相关论文: Negative Entity Suppression for Zero-Shot Captioni…

Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for…

Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. Cross-lingual NER has been proposed to alleviate this issue by transferring knowledge from…

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content…

Zero-shot multi-speaker TTS aims to synthesize speech with the voice of a chosen target speaker without any fine-tuning. Prevailing methods, however, encounter limitations at adapting to new speakers of out-of-domain settings, primarily due…

Vision-language alignment using chest X-rays and radiology reports has emerged as an advanced paradigm for zero-shot classification and grounding of chest X-ray findings. However, standard contrastive learning typically treats radiographs…

Image captioning is a longstanding problem in the field of computer vision and natural language processing. To date, researchers have produced impressive state-of-the-art performance in the age of deep learning. Most of these…

Named Entity Recognition (NER) is an important subtask of information extraction that seeks to locate and recognise named entities. Despite recent achievements, we still face limitations in correctly detecting and classifying entities,…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

The goal of unpaired image captioning (UIC) is to describe images without using image-caption pairs in the training phase. Although challenging, we except the task can be accomplished by leveraging a training set of images aligned with…

Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i.e., the gap between images' visual features (low-level) and labels' semantic features…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

Visual Semantic Embedding (VSE) aims to extract the semantics of images and their descriptions, and embed them into the same latent space for cross-modal information retrieval. Most existing VSE networks are trained by adopting a hard…

Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to…

Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Using only global image-class labels, weakly-supervised learning methods, such as class activation mapping, allow training CNNs to jointly classify an image, and locate regions of interest associated with the predicted class. However,…

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo supervision can side-step…

3D object detection aims to recover the 3D information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on the scale of labeled training data, yet it is costly to…

In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries. To this end, we formulate the task as a positive-unlabeled (PU) learning problem and accordingly propose a…

Zero-shot video captioning aims to generate sentences for describing videos without training the model on video-text pairs, which remains underexplored. Existing zero-shot image captioning methods typically adopt a text-only training…