In this paper, we present AGRoL, a novel conditional diffusion model specially purposed to track full bodies given sparse upper-body tracking signals. Our model uses a simple...
We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep...
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in...
In this blog, we’ll introduce the EgoObjects pilot version, consisting of 9,273 videos (30+ hours) for 368 categories of objects, with a total of 654K annotations.
In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i.e., block) level. We first perform empirical...
Meta AI is sharing new research to reduce the latency of existing Vision Transformer (ViT) models without the need for additional training. Our approach, called Token Merging...
This work focuses on the apparent emotional reaction recognition (AERR) from the video-only input, conducted in a self-supervised fashion.
We verify through experiments on widely available image sets that the resulting SVMs do provide superior accuracy in comparison to well-established deep neural network benchmarks...
In this paper, we develop Glimpse Transformers (GliTr), which observe only narrow glimpses at all times, thus predicting an ongoing action and the following most informative...
To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise biases that properly normalize...
