence, the task aims to generate one caption which not only describes the semantic contents of the video, but also follows the syntactic form of the given exemplar sentence. In order to tackle such an exemplar-based video captioning task, we propose a novel Syntax Modulated Caption Generator (SMCG) incorporated in an encoder-decoder-reconstructor architecture. The proposed SMCG takes video semantic representation as an input, and conditionally modulates the gates and cells of long short-term memory network with respect to the encoded syntactic information of the given exemplar sentence. Therefore, SMCG is able to control the states for word prediction and achieve the syntax customized caption generation. We conduct experiments by collecting auxiliary exemplar sentences for two public video captioning datasets. Extensive experimental results demonstrate the effectiveness of our approach on generating syntax controllable and semantic preserved video captions. By providing different exemplar sentences, our approach is capable of producing different captions with various syntactic structures, thus indicating a promising way to strengthen the diversity of video captioning.
Enhancing the diversity of sentences to describe video contents is an important problem arising in recent video captioning research. In this paper, we explore this problem from a novel perspective of customizing video captions by imitating exemplar sentence syntaxes. Specifically, given a video and any syntax-valid exemplar sentence, we introduce a new task of Syntax Customized Video Captioning (SCVC) aiming to generate one caption which not only semantically describes the video contents but also syntactically imitates the given exemplar sentence. To tackle the SCVC task, we propose a novel video captioning model, where a hierarchical sentence syntax encoder is firstly designed to extract the syntactic structure of the exemplar sentence, then a syntax conditioned caption decoder is devised to generate the syntactically structured caption expressing video semantics. As there is no available syntax customized groundtruth video captions, we tackle such a challenge by proposing a new training strategy, which leverages the traditional pairwise video captioning data and our collected exemplar sentences to accomplish the model learning. Extensive experiments, in terms of semantic, syntactic, fluency, and diversity evaluations, clearly demonstrate our model capability to generate syntax-varied and semantics-coherent video captions that well imitate different exemplar sentences with enriched diversities.