BMVC 2020

166 papers
The 2020 British Machine Vision Conference (BMVC) featured 208 papers covering a range of topics in computer vision and machine learning. Research themes focused heavily on data efficiency and model reliability, including active learning with variable annotation costs, calibrated data acquisition, and identifying diminishing returns in data labeling. Robustness was another central topic, with studies examining adversarial resilience, the limitations of obfuscated gradients, and generalization in few-shot learning. Advancements in deep metric learning and contrastive learning were also represented, specifically addressing geometric objectives and semantic collisions. Application-oriented research highlighted developments in video analysis and image retrieval. Notable works included reinforcement learning for video object segmentation, temporal modulation for thumbnail generation, and fine-grained sketch-based image retrieval. The proceedings also featured research into self-supervised anomaly detection and zero-shot learning via adversarial visual-semantic embeddings. Prolific authors contributing to the 2020 edition included Andrew Zisserman, Tinne Tuytelaars, and Yi-Zhe Song. These contributions collectively addressed challenges in balancing multiple learning objectives and improving cross-modal hierarchical modeling.

Top Research Directions

Research directions most represented by BMVC 2020 papers.

Reconstructive Regularization for Information Preservation in Latent Representations 2
Robust Feature Alignment for Unsupervised Domain Adaptation 2
Mitigating Input Perturbation Sensitivity in Deep Networks 2
Optimal Line Packing with Grassmannian Frames 1
The Mathematical Mechanisms of Dropout Regularization 1
Restoring Shift Invariance with Anti-Aliased Downsampling 1
The Performance Ceiling of Pre-trained Feature Dependency 1
Understanding the Joint Training Performance Gap 1
Scaling Metric Learning via Class Proxies 1
Inducing Sparsity in Regularized Optimal Transport 1
Point Cloud Registration via Continuous Probability Distributions 1
Overcoming Geometric Symmetry Priors in 3D Object Perception 1
Hardware and Computational Bottlenecks of Complex Activations 1
Overcoming Shift Variance in Deep Networks 1
Bridging the Discriminative to Generative Gap in Multimodal Learning 1

Top Authors

AuthorPapers
Andrew Zisserman3
Krystian Mikolajczyk3
Luc Van Gool3
Raja Giryes3
Wei Tang3
Yi-Hsuan Tsai3
Eugene Belilovsky2
Ko Nishino2
Le Wang2
Ming-Hsuan Yang2
Nathan Jacobs2
Rainer Stiefelhagen2
Theo Gevers2
Tinne Tuytelaars2
Vinay P. Namboodiri2
Vineeth N. Balasubramanian2
Xilin CHEN2
Xin Yu2
Yi Fang2
Yi-Zhe Song2

Impactful Papers

Papers from BMVC 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Non-Probabilistic Cosine Similarity Loss for Few-Shot Image Classification
Novel View Synthesis from Single Images via Point Cloud Transformation
On Modality Bias in the TVQA Dataset
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
Pano2Scene: 3D Indoor Semantic Scene Reconstruction from a Single Indoor Panorama Image
PMD-Net: Privileged Modality Distillation Network for 3D Hand Pose Estimation from a Single RGB Image
Point Cloud Super Resolution with Adversarial Residual Graph Networks
POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
RecSal : Deep Recursive Supervision for Visual Saliency Prediction
Reducing Label Noise in Anchor-Free Object Detection
Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
Relational Generalized Few-Shot Learning
Residual Likelihood Forests
Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation
Revisiting Temporal Modeling for Video Super-resolution
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
Robust Image Matching By Dynamic Feature Selection
Robust Unsupervised Cleaning of Underwater Bathymetric Point Cloud Data
RODEO: Replay for Online Object Detection
SD-MTCNN: Self-Distilled Multi-Task CNN
Seeing wake words: Audio-visual Keyword Spotting
Self-supervised Knowledge Distillation for Few-shot Learning
Self-Supervised Learning for Facial Action Unit Recognition through Temporal Consistency
Semantic Estimation of 3D Body Shape and Pose using Minimal Cameras
Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
Semi-supervised semantic segmentation needs strong, varied perturbations
Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation
SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation
SketchHealer: A Graph-to-Sequence Network for Recreating Partial Human Sketches
SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
Spatial Feedback Learning to Improve Semantic Segmentation in Hot Weather
STQ-Nets: Unifying Network Binarization and Structured Pruning
Superpixel Masking and Inpainting for Self-Supervised Anomaly Detection
Synchronous Bidirectional Learning for Multilingual Lip Reading
Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
Text and Style Conditioned GAN for the Generation of Offline-Handwriting Lines
Text Attribute Aggregation and Visual Feature Decomposition for Person Search
The Resistance to Label Noise in K-NN and DNN Depends on its Concentration
Thoracic Disease Identification and Localization using Distance Learning and Region Verification
Towards Convolutional Neural Networks Compression via Global&Progressive Product Quantization
Towards Overcoming False Positives in Visual Relationship Detection
Transferring Pretrained Networks to Small Data via Category Decorrelation
Tripping through time: Efficient Localization of Activities in Videos
Two-in-One Refinement for Interactive Segmentation
Two-Stream Spatiotemporal Compositional Attention Network for VideoQA
Uncovering Hidden Challenges in Query-Based Video Moment Retrieval
Unified Representation Learning for Cross Model Compatibility

« prev Page 3/4 next »