Olga Russakovsky

29

Papers

0

Total Citations

Papers (29)

Attention IoU: Examining Biases in CelebA using Attention Maps

D^3: Scaling Up Deepfake Detection by Learning from Discrepancy

The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation

What is Dataset Distillation Learning?

Best of Both Worlds: Human-Machine Collaboration for Object Annotation

Joint Calibration of Ensemble of Exemplar SVMs

End-To-End Learning of Action Detection From Frame Glimpses in Videos

What's in a Question: Using Visual Questions as a Form of Supervision

Predictive-Corrective Networks for Action Detection

Learning to Learn From Noisy Web Videos

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

Fair Attribute Classification Through Latent Space De-Biasing

Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability

What Actions Are Needed for Understanding Human Actions in Videos?

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Human Uncertainty Makes Classification More Robust

Understanding and Evaluating Racial Biases in Image Captioning

Gender Artifacts in Visual Datasets

Overwriting Pretrained Bias with Finetuning Data

REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets

Towards Unique and Informative Captioning of Images

HIVE: Evaluating the Human Interpretability of Visual Explanations

Multi-Query Video Retrieval

SiRi: A Simple Selective Retraining Mechanism for Transformer-Based Visual Grounding

Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation

Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks

Enabling Detailed Action Recognition Evaluation Through Video Dataset Augmentation

GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition

Boundary Guided Learning-Free Semantic Control with Diffusion Models