Related papers: Omni-Attribute: Open-vocabulary Attribute Encoder …
We consider visual domains in which a class label specifies the content of an image, and class-irrelevant properties that differentiate instances constitute the style. We present a domain-independent method that permits the open-ended…
Personalized vision-language retrieval seeks to recognize new concepts (e.g. "my dog Fido") from only a few examples. This task is challenging because it requires not only learning a new concept from a few images, but also integrating the…
Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector…
In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the…
While an image is worth more than a thousand words, only a few provide crucial information for a given task and thus should be focused on. In light of this, ideal text-to-image (T2I) retrievers should prioritize specific visual attributes…
In the realm of food computing, segmenting ingredients from images poses substantial challenges due to the large intra-class variance among the same ingredients, the emergence of new ingredients, and the high annotation costs associated…
Attributes possess appealing properties and benefit many computer vision problems, such as object recognition, learning with humans in the loop, and image retrieval. Whereas the existing work mainly pursues utilizing attributes for various…
Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…
Compositional generalization is a key facet of human cognition, but lacking in current AI tools such as vision-language models. Previous work examined whether a compositional tensor-based sentence semantics can overcome the challenge, but…
Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent…
Text-to-image diffusion techniques have shown exceptional capabilities in producing high-quality, dense visual predictions from open-vocabulary text. This indicates a strong correlation between visual and textual domains in open concepts…
Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts.…
Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several…
Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the…
The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…
While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion remains a significant challenge. Recent attempts to bridge this gap often suffer…
Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced,…
This is an opinion paper. We hope to deliver a key message that current visual recognition systems are far from complete, i.e., recognizing everything that human can recognize, yet it is very unlikely that the gap can be bridged by…
State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded…
We consider the problem of constraining diffusion model outputs with a user-supplied reference image. Our key objective is to extract multiple attributes (e.g., color, object, layout, style) from this single reference image, and then…