Scene graph generation is conventionally evaluated by (mean) Recall@K, w...
A lifespan face synthesis (LFS) model aims to generate a set of
photo-re...
Dynamic scene graph generation aims at generating a scene graph of the g...
A text to image generation (T2I) model aims to generate photo-realistic
...
A layout to image (L2I) generation model aims to generate a complicated ...
To accurately predict future positions of different agents in traffic
sc...
Trajectory prediction is a crucial task in different communities, such a...
State-of-the-art object detection approaches such as Fast/Faster R-CNN, ...
Automatic captioning of images is a task that combines the challenges of...
In this paper, we propose FairNN a neural network that performs joint fe...
Semantic image understanding is a challenging topic in computer vision. ...
Scene graph construction / visual relationship detection from an image a...
With rapidly increasing deployment of surveillance cameras, the reliable...
In this paper, we propose an unsupervised video object co-segmentation
f...
In this paper, we present an unsupervised learning framework for analyzi...
In recent years, person re-identification (re-id) catches great attentio...
The detection of vehicles in aerial images is widely applied in many
app...
Reasoning about the relationships between object pairs in images is a cr...
Scene understanding is a popular and challenging topic in both computer
...