Automatically characterizing places with opportunistic crowdsensing using smartphones
Automated and scalable approaches for understanding the semantics of places are critical
to improving both existing and emerging mobile services. In this paper, we present …
to improving both existing and emerging mobile services. In this paper, we present …
Understanding the coverage and scalability of place-centric crowdsensing
Crowd-enabled place-centric systems gather and reason over large mobile sensor datasets
and target everyday user locations (such as stores, workplaces, and restaurants). Such …
and target everyday user locations (such as stores, workplaces, and restaurants). Such …
Modal contrastive learning based end-to-end text image machine translation
Text image machine translation (TIMT) aims at directly translating text in the source
language embedded in images into the target language. Most existing systems follow the …
language embedded in images into the target language. Most existing systems follow the …
Multi-teacher knowledge distillation for end-to-end text image machine translation
Text image machine translation (TIMT) has been widely used in various real-world
applications, which translates source language texts in images into another target language …
applications, which translates source language texts in images into another target language …
Translatotron-v (ison): An end-to-end model for in-image machine translation
In-image machine translation (IIMT) aims to translate an image containing texts in source
language into an image containing translations in target language. In this regard …
language into an image containing translations in target language. In this regard …
Layoutdit: Layout-aware end-to-end document image translation with multi-step conductive decoder
Document image translation (DIT) aims to translate text embedded in images from one
language to another. It is a challenging task that needs to understand visual layout with text …
language to another. It is a challenging task that needs to understand visual layout with text …
Improving end-to-end text image translation from the auxiliary text translation task
End-to-end text image translation (TIT), which aims at translating the source language
embedded in images to the target language, has attracted intensive attention in recent …
embedded in images to the target language, has attracted intensive attention in recent …
E2timt: Efficient and effective modal adapter for text image machine translation
Text image machine translation (TIMT) aims to translate texts embedded in images from one
source language to another target language. Existing methods, both two-stage cascade and …
source language to another target language. Existing methods, both two-stage cascade and …
CCIM: Cross-modal Cross-lingual Interactive Image Translation
Text image machine translation (TIMT) which translates source language text images into
target language texts has attracted intensive attention in recent years. Although the end-to …
target language texts has attracted intensive attention in recent years. Although the end-to …
Fast: Font-agnostic scene text editing
Abstract Scene Text Editing (STE) is a challenging research problem, and it aims to modify
existing texts in an image while preserving the background and the font style of the original …
existing texts in an image while preserving the background and the font style of the original …