L3D-IVU22
* *Learning With Limited Labelled Data for Image and Video Understanding
* Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
* Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation
* AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data
* Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction
* Bootstrapped Representation Learning for Skeleton-Based Action Recognition
* Can domain adaptation make object recognition work for everyone?
* CDAD: A Common Daily Action Dataset with Collected Hard Negative Samples
* CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection
* Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels
* CoDo: Contrastive Learning with Downstream Background Invariance for Detection
* Compositional Mixture Representations for Vision and Text
* Consistency-based Active Learning for Object Detection
* Contrastive Regularization for Semi-Supervised Learning
* Denoising Pretraining for Semantic Segmentation
* Efficient Conditional Pre-training for Transfer Learning
* Faster, Lighter, Robuster: A Weakly-Supervised Crowd Analysis Enhancement Network and A Generic Feature Extraction Framework
* Few-Shot Class Incremental Learning Leveraging Self-Supervised Features
* Few-Shot Image Classification Along Sparse Graphs
* Few-Shot Supervised Prototype Alignment for Pedestrian Detection on Fisheye Images
* Open-Set Domain Adaptation Under Few Source-Domain Labeled Samples
* Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcity
* SaR: Self-adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-supervised Learning
* SCVRL: Shuffled Contrastive Video Representation Learning
* Self-Supervised Learning of Pose-Informed Latents
* Self-supervised Video Representation Learning with Cascade Positive Retrieval
* Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning
* TDT: Teaching Detectors to Track without Fully Annotated Videos
* Towards Open-Set Object Detection and Discovery
* Transformaly: Two (Feature Spaces) Are Better Than One
* Uniform Priors for Data-Efficient Learning
* Unsupervised Salient Object Detection with Spectral Cluster Voting
* Vicinal Counting Networks
* ViTOL: Vision Transformer for Weakly Supervised Object Localization
* What Should Be Equivariant In Self-Supervised Learning
* Zero-shot Learning Using Multimodal Descriptions
36 for L3D-IVU22