Related papers: Cross-Enhancement Transformer for Action Segmentat…

Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are…

Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreover, the temporal scales of important information may vary…

Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the…

Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Evaluating lesion progression and treatment response via longitudinal lesion tracking plays a critical role in clinical practice. Automated approaches for this task are motivated by prohibitive labor costs and time consumption when lesion…

The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enormous number of parameters that must be trained (ranging from…

In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video. The presented Multiscale Encoder-Decoder Video Transformer (MED-VT) uses multiscale…

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of…

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level…

Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where self-attentions are…

Time series analysis faces significant challenges in handling variable-length data and achieving robust generalization. While Transformer-based models have advanced time series tasks, they often struggle with feature redundancy and limited…

Code-switching (CS) occurs when a speaker alternates words of two or more languages within a single sentence or across sentences. Automatic speech recognition (ASR) of CS speech has to deal with two or more languages at the same time. In…

As a cost-effective and robust technology, automotive radar has seen steady improvement during the last years, making it an appealing complement to commonly used sensors like camera and LiDAR in autonomous driving. Radio frequency data with…

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

The incredible success of transformers on sequence modeling tasks can be largely attributed to the self-attention mechanism, which allows information to be transferred between different parts of a sequence. Self-attention allows…

The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems. Historically, cross-domain co-clustering methods have successfully leveraged shared users…

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…

Transformer-based methods have shown great potential in long-term time series forecasting. However, most of these methods adopt the standard point-wise self-attention mechanism, which not only becomes intractable for long-term forecasting…