630 citations · 1.6k across the 22 of their papers we have counts for
23 papers
Optimizing ViViT Training: Time and Memory Reduction for Action Recognition
Shreyank N Gowda, Anurag Arnab, Jonathan Huang
In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Trans…
DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
Xiuye Gu, Yin Cui, Jonathan Huang +8
Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We u…
Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations
Vasudha Kowtha, Miquel Espi Marques, Jonathan Huang +2
This work investigates pretrained audio representations for few shot Sound Event Detection. We specifically address the task of few shot detection of novel acoustic sequences, or s…
Local Metrics for Multi-Object Tracking
Jack Valmadre, Alex Bewley, Jonathan Huang +3
This paper introduces temporally local metrics for Multi-Object Tracking. These metrics are obtained by restricting existing metrics based on track matching to a finite temporal ho…
The surprising impact of mask-head architecture on novel class segmentation
Vighnesh Birodkar, Zhichao Lu, Siyang Li +2
Instance segmentation models today are very accurate when trained on large annotated datasets, but collecting mask annotations at scale is prohibitively expensive. We address the p…
PERF-Net: Pose Empowered RGB-Flow Net
Yinxiao Li, Zhichao Lu, Xuehan Xiong +1
In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving…