From show to tell: A survey on deep learning-based image captioning
Connecting Vision and Language plays an essential role in Generative Intelligence. For this
reason, large research efforts have been devoted to image captioning, ie describing images …
reason, large research efforts have been devoted to image captioning, ie describing images …
Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning
The milestone improvements brought about by deep representation learning and pre-
training techniques have led to large performance gains across downstream NLP, IR and …
training techniques have led to large performance gains across downstream NLP, IR and …
[HTML][HTML] AutoML: A systematic review on automated machine learning with neural architecture search
Abstract AutoML (Automated Machine Learning) is an emerging field that aims to automate
the process of building machine learning models. AutoML emerged to increase productivity …
the process of building machine learning models. AutoML emerged to increase productivity …
Chinese clip: Contrastive vision-language pretraining in chinese
The tremendous success of CLIP (Radford et al., 2021) has promoted the research and
application of contrastive learning for vision-language pretraining. In this work, we construct …
application of contrastive learning for vision-language pretraining. In this work, we construct …
Vatex: A large-scale, high-quality multilingual dataset for video-and-language research
We present a new large-scale multilingual video description dataset, VATEX, which contains
over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions …
over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions …
AI-empowered speed extraction via port-like videos for vehicular trajectory analysis
Automated container terminal (ACT) is considered as port industry development direction,
and accurate kinematic data (speed, volume, etc.) is essential for enhancing ACT operation …
and accurate kinematic data (speed, volume, etc.) is essential for enhancing ACT operation …
Visually grounded reasoning across languages and cultures
The design of widespread vision-and-language datasets and pre-trained encoders directly
adopts, or draws inspiration from, the concepts and images of ImageNet. While one can …
adopts, or draws inspiration from, the concepts and images of ImageNet. While one can …
Altclip: Altering the language encoder in clip for extended language capabilities
In this work, we present a conceptually simple and effective method to train a strong
bilingual/multilingual multimodal representation model. Starting from the pre-trained …
bilingual/multilingual multimodal representation model. Starting from the pre-trained …
X2-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
Vision language pre-training aims to learn alignments between vision and language from a
large amount of data. Most existing methods only learn image-text alignments. Some others …
large amount of data. Most existing methods only learn image-text alignments. Some others …
IGLUE: A benchmark for transfer learning across modalities, tasks, and languages
Reliable evaluation benchmarks designed for replicability and comprehensiveness have
driven progress in machine learning. Due to the lack of a multilingual benchmark, however …
driven progress in machine learning. Due to the lack of a multilingual benchmark, however …