In the modern financial industry system, the structure of products has b...
We propose MAMo, a novel memory and attention frame-work for monocular v...
We introduce OpenShape, a method for learning multi-modal joint
represen...
Inverse path tracing has recently been applied to joint material and lig...
The ubiquitous multi-camera setup on modern autonomous vehicles provides...
In this paper, we develop rotation-equivariant neural networks for 4D
pa...
We propose a novel data augmentation approach, DistractFlow, for trainin...
We present DejaVu, a novel framework which leverages conditional image
r...
Test-time adaptive (TTA) semantic segmentation adapts a source pre-train...
Generalizable 3D part segmentation is important but challenging in visio...
Bird's-eye-view (BEV) grid is a common representation for the perception...
This paper presents a novel framework to integrate both semantic and ins...
Machine learning methods have revolutionized the discovery process of ne...
While deeply supervised networks are common in recent literature, they
t...
In this paper, we propose a novel method, X-Distill, to improve the
self...
In this paper, we present a novel perceptual consistency perspective on ...
In video segmentation, generating temporally consistent results across f...
The ability to estimate the perceptual error between images is an import...