Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

In this work, we investigate the task of text-to-image (T2I) synthesis under the abstract-to-
intricate setting, ie, generating intricate visual content from simple abstract text prompts …

Recent state-of-the-art methods for HOI detection typically build on transformer architectures
with two decoder branches, one for human-object pair detection and the other for interaction …

Text-to-video (T2V) synthesis has gained increasing attention in the community, in which the
recently emerged diffusion models (DMs) have promisingly shown stronger performance …

Abstract 2D image understanding is a complex problem within computer vision, but it holds
the key to providing human-level scene comprehension. It goes further than identifying the …

Being able to understand visual scenes is a precursor for many downstream tasks including
autonomous driving robotics and other vision-based approaches. A common approach …

Abstract Text-to-video (T2V) synthesis has gained increasing attention in the community in
which the recently emerged diffusion models (DMs) have promisingly shown stronger …

Existing Unbiased Scene Graph Generation (USGG) methods only focus on addressing the
predicate-level imbalance that high-frequency classes dominate predictions of rare ones …

Image-to-image retrieval, a fundamental task, aims at matching similar images based on a
query image. Existing methods with convolutional neural networks are usually sensitive to …

Visual relationship detection aims to recognize visual relationships in scenes as triplets<
subject-predicate-object>. Previous works have shown remarkable progress by introducing …