SOTAVerified

Object Detection

Papers

Showing 676700 of 10957 papers

TitleStatusHype
Decompose to Adapt: Cross-domain Object Detection via Feature DisentanglementCode1
3DMOTFormer: Graph Transformer for Online 3D Multi-Object TrackingCode1
Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving ScenariosCode1
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing AttentionCode1
DECO: Query-Based End-to-End Object Detection with ConvNetsCode1
Deep Fourier-embedded Network for Bi-modal Salient Object DetectionCode1
Deep learning for radar data exploitation of autonomous vehicleCode1
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object DetectionCode1
Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous ModalitiesCode1
DCDet: Dynamic Cross-based 3D Object DetectorCode1
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionCode1
Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave RadarCode1
DC-Net: Divide-and-Conquer for Salient Object DetectionCode1
DATE: Dual Assignment for End-to-End Fully Convolutional Object DetectionCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within DatasetsCode1
Energy-Based Models for Deep Probabilistic RegressionCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Advancing Referring Expression Segmentation Beyond Single ImageCode1
Data-Free Quantization Through Weight Equalization and Bias CorrectionCode1
DARTH: Holistic Test-time Adaptation for Multiple Object TrackingCode1
DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model TrainingCode1
Data Augmentation for Object Detection via Differentiable Neural RenderingCode1
Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based SegmentationCode1
Show:102550
← PrevPage 28 of 439Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Co-DETRbox mAP66Unverified
2InternImage-H (M3I Pre-training)box mAP65.5Unverified
3M3I Pre-training (InternImage-H)box mAP65.4Unverified
4MoCaEbox mAP65.1Unverified
5Co-DETR (Swin-L)box mAP64.8Unverified
6Focal-Stable-DINO (Focal-Huge, no TTA)box mAP64.8Unverified
7EVAbox mAP64.7Unverified
8Group DETR v2box mAP64.5Unverified
9FocalNet-H (DINO)box mAP64.4Unverified
10InternImage-XLbox mAP64.3Unverified