相关论文: Efficient and Accurate Scene Text Recognition with…

We present Tensor4D, an efficient yet effective approach to dynamic scene modeling. The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor.…

This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle…

Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. In this work we propose SCENE, a methodology to encode diverse traffic scenes in heterogeneous graphs and to…

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded…

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in…

Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method…

In this paper, we address the problem of having characters with different scales in scene text recognition. We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales.…

Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In multi-class density estimation, class awareness can be introduced by modelling classes…

We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature…

Scene text detection methods based on deep learning have achieved remarkable results over the past years. However, due to the high diversity and complexity of natural scenes, previous state-of-the-art text detection methods may still…

We propose replacing scene text in videos using deep style transfer and learned photometric transformations.Building on recent progress on still image text replacement,we present extensions that alter text while preserving the appearance…

We study the underexplored but fundamental vision problem of machine understanding of abstract freehand scene sketches. We introduce a sketch encoder that results in semantically-aware feature space, which we evaluate by testing its…

Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT)…

In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

An unconstrained end-to-end text localization and recognition method is presented. The method detects initial text hypothesis in a single pass by an efficient region-based method and subsequently refines the text hypothesis using a more…

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted…

Despite the potential of neural scene representations to effectively compress 3D scalar fields at high reconstruction quality, the computational complexity of the training and data reconstruction step using scene representation networks…