Zsolt Kira

papers

3,307

total citations

papers (28)

Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data

CVPR 2020arXiv

660

citations

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

NEURIPS 2021arXiv

651

citations

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

CVPR 2023arXiv

472

citations

Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors

CVPR 2022arXiv

130

citations

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

ECCV 2020arXiv

127

citations

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

CVPR 2022arXiv

citations

Posterior Re-calibration for Imbalanced Datasets

NEURIPS 2020arXiv

citations

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

CVPR 2024arXiv

citations

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

NEURIPS 2022arXiv

citations

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

ICCV 2023arXiv

citations

Trainable Projected Gradient Method for Robust Fine-Tuning

CVPR 2023arXiv

citations

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

CVPR 2023arXiv

citations

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

NEURIPS 2023arXiv

citations

Open-Set Semi-Supervised Object Detection

ECCV 2022arXiv

citations

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

CVPR 2023arXiv

citations

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

NEURIPS 2021arXiv

citations

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

CVPR 2025arXiv

citations

Fast Trainable Projection for Robust Fine-tuning

NEURIPS 2023arXiv

citations

Seeing the Unseen: Visual Common Sense for Semantic Placement

CVPR 2024arXiv

citations

Training Energy-Based Normalizing Flow with Score-Matching Objectives

NEURIPS 2023arXiv

citations

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

CVPR 2025arXiv

citations

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device

ICCV 2025arXiv

citations

When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach

CVPR 2025arXiv

citations

"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization"

ECCV 2022

citations

Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

CVPR 2024

citations

Zsolt Kira

papers (28)

Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

When2com: Multi-Agent Perception via Communication Graph Grouping

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation

Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

Posterior Re-calibration for Imbalanced Datasets

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

Trainable Projected Gradient Method for Robust Fine-Tuning

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Open-Set Semi-Supervised Object Detection

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

Fast Trainable Projection for Robust Fine-tuning

Seeing the Unseen: Visual Common Sense for Semantic Placement

Training Energy-Based Normalizing Flow with Score-Matching Objectives

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device

When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach

"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization"

Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

papers (28)

Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

When2com: Multi-Agent Perception via Communication Graph Grouping

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation

Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

Posterior Re-calibration for Imbalanced Datasets

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

Trainable Projected Gradient Method for Robust Fine-Tuning

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Open-Set Semi-Supervised Object Detection

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons

Fast Trainable Projection for Robust Fine-tuning

Seeing the Unseen: Visual Common Sense for Semantic Placement

Training Energy-Based Normalizing Flow with Score-Matching Objectives

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device

When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach

"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization"

Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion