Related papers: Do vision models perceive illusory motion in stati…
The primate visual system achieves remarkable visual object recognition performance even in brief presentations and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object…
Various research studies indicate that action recognition performance highly depends on the types of motions being extracted and how accurate the human actions are represented. In this paper, we investigate different optical flow, and…
Animals are known to make efficient probabilistic inferences based on uncertain and noisy information from the outside world. Although it is known that generic neural networks can perform near-optimal point estimation by probabilistic…
Deep neural networks (DNNs) show promise in image-based medical diagnosis, but cannot be fully trusted since their performance can be severely degraded by dataset shifts to which human perception remains invariant. If we can better…
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…
Adversarial examples have shown that albeit highly accurate, models learned by machines, differently from humans, have many weaknesses. However, humans' perception is also fundamentally different from machines, because we do not see the…
We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-point-inspired iterative approach to invert real-world images,…
Monocular depth estimation is a fundamental capability for real-world applications such as autonomous driving and robotics. Although deep neural networks (DNNs) have achieved superhuman accuracy on physical-based benchmarks, a key challenge…
Deep convolutional neural networks (DCNNs) have demonstrated excellent performance in object recognition and have been found to share some similarities with brain visual processing. However, the substantial gap between DCNNs and human…
Humans possess an exceptional ability to imagine 4D scenes, encompassing both motion and 3D geometry, from a single still image. This ability is rooted in our accumulated observations of similar scenes and an intuitive understanding of…
Even during fixation the human eye is constantly in low amplitude motion, jittering over small angles in random directions at up to 100Hz. This motion results in all features of the image on the retina constantly traversing a number of…
In this paper, we study the challenging problem of predicting the dynamics of objects in static images. Given a query object in an image, our goal is to provide a physical understanding of the object in terms of the forces acting upon it…
Why do moving objects appear rigid when projected retinal images are deformed nonrigidly? We used rotating rigid objects that can appear rigid or non-rigid to test whether shape features contribute to rigidity perception. When two circular…
The current state-of-the-art object recognition algorithms, deep convolutional neural networks (DCNNs), are inspired by the architecture of the mammalian visual system, and are capable of human-level performance on many tasks. However, even…
Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those depicted on point-light displays. While humans excel at…
Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the…
Visual intelligence requires anticipating the future behavior of agents, yet vision systems lack a general representation for motion and behavior. We propose dense point trajectories as visual tokens for behavior, a structured mid-level…
Deep neural networks (DNNs) transform stimuli across multiple processing stages to produce representations that can be used to solve complex tasks, such as object recognition in images. However, a full understanding of how they achieve this…
Recurrent neural networks (RNNs) trained on neuroscience-inspired tasks offer powerful models of brain computation. However, typical training paradigms rely on open-loop, supervised settings, whereas real-world learning unfolds in…
In recent years, deep neural networks (DNNs) achieved state-of-the-art performance on several computer vision tasks. However, the one typical drawback of these DNNs is the requirement of massive labeled data. Even though few-shot learning…