Search Results for author:
Found 12 papers, 10 papers with code
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling.
Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss.
PETR: Position Embedding Transformation for Multi-View 3D Object Detection
Object query can perceive the 3D position-aware features and perform end-to-end object detection.
Implicit Feature Refinement for Instance Segmentation
Our IFR enjoys several advantages: 1) simulates an infinite-depth refinement network while only requiring parameters of single residual block; 2) produces high-level equilibrium instance features of global receptive field; 3) serves as a plug-and-play general module easily extended to most object recognition frameworks.
SOLQ: Segmenting Objects by Learning Queries
Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR.
Ranked #17 on
Instance Segmentation
on COCO test-dev
MOTR: End-to-End Multiple-Object Tracking with Transformer
Temporal modeling of objects is a key challenge in multiple-object tracking (MOT).
Ranked #2 on
Multi-Object Tracking
on DanceTrack
Implicit Feature Pyramid Network for Object Detection
In this paper, we present an implicit feature pyramid network (i-FPN) for object detection.
Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
Object detectors usually achieve promising results with the supervision of complete instance annotations.
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
Ranked #5 on
Few-Shot Object Detection
on LVIS v1.0 val
Learning Human-Object Interaction Detection using Interaction Points
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
Deep Contextual Attention for Human-Object Interaction Detection
Our approach outperforms the state-of-the-art on all datasets.
Learning Rich Features at High-Speed for Single-Shot Object Detection
We introduce a single-stage detection framework that combines the advantages of both fine-tuning pretrained models and training from scratch.
