Matt Feiszli

papers

1,555

total citations

papers (21)

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

CVPR 2022arXiv

citations

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

NEURIPS 2023arXiv

citations

FP-NAS: Fast Probabilistic Neural Architecture Search

CVPR 2021arXiv

citations

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

CVPR 2025arXiv

citations

3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

ECCV 2024arXiv

citations

Searching for Two-Stream Models in Multivariate Space for Video Recognition

ICCV 2021arXiv

citations

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

CVPR 2024arXiv

citations

ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation

ECCV 2024arXiv

citations

Learning to Segment Referred Objects from Narrated Egocentric Videos

CVPR 2024

citations

SiLK: Simple Learned Keypoints

ICCV 2023

citations

Self-Supervised Object Detection from Egocentric Videos

ICCV 2023

citations

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

NEURIPS 2023

citations

Relational Space-Time Query in Long-Form Videos

CVPR 2023

citations

"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval"

ECCV 2022

citations

Matt Feiszli

papers (21)

What Makes Training Multi-Modal Classification Networks Hard?

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

SF-Net: Single-Frame Supervision for Temporal Action Localization

Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation

Video Modeling With Correlation Networks

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

FP-NAS: Fast Probabilistic Neural Architecture Search

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

Searching for Two-Stream Models in Multivariate Space for Video Recognition

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation

Learning to Segment Referred Objects from Narrated Egocentric Videos

SiLK: Simple Learned Keypoints

Self-Supervised Object Detection from Egocentric Videos

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

Relational Space-Time Query in Long-Form Videos

"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval"

papers (21)

What Makes Training Multi-Modal Classification Networks Hard?

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

SF-Net: Single-Frame Supervision for Temporal Action Localization

Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation

Video Modeling With Correlation Networks

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

FP-NAS: Fast Probabilistic Neural Architecture Search

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

Searching for Two-Stream Models in Multivariate Space for Video Recognition

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation

Learning to Segment Referred Objects from Narrated Egocentric Videos

SiLK: Simple Learned Keypoints

Self-Supervised Object Detection from Egocentric Videos

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

Relational Space-Time Query in Long-Form Videos

"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval"