Search Results for author:
Found 12 papers, 3 papers with code
Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation
We propose a weakly supervised approach to semantic segmentation using bounding box annotations.
FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
We present FlexNeRF, a method for photorealistic freeviewpoint rendering of humans in motion from monocular videos.
Sequential Ensembling for Semantic Segmentation
Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications.
Ranked #10 on
Semantic Segmentation
on PASCAL Context
Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
Specifically, we achieve 70. 0 AP on CrowdPose and 42. 5 AP on OCHuman test sets, a significant improvement of 2. 4 AP and 6. 5 AP over the prior art, respectively.
Ranked #1 on
Multi-Person Pose Estimation
on OCHuman
PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation
Finally, both the teacher and the student networks are jointly fine-tuned in an end-to-end manner using temporal, self-consistency and adversarial losses, improving the accuracy of each individual network.
Ranked #70 on
3D Human Pose Estimation
on MPI-INF-3DHP
(using extra training data)
Learning to Generate Synthetic Data via Compositing
The synthesizer and target networks are trained in an adversarial manner wherein each network is updated with a goal to outdo the other.
Unsupervised 3D Pose Estimation with Geometric Self-Supervision
Additionally, to learn from 2D poses "in the wild", we train an unsupervised 2D domain adapter network to allow for an expansion of 2D data.
Ranked #73 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
"When and Where?": Behavior Dominant Location Forecasting with Micro-blog Streams
The proliferation of smartphones and wearable devices has increased the availability of large amounts of geospatial streams to provide significant automated discovery of knowledge in pervasive environments, but most prominent information related to altering interests have not yet adequately capitalized.
Can 3D Pose be Learned from 2D Projections Alone?
We present a weakly supervised approach to estimate 3D pose points, given only 2D pose landmarks.
CRAFT: Complementary Recommendations Using Adversarial Feature Transformer
Such a conditional generative model can produce multiple novel samples of complementary items (in the feature space) for a given query item.
Context Encoding for Semantic Segmentation
In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps.
Ranked #7 on
Semantic Segmentation
on PASCAL VOC 2012 test
Single Image Calibration of Multi-axial Imaging Systems
We describe such setups as multi-axial imaging systems, since a single sphere results in an axial system.
