699 citations · 2.1k across the 49 of their papers we have counts for
7 papers · 1 filter
Video Object Detection with an Aligned Spatial-Temporal Memory
Fanyi Xiao, Yong Jae Lee
We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to mod…
Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery
Zhongzheng Ren, Yong Jae Lee
In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we…
Weakly-supervised Visual Grounding of Phrases with Linguistic Structures
Fanyi Xiao, Leonid Sigal, Yong Jae Lee
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial…
Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks
Wenjian Hu, Krishna Kumar Singh, Fanyi Xiao +3
Content popularity prediction has been extensively studied due to its importance and interest for both users and hosts of social media sites like Facebook, Instagram, Twitter, and…
Identifying First-person Camera Wearers in Third-person Videos
Chenyou Fan, Jangwon Lee, Mingze Xu +4
We consider scenarios in which we wish to perform joint scene understanding, object tracking, activity recognition, and other tasks in environments in which multiple people are wea…
Interspecies Knowledge Transfer for Facial Keypoint Detection
Maheen Rashid, Xiuye Gu, Yong Jae Lee
We present a method for localizing facial keypoints on animals by transferring knowledge gained from human faces. Instead of directly finetuning a network trained to detect keypoin…
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
Krishna Kumar Singh, Yong Jae Lee
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised meth…