Related papers: Learning Object Semantic Similarity with Self-Supe…
The recent successful deep neural networks are largely trained in a supervised manner. It {\it associates} complex patterns of input samples with neurons in the last layer, which form representations of {\it concepts}. In spite of their…
While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large…
We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich…
We present a meta-learning framework for learning new visual concepts quickly, from just one or a few examples, guided by multiple naturally occurring data streams: simultaneously looking at images, reading sentences that describe the…
Visual relationships capture a wide variety of interactions between pairs of objects in images (e.g. "man riding bicycle" and "man pushing bicycle"). Consequently, the set of possible relationships is extremely large and it is difficult to…
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters. Current works face the…
Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially…
As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…
The training methods in AI do involve semantically distinct pairs of samples. However, their role typically is to enhance the between class separability. The actual notion of similarity is normally learned from semantically identical pairs.…
Humans learn powerful representations of objects and scenes by observing how they evolve over time. Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for…
Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. These approaches align objects with language queries (e.g. "a photo of a cat") and improve the…
Merchandise categories inherently form a semantic hierarchy with different levels of concept abstraction, especially for fine-grained categories. This hierarchy encodes rich correlations among various categories across different levels,…
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…
This paper proposes a new methodology to automatically build semantic hierarchies suitable for image annotation and classification. The building of the hierarchy is based on a new measure of semantic similarity. The proposed measure…
Detecting semantic parts of an object is a challenging task in computer vision, particularly because it is hard to construct large annotated datasets due to the difficulty of annotating semantic parts. In this paper we present an approach…
Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained…
The ability to accurately predict the surrounding environment is a foundational principle of intelligence in biological and artificial agents. In recent years, a variety of approaches have been proposed for learning to predict the physical…
Establishing stable mappings between natural language expressions and visual percepts is a foundational problem for both cognitive science and artificial intelligence. Humans routinely ground linguistic reference in noisy, ambiguous…
The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'',…
This paper addresses the challenge of learning a local visual pattern of an object from one image, and generating images depicting objects with that pattern. Learning a localized concept and placing it on an object in a target image is a…