Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging

no code implementations • 3 May 2022 • Fangzhou Mu, Sicheng Mo, Jiayong Peng, Xiaochun Liu, Ji Hyun Nam, Siddeshwar Raghavan, Andreas Velten, Yin Li

Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms.

A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge

1 code implementation • 16 Nov 2022 • Sicheng Mo, Fangzhou Mu, Yin Li

This report describes Badgers@UW-Madison, our submission to the Ego4D Natural Language Queries (NLQ) Challenge.

Natural Language Queries Temporal Action Localization +1

Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge

2 code implementations • 16 Nov 2022 • Fangzhou Mu, Sicheng Mo, Gillian Wang, Yin Li

This report describes our submission to the Ego4D Moment Queries Challenge 2022.

Moment Queries Temporal Action Localization

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

no code implementations • 12 Dec 2023 • Sicheng Mo, Fangzhou Mu, Kuan Heng Lin, Yanli Liu, Bochen Guan, Yin Li, Bolei Zhou

Recent approaches such as ControlNet offer users fine-grained spatial control over text-to-image (T2I) diffusion models.

SnAG: Scalable and Accurate Video Grounding

1 code implementation • 2 Apr 2024 • Fangzhou Mu, Sicheng Mo, Yin Li

In this paper, we study the effect of cross-modal fusion on the scalability of video grounding models.

Video Grounding Video Understanding