Publications

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and …

Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their …

This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive …

This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. …

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention …

High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs …

This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal …

Though the state-of-the architectures for semantic segmentation, such as HRNet, demonstrate impressive accuracy, the complexity arising …

Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional …

We propose Skip-Convolutions to leverage the large amount of redundancies in video streams and save computations. Each video is …

In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on …

We tackle the task of efficient video super resolution. Motivated by our study on the quality vs. efficiency trade-off on a wide range …

Video action classification and temporal localization are two key components of video understanding where we witnessed significant …

In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes …

Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing …

This paper studies the effect of quality degradation, caused by lossy video compression, on video recognition. We investigate how the …

In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder …

This paper proposes a data-driven approach for cross-media retrieval by automatically learning its underlying semantic vocabulary. …

This paper proposes a data-driven approach for cross-media retrieval by automatically learning its underlying semantic vocabulary. …

R We consider automated detection of events in video without the use of any visual training examples. A common approach is to represent …

Representing videos using vocabularies composed of concept detectors appears promising for event recognition. While many have recently …