WACV 2020

424 papers

Top Research Directions

Research directions most represented by WACV 2020 papers.

Composite Loss Functions for Perceptual Image Restoration 7
Resolving Extreme Scale Variation in Object Detection 7
Preserving Tiny Features Against Spatial Resolution Degradation 7
Adversarial Training for Domain Invariant Representations 6
Learning to Translate Images Without Paired Data 6
Learning Similarity Metrics with Twin Networks 5
Efficient Single Stage Object Detection for Edge Hardware 5
High-Resolution Generative Scaling 5
Dynamic Frame Weighting for Video Understanding 5
Aligning Generative Media with Human Perceptual Preferences 4
Mitigating Seen Class Bias in Open World Learning 4
3D Convolutions for Spatiotemporal Feature Learning 4
Asymmetric Spatiotemporal Decoupling for Video Models 4
The Cross Modal Representation Gap 4
Domain Adaptation with Category Shift 4

Top Authors

AuthorPapers
Vinay P. Namboodiri9
Venkatesh Babu Radhakrishnan5
Alan Yuille4
Balaji Krishnamurthy4
Ming-Hsuan Yang4
Pravendra Singh4
Vinay Kumar Verma4
Vineeth N. Balasubramanian4
Gaurav Sharma3
Juho Kannala3
Lars Petersson3
Manmohan Chandraker3
Shuicheng YAN3
Abby Stylianou2
Abhinav Shrivastava2
Amelie Royer2
Ayan Chakrabarti2
Badri Narayana Patro2
Changick Kim2
Christoph H. Lampert2

Impactful Papers

Papers from WACV 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations
Spatial-Content Image Search in Complex Scenes
Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment
s-SBIR: Style Augmented Sketch based Image Retrieval
SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation
Stable Intrinsic Auto-Calibration from Fundamental Matrices of Devices with Uncorrelated Camera Parameters
Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
StacMR: Scene-Text Aware Cross-Modal Retrieval
Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy
Stochastic Dynamics for Video Infilling
Street Scene: A new dataset and evaluation protocol for video anomaly detection
Structured Compression of Deep Neural Networks with Debiased Elastic Group LASSO
Style Transfer for Light Field Photography
SubICap: Towards Subword-informed Image Captioning
Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network
Supervised and Unsupervised Learning of Parameterized Color Enhancement
SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
SymGAN: Orientation Estimation without Annotation for Symmetric Objects
SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving
Synthesizing human-like sketches from natural images using a conditional convolutional decoder
Synthetic Examples Improve Generalization for Rare Classes
TailorGAN: Making User-Defined Fashion Designs
Template-Based Automatic Search of Compact Semantic Segmentation Architectures
Temporal Contrastive Pretraining for Video Action Recognition
Temporal Similarity Analysis of Remote Photoplethysmography for Fast 3D Mask Face Presentation Attack Detection
Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition
Text-based Person Search via Attribute-aided Matching
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain
The Overlooked Elephant of Object Detection: Open Set
The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentation
TKD: Temporal Knowledge Distillation for Active Perception
Toward Explainable Fashion Recommendation
Toward Interactive Self-Annotation For Video Object Bounding Box: Recurrent Self-Learning And Hierarchical Annotation Based Framework
Towards a Unified Framework for Visual Compatibility Prediction
Towards Good Practice for CNN-Based Monocular Depth Estimation
Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
Towards Preserving the Ephemeral: Texture-Based Background Modelling for Capturing Back-of-the-Napkin Notes
Training with Noise Adversarial Network: A Generalization Method for Object Detection on Sonar Image
Transductive Zero-Shot Learning for 3D Point Cloud Classification
Triple-SGM: Stereo Processing using Semi-Global Matching with Cost Fusion
Two-Grid Preconditioned Solver for Bundle Adjustment
TwoStreamVAN: Improving Motion Modeling in Video Generation
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking

« prev Page 8/9 next »