Matt Feiszli

20

Papers

0

Total Citations

Papers (20)

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

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

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

Learning to Segment Referred Objects from Narrated Egocentric Videos

Video Modeling With Correlation Networks

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

What Makes Training Multi-Modal Classification Networks Hard?

FP-NAS: Fast Probabilistic Neural Architecture Search

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

Relational Space-Time Query in Long-Form Videos

Video Classification With Channel-Separated Convolutional Networks

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

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

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Self-Supervised Object Detection from Egocentric Videos

SiLK: Simple Learned Keypoints

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

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

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

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset