11 citations · 21 across the 10 of their papers we have counts for
12 papers
Unified Video Dense Prediction from Disjoint Data
Yihong Sun, Seoung Wug Oh, Jiahui Huang +2
Scene understanding requires simultaneous prediction about geometry, appearance, and semantics. However, existing task-specific annotations are fragmented across incompatible, doma…
Efficient Tracking and Understanding Object Transformations
Yihong Sun, Bharath Hariharan
Tracking objects through state transformations is essential for understanding real-world dynamics. However, existing methods are computationally expensive. TubeletGraph recently sh…
Live Interactive Training for Video Segmentation
Xinyu Yang, Haozheng Yu, Yihong Sun +2
Interactive video segmentation often requires many user interventions for robust performance in challenging scenarios (e.g., occlusions, object separations, camouflage, etc.). Yet,…
Tracking and Understanding Object Transformations
Yihong Sun, Xinyu Yang, Jennifer J. Sun +1
Real-world objects frequently undergo state transformations. From an apple being cut into pieces to a butterfly emerging from its cocoon, tracking through these changes is importan…
Video Creation by Demonstration
Yihong Sun, Hao Zhou, Liangzhe Yuan +7
We explore a novel video creation experience, namely Video Creation by Demonstration. Given a demonstration video and a context image from a different scene, we generate a physical…
Learning 3D Perception from Others' Predictions
Jinsu Yoo, Zhenyang Feng, Tai-Yu Pan +7
Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs re…
MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
Yihong Sun, Bharath Hariharan
Embodied agents must detect and localize objects of interest, e.g. traffic participants for self-driving cars. Supervision in the form of bounding boxes for this task is extremely…
Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
Yihong Sun, Bharath Hariharan
Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dyna…
Robust Instance Segmentation through Reasoning about Multi-Object Occlusion
Xiaoding Yuan, Adam Kortylewski, Yihong Sun +1
Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches t…
Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model
Yihong Sun, Adam Kortylewski, Alan Yuille
Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occlude…
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
Adam Kortylewski, Qing Liu, Angtian Wang +2
Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neur…
Robust Object Detection under Occlusion with Context-Aware CompositionalNets
Angtian Wang, Yihong Sun, Adam Kortylewski +1
Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection unde…