From show to tell: A survey on deep learning-based image captioning

M Stefanini, M Cornia, L Baraldi… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
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 …

Multimodal image synthesis and editing: A survey and taxonomy

F Zhan, Y Yu, R Wu, J Zhang, S Lu, L Liu… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

Dinov2: Learning robust visual features without supervision

M Oquab, T Darcet, T Moutakanni, H Vo… - arxiv preprint arxiv …, 2023 - arxiv.org
The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

Llama-adapter: Efficient fine-tuning of language models with zero-init attention

R Zhang, J Han, C Liu, P Gao, A Zhou, X Hu… - arxiv preprint arxiv …, 2023 - arxiv.org
We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA
into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter …

Scaling vision transformers to 22 billion parameters

M Dehghani, J Djolonga, B Mustafa… - International …, 2023 - proceedings.mlr.press
The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation

K Huang, K Sun, E **e, Z Li… - Advances in Neural …, 2023 - proceedings.neurips.cc
Despite the stunning ability to generate high-quality images by recent text-to-image models,
current approaches often struggle to effectively compose objects with different attributes and …

Eva-clip: Improved training techniques for clip at scale

Q Sun, Y Fang, L Wu, X Wang, Y Cao - arxiv preprint arxiv:2303.15389, 2023 - arxiv.org
Contrastive language-image pre-training, CLIP for short, has gained increasing attention for
its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models …

Improving clip training with language rewrites

L Fan, D Krishnan, P Isola… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective
and scalable methods for training transferable vision models using paired image and text …

Vision-language models for vision tasks: A survey

J Zhang, J Huang, S **, S Lu - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

Eva-02: A visual representation for neon genesis

Y Fang, Q Sun, X Wang, T Huang, X Wang… - Image and Vision …, 2024 - Elsevier
We launch EVA-02, a next-generation Transformer-based visual representation pre-trained
to reconstruct strong and robust language-aligned vision features via masked image …