no code implementations • 20 Mar 2024 • Mengyu Yang, Ye Tian, Lanshan Zhang, Xiao Liang, Xuming Ran, Wendong Wang
Recently, prompt-based methods have emerged as a new alternative `parameter-efficient fine-tuning' paradigm, which only fine-tunes a small number of additional parameters while keeping the original model frozen.
no code implementations • 5 Oct 2023 • Mengyu Yang, Patrick Grady, Samarth Brahmbhatt, Arun Balajee Vasudevan, Charles C. Kemp, James Hays
How easy is it to sneak up on a robot?
no code implementations • 9 Aug 2023 • Ye Tian, Mengyu Yang, Lanshan Zhang, Zhizhen Zhang, Yang Liu, Xiaohui Xie, Xirong Que, Wendong Wang
To this end, inspired by human cognition, we propose a novel recognition paradigm of "View while Moving" for efficient long-untrimmed video recognition.
no code implementations • 28 Jul 2023 • Zhizhen Zhang, Xiaohui Xie, Mengyu Yang, Ye Tian, Yong Jiang, Yong Cui
Social Media Popularity Prediction has drawn a lot of attention because of its profound impact on many different applications, such as recommendation systems and multimedia advertising.
1 code implementation • NeurIPS 2021 • Tanzila Rahman, Mengyu Yang, Leonid Sigal
In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables contextual feature learning across three modalities: vision, pose, and audio, with the use of flexible co-attention.
1 code implementation • 26 Oct 2021 • Tanzila Rahman, Mengyu Yang, Leonid Sigal
In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables contextual feature learning across three modalities: vision, pose, and audio, with the use of flexible co-attention.
1 code implementation • 15 May 2021 • Mengyu Yang, David Rokeby, Xavier Snelgrove
Advances in the realm of Generative Adversarial Networks (GANs) have led to architectures capable of producing amazingly realistic images such as StyleGAN2, which, when trained on the FFHQ dataset, generates images of human faces from random vectors in a lower-dimensional latent space.