We present Mesh Pre-Training (MPT), a new pre-training framework that leverages 3D mesh data such as MoCap data for human pose and mesh reconstruction from a single image.
In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks.
The model design provides a natural mechanism for visual and semantic representations to be learned in a shared knowledge space, whereby it encourages the learned visual embedding to be discriminative and more semantically consistent.
Ranked #2 on Zero-Shot Action Recognition on ActivityNet
Initial access in millimeter-wave (mmW) wireless is critical toward successful realization of the fifth-generation (5G) wireless networks and beyond.
no code implementations • 30 Nov 2021 • Chung-Ching Lin, Veljko Boljanovic, Han Yan, Erfan Ghaderi, Mohammad Ali Mokri, Jayce Jeron Gaddis, Aditya Wadaskar, Chase Puglisi, Soumen Mohapatra, Qiuyan Xu, Sreeni Poolakkal, Deukhyoun Heo, Subhanshu Gupta, Danijela Cabric
The decadal research in integrated true-time-delay arrays have seen organic growth enabling realization of wideband beamformers for large arrays with wide aperture widths.
Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames as opposed to previous successes with sparsely sampled video frames for video-and-language understanding tasks (e. g., video question answering).
In this work, we demonstrate a true-time-delay (TTD) array with digitally reconfigurable delay elements enabling both fast beam-training at the receiver with wideband data communications.
An inherent property of real-world videos is the high correlation of information across frames which can translate into redundancy in either temporal or spatial feature maps of the models, or both.
Temporal modelling is the key for efficient video action recognition.
Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency.
We also propose a suitable algorithm that requires a single pilot to achieve high-accuracy estimation of angle of arrival.
We propose a modified variational autoencoder (VAE) architecture built on top of Mask R-CNN for instance-level video segmentation and tracking.
This paper presents a prior-less method for tracking and clustering an unknown number of human faces and maintaining their individual identities in unconstrained videos.
Quantitative relevance of results, according to non-expert similarity, as well as localized image regions, are also significantly improved.
Computing the warp is fully automated and uses a combination of local homography and global similarity transformations, both of which are estimated with respect to the target.