activity
20202022
most citedCDFI: Compression-Driven Network Design for Frame Interpolation

6 citations · 16 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV20224 cited

RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution

Zhicheng Geng, Luming Liang, Tianyu Ding +1

Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-…

cs.LG2021

A Geometric Analysis of Neural Collapse with Unconstrained Features

Zhihui Zhu, Tianyu Ding, Jinxin Zhou +4

We provide the first global optimization landscape analysis of -- an intriguing empirical phenomenon that arises in the last-layer classifiers and features of ne…

cs.CV20216 cited

CDFI: Compression-Driven Network Design for Frame Interpolation

Tianyu Ding, Luming Liang, Zhihui Zhu +1

DNN-based frame interpolation--that generates the intermediate frames given two consecutive frames--typically relies on heavy model architectures with a huge number of features, pr…

cs.LG20206 cited

Neural Network Compression Via Sparse Optimization

Tianyi Chen, Bo Ji, Yixin Shi +4

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have…

math.OC2020

Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem

Tianyi Chen, Guanyi Wang, Tianyu Ding +3

Optimizing with group sparsity is significant in enhancing model interpretability in machining learning applications, e.g., feature selection, compressed sensing and model compress…

math.OC2020

Orthant Based Proximal Stochastic Gradient Method for -Regularized Optimization

Tianyi Chen, Tianyu Ding, Bo Ji +6

Sparsity-inducing regularization problems are ubiquitous in machine learning applications, ranging from feature selection to model compression. In this paper, we present a novel st…