相关论文: LocCa: Visual Pretraining with Location-aware Capt…

Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text descriptions. However, such an operation will cause a…

In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). Our approach employs the generated captions by a captioning model as the context of an answer…

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…

Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and…

Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition…

In current multimodal tasks, models typically freeze the encoder and decoder while adapting intermediate layers to task-specific goals, such as region captioning. Region-level visual understanding presents significant challenges for…

People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual…

We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths. FlexCap is trained to produce length-conditioned captions for input boxes, enabling control over information density, with…

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature…

From paired image-text training to text-only training for image captioning, the pursuit of relaxing the requirements for high-cost and large-scale annotation of good quality data remains consistent. In this paper, we propose Text-only…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of…

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…

Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger…

Place recognition is a critical and challenging task for mobile robots, aiming to retrieve an image captured at the same place as a query image from a database. Existing methods tend to fail while robots move autonomously under occlusion…

We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders -- a convolutional neural network trained to generate the contents of an…

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the…

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process. Without requiring any multilingual caption data, we propose LMCap, an…