activity
20192023
most citedTAda! Temporally-Adaptive Convolutions for Video Understanding

31 citations · 182 across the 26 of their papers we have counts for

collaborators

31 papers

cs.CV2023★ 2 cited

Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning

Zhiwu Qing, Shiwei Zhang, Ziyuan Huang +4

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to…

cs.CV2023

Towards Real-World Visual Tracking with Temporal Contexts

Ziang Cao, Ziyuan Huang, Liang Pan +3

Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooki…

cs.CV2023★ 7 cited

Temporally-Adaptive Models for Efficient Video Understanding

Ziyuan Huang, Shiwei Zhang, Liang Pan +4

Spatial convolutions are extensively used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in diffe…

cs.CV2023★ 2 cited

Rethinking Efficient Tuning Methods from a Unified Perspective

Zeyinzi Jiang, Chaojie Mao, Ziyuan Huang +3

Parameter-efficient transfer learning (PETL) based on large-scale pre-trained foundation models has achieved great success in various downstream applications. Existing tuning metho…

cs.CV2022

Physically Plausible Animation of Human Upper Body from a Single Image

Ziyuan Huang, Zhengping Zhou, Yung-Yu Chuang +2

We present a new method for generating controllable, dynamically responsive, and photorealistic human animations. Given an image of a person, our system allows the user to generate…

cs.CV2022★ 1 cited

Progressive Learning without Forgetting

Tao Feng, Hangjie Yuan, Mang Wang +3

Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on…