activity
20122022
most citedA Survey of Point-of-interest Recommendation in Location-based Social Networks

79 citations · 583 across the 45 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV20211 cited

Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation

Pengpeng Liu, Michael R. Lyu, Irwin King +1

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformation…

cs.CV20202 cited

Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings

Yue Wang, Jing Li, Michael R. Lyu +1

Social media produces large amounts of contents every day. To help users quickly capture what they need, keyphrase prediction is receiving a growing attention. Nevertheless, most p…

cs.CV2020

Learning 3D Face Reconstruction with a Pose Guidance Network

Pengpeng Liu, Xintong Han, Michael Lyu +2

We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation i…

cs.CV20203 cited

Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching

Pengpeng Liu, Irwin King, Michael Lyu +1

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flo…

cs.CV2020

VD-BERT: A Unified Vision and Dialog Transformer with BERT

Yue Wang, Shafiq Joty, Michael R. Lyu +3

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior wor…

cs.CV201914 cited

SelFlow: Self-Supervised Learning of Optical Flow

Pengpeng Liu, Michael Lyu, Irwin King +1

We present a self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth…