A complete survey on generative ai (aigc): Is chatgpt from gpt-4 to gpt-5 all you need?
As ChatGPT goes viral, generative AI (AIGC, aka AI-generated content) has made headlines
everywhere because of its ability to analyze and create text, images, and beyond. With such …
everywhere because of its ability to analyze and create text, images, and beyond. With such …
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 …
Clipcap: Clip prefix for image captioning
Image captioning is a fundamental task in vision-language understanding, where the model
predicts a textual informative caption to a given input image. In this paper, we present a …
predicts a textual informative caption to a given input image. In this paper, we present a …
Multiscale vision transformers
Abstract We present Multiscale Vision Transformers (MViT) for video and image recognition,
by connecting the seminal idea of multiscale feature hierarchies with transformer models …
by connecting the seminal idea of multiscale feature hierarchies with transformer models …
Imagenet-21k pretraining for the masses
ImageNet-1K serves as the primary dataset for pretraining deep learning models for
computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used …
computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used …
Remote sensing image change detection with transformers
Modern change detection (CD) has achieved remarkable success by the powerful
discriminative ability of deep convolutions. However, high-resolution remote sensing CD …
discriminative ability of deep convolutions. However, high-resolution remote sensing CD …
Detclipv2: Scalable open-vocabulary object detection pre-training via word-region alignment
This paper presents DetCLIPv2, an efficient and scalable training framework that
incorporates large-scale image-text pairs to achieve open-vocabulary object detection …
incorporates large-scale image-text pairs to achieve open-vocabulary object detection …
Causal transformer for estimating counterfactual outcomes
V Melnychuk, D Frauen… - … Conference on Machine …, 2022 - proceedings.mlr.press
Estimating counterfactual outcomes over time from observational data is relevant for many
applications (eg, personalized medicine). Yet, state-of-the-art methods build upon simple …
applications (eg, personalized medicine). Yet, state-of-the-art methods build upon simple …
Reltr: Relation transformer for scene graph generation
Different objects in the same scene are more or less related to each other, but only a limited
number of these relationships are noteworthy. Inspired by Detection Transformer, which …
number of these relationships are noteworthy. Inspired by Detection Transformer, which …
Prior: Prototype representation joint learning from medical images and reports
Contrastive learning based vision-language joint pre-training has emerged as a successful
representation learning strategy. In this paper, we present a prototype representation …
representation learning strategy. In this paper, we present a prototype representation …