Workshops @ CVPR 2020

529 papers

Top Research Directions

Research directions most represented by Workshops @ CVPR 2020 papers.

Bridging the Synthetic-to-Real Degradation Gap 16
Generalizing from Synthetic Data to the Real World 14
Composite Loss Functions for Perceptual Image Restoration 11
The Perceptual Misalignment of Image Quality Metrics 11
The Perception-Distortion Tradeoff 11
Preserving Tiny Features Against Spatial Resolution Degradation 10
Mitigating Motion and Lighting Artifacts in Remote Photoplethysmography 9
Spatio-Temporal Pruning for Multi-Camera Tracking 7
Image Dehazing under Non-Uniform Atmospheric Degradation 7
Removing Moiré Interference from Screen Photography 6
Dense Feature Reuse in Deep Neural Networks 6
Eliminating the Optical Flow Bottleneck in Video Understanding 6
Geometric Adaptation for Wide Angle and Fisheye Lenses 6
Overcoming Computational Overhead in Neural Video Codecs 6
Perceptual Fidelity in Extreme Image Compression 6

Top Authors

AuthorPapers
Radu Timofte11
Mayank Vatsa6
Richa Singh6
Yanyun Qu5
Yuan Xie5
Errui Ding4
Fabian Hüger4
Luc Van Gool4
Martin Danelljan4
Shuai Liu4
Tim Fingscheidt4
Xiao Tan4
Yuzhi Zhao4
Zhibo Chen4
Andreas Bär3
Biplab Banerjee3
Dejia Xu3
Eduardo Valle3
Lizhuang Ma3
Marvin Klingner3

Impactful Papers

Papers from Workshops @ CVPR 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Structured Weight Unification and Encoding for Neural Network Compression and Acceleration
Structure Preserving Compressive Sensing MRI Reconstruction using Generative Adversarial Networks
Subpixel Dense Refinement Network for Skeletonization
Superkernel Neural Architecture Search for Image Denoising
SUW-Learn: Joint Supervised, Unsupervised, Weakly Supervised Deep Learning for Monocular Depth Estimation
Symbol Spotting on Digital Architectural Floor Plans Using a Deep Learning-based Framework
Syntharch: Interactive Image Search with Attribute-Conditioned Synthesis
Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers
Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation
TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning
Ternary MobileNets via Per-Layer Hybrid Filter Banks
Textual Visual Semantic Dataset for Text Spotting
The 1st Challenge on Remote Physiological Signal Sensing (RePSS)
The 4th AI City Challenge
The MTA Dataset for Multi Target Multi Camera Pedestrian Tracking by Weighted Distance Aggregation
TherISuRNet - A Computationally Efficient Thermal Image Super-Resolution Network
Thermal Image Super-Resolution Challenge - PBVS 2020
The Role of 'Sign' and 'Direction' of Gradient on the Performance of CNN
The "Vertigo Effect" on Your Smartphone: Dolly Zoom via Single Shot View Synthesis
The Weighted Euler Curve Transform for Shape and Image Analysis
Top-Down Networks: A coarse-to-fine reimagination of CNNs
Topology-Aware Single-Image 3D Shape Reconstruction
Topometric Imitation Learning For Route Following Under Appearance Change
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways
Toward Real-world Panoramic Image Enhancement
Towards Fine-grained Sampling for Active Learning in Object Detection
Towards Real-Time Systems for Vehicle Re-Identification, Multi-Camera Tracking, and Anomaly Detection
Towards Real-time Traffic Movement Count and Trajectory Reconstruction Using Virtual Traffic Lanes
Towards the Perceptual Quality Enhancement of Low Bit-rate Compressed Images
Towards Untrusted Social Video Verification to Combat Deepfakes via Face Geometry Consistency
Trident Dehazing Network
Triple-GAN: Progressive Face Aging with Triple Translation Loss
TTNet: Real-time temporal and spatial video analysis of table tennis
Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval
Ultra Low Bitrate Learned Image Compression by Selective Detail Decoding
Uncertainty Estimation in Deep Neural Networks for Dermoscopic Image Classification
Understanding action recognition in still images
Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing
Unsupervised Batch Normalization
Unsupervised Ensemble-Kernel Principal Component Analysis for Hyperspectral Anomaly Detection
Unsupervised Image Super-Resolution with an Indirect Supervised Path
Unsupervised Learning of Metric Representations with Slow Features from Omnidirectional Views
Unsupervised object detection via LWIR/RGB translation
Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder
Unsupervised Real-World Super Resolution with Cycle Generative Adversarial Network and Domain Discriminator
Unsupervised Single Image Super-Resolution Network (USISResNet) for Real-World Data Using Generative Adversarial Network
Unsupervised Temporal Consistency Metric for Video Segmentation in Highly-Automated Driving
Upright and Stabilized Omnidirectional Depth Estimation for Wide-baseline Multi-camera Inertial Systems
Using Mixture of Expert Models to Gain Insights into Semantic Segmentation
Using Player's Body-Orientation to Model Pass Feasibility in Soccer

« prev Page 10/11 next »