Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …

During image editing, existing deep generative models tend to re-synthesize the entire
output from scratch, including the unedited regions. This leads to a significant waste of …

Diffusion models have achieved great success in synthesizing high-quality images.
However generating high-resolution images with diffusion models is still challenging due to …

We present AdaFrame, a framework that adaptively selects relevant frames on a per-input
basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network …

Visual recognition is currently one of the most important and active research areas in
computer vision, pattern recognition, and even the general field of artificial intelligence. It …

Sparse convolution plays a pivotal role in emerging workloads, including point cloud
processing in AR/VR, autonomous driving, and graph understanding in recommendation …

Convolutional neural network inference on video data requires powerful hardware for real-
time processing. Given the inherent coherence across consecutive frames, large parts of a …

We introduce AdaFrame, a conditional computation framework that adaptively selects
relevant frames on a per-input basis for fast video recognition. AdaFrame, which contains a …

In this paper, we propose a new multi-scale face detector having an extremely tiny number
of parameters (EXTD), less than 0.1 million, as well as achieving comparable performance …

This paper proposes a novel lightweight thumbnail container-based summarization (LTC-
SUM) framework for full feature-length videos. This framework generates a personalized …