Related papers: SVTRv2: CTC Beats Encoder-Decoder Models in Scene …

Recognition of text on word or line images, without the need for sub-word segmentation has become the mainstream of research and development of text recognition for Indian languages. Modelling unsegmented sequences using Connectionist…

With the rapid growth of video data, Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval and is receiving increasing attention from researchers. Unlike unimodal video retrieval methods, the CVR task takes a…

Scene text recognition (STR) is an important bridge between images and text, attracting abundant research attention. While convolutional neural networks (CNNS) have achieved remarkable progress in this task, most of the existing works need…

Scaling architectures have been proven effective for improving Scene Text Recognition (STR), but the individual contribution of vision encoder and text decoder scaling remain under-explored. In this work, we present an in-depth empirical…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few…

Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models still struggle in other areas, such as personalization towards…

We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that…

Click-Through Rate (CTR) prediction holds a pivotal place in online advertising and recommender systems since CTR prediction performance directly influences the overall satisfaction of the users and the revenue generated by companies. Even…

Scene text recognition models have advanced greatly in recent years. Inspired by human reading we characterize two important scene text recognition models by measuring their domains i.e. the range of stimulus images that they can read. The…

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech…

Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors…

Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global…

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…

Chinese scene text retrieval is a practical task that aims to search for images containing visual instances of a Chinese query text. This task is extremely challenging because Chinese text often features complex and diverse layouts in…

Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modification of the ASR model or the beam-search decoding algorithm,…

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…

Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel…

Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into…

Camera-based 3D semantic scene completion (SSC) is pivotal for predicting complicated 3D layouts with limited 2D image observations. The existing mainstream solutions generally leverage temporal information by roughly stacking history…