Related papers: Vision encoders should be image size agnostic and …
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…
Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep…
Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…
Vision transformers (ViTs) are top performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological…
Rapid categorization paradigms have a long history in experimental psychology: Characterized by short presentation times and speedy behavioral responses, these tasks highlight the efficiency with which our visual system processes natural…
Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack…
Motivated by theories of language and communication that explain why communities with large numbers of speakers have, on average, simpler languages with more regularity, we cast the representation learning problem in terms of learning to…
In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete…
Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passively process entire scenes at once, resulting in excessive…
This paper sustains the position that the time has come for thinking of learning machines that conquer visual skills in a truly human-like context, where a few human-like object supervisions are given by vocal interactions and pointing aids…
Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…
Over the last decade, Computer Vision, the branch of Artificial Intelligence aimed at understanding the visual world, has evolved from simply recognizing objects in images to describing pictures, answering questions about images, aiding…
Humans are continuously exposed to a stream of visual data with a natural temporal structure. However, most successful computer vision algorithms work at image level, completely discarding the precious information carried by motion. In this…
Video games have served as useful benchmarks for the decision-making community, but going beyond Atari games towards modern games has been prohibitively expensive for the vast majority of the research community. Prior work in modern video…
Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts…
Computer vision has received a significant attention in recent year, which is one of the important parts for robots to obtain information about the external environment. Visual trackers can provide the necessary physical and environmental…
Neural network (connectionist) models are designed to encode image features and provide the building blocks for object and shape recognition. These models generally call for: a) initial diffuse connections from one neuron population to…
Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When this occurs, they introduce a form of distribution shift at…
Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization…
Authors often transform a large screen visualization for smaller displays through rescaling, aggregation and other techniques when creating visualizations for both desktop and mobile devices (i.e., responsive visualization). However,…