87 citations · 376 across the 31 of their papers we have counts for
33 papers
Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers
Matthew Dutson, Yin Li, Mohit Gupta
Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a…
NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023
Lin Sui, Fangzhou Mu, Yin Li
This report describes our submission to the Ego4D Moment Queries Challenge 2023. Our submission extends ActionFormer, a latest method for temporal action localization. Our extensio…
Beyond-Voice: Towards Continuous 3D Hand Pose Tracking on Commercial Home Assistant Devices
Yin Li, Rohan Reddy, Cheng Zhang +1
The surging popularity of home assistants and their voice user interface (VUI) have made them an ideal central control hub for smart home devices. However, current form factors hea…
SimHaze: game engine simulated data for real-world dehazing
Zhengyang Lou, Huan Xu, Fangzhou Mu +7
Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a ha…
InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning
Zhuoran Yu, Yin Li, Yong Jae Lee
Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo…
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
Fangzhou Mu, Sicheng Mo, Gillian Wang +1
This report describes our submission to the Ego4D Moment Queries Challenge 2022. Our submission builds on ActionFormer, the state-of-the-art backbone for temporal action localizati…
A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge
Sicheng Mo, Fangzhou Mu, Yin Li
This report describes Badgers@UW-Madison, our submission to the Ego4D Natural Language Queries (NLQ) Challenge. Our solution inherits the point-based event representation from our…
3D Scene Inference from Transient Histograms
Sacha Jungerman, Atul Ingle, Yin Li +1
Time-resolved image sensors that capture light at pico-to-nanosecond timescales were once limited to niche applications but are now rapidly becoming mainstream in consumer devices.…
mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors
Sizhe An, Yin Li, Umit Ogras
The ability to estimate 3D human body pose and movement, also known as human pose estimation (HPE), enables many applications for home-based health monitoring, such as remote rehab…
Robust Scene Inference under Noise-Blur Dual Corruptions
Bhavya Goyal, Jean-François Lalonde, Yin Li +1
Scene inference under low-light is a challenging problem due to severe noise in the captured images. One way to reduce noise is to use longer exposure during the capture. However,…
EnergyMatch: Energy-based Pseudo-Labeling for Semi-Supervised Learning
Zhuoran Yu, Yin Li, Yong Jae Lee
Recent state-of-the-art methods in semi-supervised learning (SSL) combine consistency regularization with confidence-based pseudo-labeling. To obtain high-quality pseudo-labels, a…
Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging
Fangzhou Mu, Sicheng Mo, Jiayong Peng +5
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 algo…
ActionFormer: Localizing Moments of Actions with Transformers
Chenlin Zhang, Jianxin Wu, Yin Li
Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by t…
RegionCLIP: Region-based Language-Image Pretraining
Yiwu Zhong, Jianwei Yang, Pengchuan Zhang +8
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. Howev…
3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image
Fangzhou Mu, Jian Wang, Yicheng Wu +1
Visual content creation has spurred a soaring interest given its applications in mobile photography and AR / VR. Style transfer and single-image 3D photography as two representativ…
Event Neural Networks
Matthew Dutson, Yin Li, Mohit Gupta
Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-leve…
Learning to Generate Scene Graph from Natural Language Supervision
Yiwu Zhong, Jing Shi, Jianwei Yang +2
Learning from image-text data has demonstrated recent success for many recognition tasks, yet is currently limited to visual features or individual visual concepts such as objects.…
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Chen-Lin Zhang, Yin Li, Jianxin Wu
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised obj…
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty +4
Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the s…
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning
Bin Li, Yin Li, Kevin W. Eliceiri
We address the challenging problem of whole slide image (WSI) classification. WSIs have very high resolutions and usually lack localized annotations. WSI classification can be cast…
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
Ran Xu, Chen-lin Zhang, Pengcheng Wang +5
Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transporta…
Comprehensive Image Captioning via Scene Graph Decomposition
Yiwu Zhong, Liwei Wang, Jianshu Chen +2
We address the challenging problem of image captioning by revisiting the representation of image scene graph. At the core of our method lies the decomposition of a scene graph into…
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
Liwei Wang, Jing Huang, Yin Li +3
Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image re…
In the Eye of the Beholder: Gaze and Actions in First Person Video
Yin Li, Miao Liu, James M. Rehg
We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera. To facilitate our researc…