Related papers: Understanding Synonymous Referring Expressions via…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction…

Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of…

Although transformer-based models have shown strong performance in word- and sentence-level tasks, effectively representing long documents, especially in fields like law and medicine, remains difficult. Sparse attention mechanisms can…

Image-text matching aims to build correspondences between visual and textual data by learning their pairwise similarities. Most existing approaches have adopted sparse binary supervision, indicating whether a pair of images and sentences…

We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i.e., referring expression. Previous works divide this problem into two…

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…

The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a representation for each word as a function of words and…

As pre-trained text-to-image diffusion models have become a useful tool for image synthesis, people want to specify the results in various ways. This paper tackles training-free appearance transfer, which produces an image with the…

Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead to performance…

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…

Object counting has progressed from class-specific models, which count only known categories, to class-agnostic models that generalize to unseen categories. The next challenge is Referring Expression Counting (REC), where the goal is to…

Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method…

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…