activity
20142019
most citedPixelNet: Towards a General Pixel-level Architecture

55 citations · 115 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20191 cited

Growing a Brain: Fine-Tuning by Increasing Model Capacity

Yu-Xiong Wang, Deva Ramanan, Martial Hebert

CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is t…

cs.CV20191 cited

Shapes and Context: In-the-Wild Image Synthesis & Manipulation

Aayush Bansal, Yaser Sheikh, Deva Ramanan

We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this spac…

cs.CV20164 cited

Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery

Vivek Krishnan, Deva Ramanan

We consider the task of visual net surgery, in which a CNN can be reconfigured without extra data to recognize novel concepts that may be omitted from the training set. While most…

cs.CV201655 cited

PixelNet: Towards a General Pixel-level Architecture

Aayush Bansal, Xinlei Chen, Bryan Russell +2

We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Conv…

cs.CV201451 cited

3D Hand Pose Detection in Egocentric RGB-D Images

Gregory Rogez, James S. Supancic, Maryam Khademi +2

We focus on the task of everyday hand pose estimation from egocentric viewpoints. For this task, we show that depth sensors are particularly informative for extracting near-field i…

cs.CV20143 cited

Egocentric Pose Recognition in Four Lines of Code

Gregory Rogez, James S. Supancic, Deva Ramanan

We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during every…