Related papers: Multi-modal Text Recognition Networks: Interactive…
Driven by deep learning and the large volume of data, scene text recognition has evolved rapidly in recent years. Formerly, RNN-attention based methods have dominated this field, but suffer from the problem of \textit{attention drift} in…
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…
Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity…
Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…
Text detection is frequently used in vision-based mobile robots when they need to interpret texts in their surroundings to perform a given task. For instance, delivery robots in multilingual cities need to be capable of doing multilingual…
Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…
Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…
Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent…
Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape.…
The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store scene properties in…
Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text provides explicit semantic information that can enhance anomaly characterization and…
Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…
Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the fine-grained cross-modal correspondence between image and…
Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework…
Many current state-of-the-art methods for text recognition are based on purely local information and ignore the semantic correlation between text and its surrounding visual context. In this paper, we propose a post-processing approach to…
Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…
Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often…
The existing image feature extraction methods are primarily based on the content and structure information of images, and rarely consider the contextual semantic information. Regarding some types of images such as scenes and objects, the…
Deep neural networks have achieved promising results in automatic image captioning due to their effective representation learning and context-based content generation capabilities. As a prominent type of deep features used in many of the…
Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level…