VDU22
* *Video Action Detection: Analysing Limitations and Challenges
* *Vision Datasets Understanding
* A3D: Studying Pretrained Representations with Programmable Datasets
* Analysis of Temporal Tensor Datasets on Product Grassmann Manifold
* BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
* Can the Mathematical Correctness of Object Configurations Affect the Accuracy of Their Perception?
* Can we trust bounding box annotations for object detection?
* Challenging Benchmark of Anime Style Recognition, A
* Dark Corner on Skin Lesion Image Dataset: Does it matter?
* Dataset Distillation by Matching Training Trajectories
* deepPIC: Deep Perceptual Image Clustering For Identifying Bias In Vision Datasets
* Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets
* Effect of Improving Annotation Quality on Object Detection Datasets: A Preliminary Study, The
* Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling
* Investigating Neural Architectures by Synthetic Dataset Design
* Mitigating Paucity of Data in Sinusoid Characterization Using Generative Synthetic Noise
* On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models
* Rethinking Illumination for Person Re-Identification: A Unified View
* Self-supervision versus synthetic datasets: Which is the lesser evil in the context of video denoising?
* Topology and Language of Relationships in the Visual Genome Dataset, The
* Towards Explaining Image-Based Distribution Shifts
* What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics
* Why Object Detectors Fail: Investigating the Influence of the Dataset
23 for VDU22
VDU23
* *Vision Datasets Understanding
* Compensation Learning in Semantic Segmentation
* Consistency and Accuracy of CelebA Attribute Values
* Digital Twin Tracking Dataset (DTTD): A New RGB+Depth 3D Dataset for Longer-Range Object Tracking Applications
* Exploring Video Frame Redundancies for Efficient Data Sampling and Annotation in Instance Segmentation
* K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation
* Scoring Your Prediction on Unseen Data
* WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models
8 for VDU23