Related papers: The macaque IT cortex but not current artificial v…

Based on the concept that ventral visual stream (VVS) mainly functions for object recognition, current unsupervised task-driven methods model VVS by contrastive learning, and have achieved good brain similarity. However, we believe…

Adversarial attacks of deep neural networks have been intensively studied on image, audio, natural language, patch, and pixel classification tasks. Nevertheless, as a typical, while important real-world application, the adversarial attacks…

Manipulating an articulated object requires perceiving itskinematic hierarchy: its parts, how each can move, and howthose motions are coupled. Previous work has explored per-ception for kinematics, but none infers a complete…

Articulated objects (e.g., doors and drawers) exist everywhere in our life. Different from rigid objects, articulated objects have higher degrees of freedom and are rich in geometries, semantics, and part functions. Modeling different kinds…

Visual Object tracking research has undergone significant improvement in the past few years. The emergence of tracking by detection approach in tracking paradigm has been quite successful in many ways. Recently, deep convolutional neural…

This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The…

A major goal of neuroscience is to understand brain computations during visual processing in naturalistic settings. A dominant approach is to use image-computable deep neural networks trained with different task objectives as a basis for…

Some visual search tasks require to memorize the location of stimuli that have been previously scanned. Considerations about the eye movements raise the question of how we are able to maintain a coherent memory, despite the frequent…

Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…

Broader access to high-quality movement analysis could greatly benefit movement science and rehabilitation, such as allowing more detailed characterization of movement impairments and responses to interventions, or even enabling early…

Object pose estimation is an integral part of robot vision and AR. Previous 6D pose retrieval pipelines treat the problem either as a regression task or discretize the pose space to classify. We change this paradigm and reformulate the…

Objective. Decoding visual attention from brain signals during naturalistic video viewing has emerged as a new direction in brain-computer interface research. Current methods assume that stronger coupling between object motion and neural…

We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interacting pathways: identity and control, intended to mirror the…

Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…

Human motion prediction, i.e., forecasting future body poses given observed pose sequence, has typically been tackled with recurrent neural networks (RNNs). However, as evidenced by prior work, the resulted RNN models suffer from prediction…

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through…

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

The human visual system has a hierarchical structure consisting of layers of processing, such as the retina, V1, V2, etc. Understanding the functional roles of these visual processing layers would help to integrate the psychophysiological…

Computational neuroscience studies that have examined human visual system through functional magnetic resonance imaging (fMRI) have identified a model where the mammalian brain pursues two distinct pathways (for recognition of biological…

Interactive applications demand believable characters that respond naturally to dynamic environments. Traditional character animation techniques often struggle to handle arbitrary situations, leading to a growing trend of dynamically…