activity
20172024
most citedLearning Affinity via Spatial Propagation Networks

26 citations · 95 across the 11 of their papers we have counts for

collaborators

15 papers

cs.CV2021

Self-Supervised Object Detection via Generative Image Synthesis

Siva Karthik Mustikovela, Shalini De Mello, Aayush Prakash +5

We present SSOD, the first end-to-end analysis-by synthesis framework with controllable GANs for the task of self-supervised object detection. We use collections of real world imag…

cs.CV2021

Weakly-Supervised Physically Unconstrained Gaze Estimation

Rakshit Kothari, Shalini De Mello, Umar Iqbal +3

A major challenge for physically unconstrained gaze estimation is acquiring training data with 3D gaze annotations for in-the-wild and outdoor scenarios. In contrast, videos of hum…

cs.CV202118 cited

Contrastive Syn-to-Real Generalization

Wuyang Chen, Zhiding Yu, Shalini De Mello +4

Training on synthetic data can be beneficial for label or data-scarce scenarios. However, synthetically trained models often suffer from poor generalization in real domains due to…

cs.CV20213 cited

Learning to Track Instances without Video Annotations

Yang Fu, Sifei Liu, Umar Iqbal +3

Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation…

cs.CV202019 cited

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Xueting Li, Sifei Liu, Shalini De Mello +4

This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D…

cs.CV2020

Self-Learning Transformations for Improving Gaze and Head Redirection

Yufeng Zheng, Seonwook Park, Xucong Zhang +2

Many computer vision tasks rely on labeled data. Rapid progress in generative modeling has led to the ability to synthesize photorealistic images. However, controlling specific asp…