Trending Research

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

jfzhang95/PoseAug 6 May 2021

To address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose estimator.

3D Human Pose Estimation Data Augmentation

0.15 stars / hour

EagerMOT: 3D Multi-Object Tracking via Sensor Fusion

aleksandrkim61/EagerMOT 29 Apr 2021

Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time.

3D Multi-Object Tracking Motion Planning +2

0.15 stars / hour

Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study

rahuln/lm-bio-kgc 17 Jun 2021

Biomedical knowledge graphs (KGs) hold rich information on entities such as diseases, drugs, and genes.

Knowledge Base Completion Knowledge Graphs +1

0.15 stars / hour

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

aim-uofa/depth 3 Feb 2020

Compared with previous learning objectives, i. e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes.

Affine Transformation Curriculum Learning +1

0.15 stars / hour

Invertible Image Signal Processing

yzxing87/Invertible-ISP 28 Mar 2021

Unprocessed RAW data is a highly valuable image format for image editing and computer vision.

0.15 stars / hour

Learning Dense Representations of Phrases at Scale

princeton-nlp/DensePhrases 23 Dec 2020

Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019).

Open-Domain Question Answering Question Generation +3

0.14 stars / hour

Plan2Scene: Converting Floorplans to 3D Scenes

3dlg-hcvc/plan2scene 9 Jun 2021

We address the task of converting a floorplan and a set of associated photos of a residence into a textured 3D mesh model, a task which we call Plan2Scene.


0.14 stars / hour

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

alisawuffles/DExperts 7 May 2021

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text.

Language Modelling Text Generation

0.14 stars / hour

Delving Deep into the Generalization of Vision Transformers under Distribution Shifts

Phoenix1153/ViT_OOD_generalization 14 Jun 2021

By investigating three types of generalization-enhanced ViTs, we observe their gradient-sensitivity and design a smoother learning strategy to achieve a stable training process.

Self-Supervised Learning

0.14 stars / hour

Simplifying Paragraph-level Question Generation via Transformer Language Models

patil-suraj/question_generation 3 May 2020

Question generation (QG) is a natural language generation task where a model is trained to ask questions corresponding to some input text.

Language Modelling Question Generation +2

0.13 stars / hour