319 citations · 363 across the 10 of their papers we have counts for
13 papers
Mobile Video Diffusion
Haitam Ben Yahia, Denis Korzhenkov, Ioannis Lelekas +2
Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper intro…
MoViE: Mobile Diffusion for Video Editing
Adil Karjauv, Noor Fathima, Ioannis Lelekas +3
Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods remain prohibitively expensive and challenging to…
Clockwork Diffusion: Efficient Generation With Model-Step Distillation
Amirhossein Habibian, Amir Ghodrati, Noor Fathima +4
This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation…
Skip-Attention: Improving Vision Transformers by Paying Less Attention
Shashanka Venkataramanan, Amir Ghodrati, Yuki M. Asano +2
This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these ope…
SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
Babak Ehteshami Bejnordi, Amirhossein Habibian, Fatih Porikli +1
High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs comes with high computation costs, and naive d…
FrameExit: Conditional Early Exiting for Efficient Video Recognition
Amir Ghodrati, Babak Ehteshami Bejnordi, Amirhossein Habibian
In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on selecting a subset of salient frames to reduce the co…
Video Time: Properties, Encoders and Evaluation
Amir Ghodrati, Efstratios Gavves, Cees G. M. Snoek
Time-aware encoding of frame sequences in a video is a fundamental problem in video understanding. While many attempted to model time in videos, an explicit study on quantifying vi…
Actor and Action Video Segmentation from a Sentence
Kirill Gavrilyuk, Amir Ghodrati, Zhenyang Li +1
This paper strives for pixel-level segmentation of actors and their actions in video content. Different from existing works, which all learn to segment from a fixed vocabulary of a…
DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers
Amir Ghodrati, Ali Diba, Marco Pedersoli +2
In this paper, a new method for generating object and action proposals in images and videos is proposed. It builds on activations of different convolutional layers of a pretrained…
Online Action Detection
Roeland De Geest, Efstratios Gavves, Amir Ghodrati +3
In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car shou…
Rank Pooling for Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas +2
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We sh…
Towards Automatic Image Editing: Learning to See another You
Amir Ghodrati, Xu Jia, Marco Pedersoli +1
Learning the distribution of images in order to generate new samples is a challenging task due to the high dimensionality of the data and the highly non-linear relations that are i…
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
Amir Ghodrati, Ali Diba, Marco Pedersoli +2
In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the gen- eration of object proposals. We generate hypotheses in a sliding…