Time-to-Contact (TTC) estimation is a critical task for assessing collis...
Edge detection, as a core component in a wide range of visionoriented ta...
The reflection superposition phenomenon is complex and widely distribute...
Conversational recommendation systems (CRS) effectively address informat...
The recent improvement in code generation capabilities due to the use of...
Previous face inverse rendering methods often require synthetic data wit...
It has been observed in practice that applying pruning-at-initialization...
Developing deep generative models has been an emerging field due to the
...
Temporal action localization aims to predict the boundary and category o...
Video object detection (VID) is challenging because of the high variatio...
Designing and generating new data under targeted properties has been
att...
In this work, we propose PolarBEV for vision-based uneven BEV representa...
Automatic product description generation for e-commerce has witnessed
si...
Spatiotemporal graph represents a crucial data structure where the nodes...
Designing molecules with specific properties is a long-lasting research
...
Periodic graphs are graphs consisting of repetitive local structures, su...
Graph Structure Learning (GSL) recently has attracted considerable atten...
In the past decade, automatic product description generation for e-comme...
Images captured in low-light environment often suffer from complex
degra...
Single image reflection separation (SIRS), as a representative blind sou...
Deep learning has become the dominant approach in coping with various ta...
Graphs are important data representations for describing objects and the...
Disentangled representation learning has recently attracted a significan...
Much scientific enquiry across disciplines is founded upon a mechanistic...
Generalized from image and language translation, graph translation aims ...
It is challenging to inpaint face images in the wild, due to the large
v...
Image-to-image translation is to convert an image of the certain style t...
At present, object recognition studies are mostly conducted in a closed ...
Images captured under low-light conditions often suffer from (partially)...
We present a comprehensive study and evaluation of existing single image...
Being accurate, efficient, and compact is essential to a facial landmark...
Inspired by the tremendous success of deep generative models on generati...
Softmax loss is arguably one of the most popular losses to train CNN mod...
Rain effect in images typically is annoying for many multimedia and comp...
The blocking artifact frequently appears in compressed real-world images...