SOTAVerified

Video Object Tracking

Video Object Detection aims to detect targets in videos using both spatial and temporal information. It's usually deeply integrated with tasks such as Object Detection and Object Tracking.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 98 papers

TitleStatusHype
AiATrack: Attention in Attention for Transformer Visual TrackingCode1
High-Speed Tracking with Kernelized Correlation FiltersCode1
STMTrack: Template-free Visual Tracking with Space-time Memory NetworksCode1
HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term TrackingCode1
ApproxDet: Content and Contention-Aware Approximate Object Detection for MobilesCode1
Single-Model and Any-Modality for Video Object TrackingCode1
Robust Visual Tracking by SegmentationCode1
Revealing the Dark Secrets of Masked Image ModelingCode1
Referring Video Object Segmentation via Language-aligned Track SelectionCode1
A Real-Time Wrong-Way Vehicle Detection Based on YOLO and Centroid TrackingCode1
Transformer TrackingCode1
Quo Vadis, Action Recognition? A New Model and the Kinetics DatasetCode1
Learning Object Permanence from VideoCode1
Associate Everything Detected: Facilitating Tracking-by-Detection to the UnknownCode1
Learning Spatio-Temporal Transformer for Visual TrackingCode1
Learning to Fuse Asymmetric Feature Maps in Siamese TrackersCode1
Learning What and Where: Disentangling Location and Identity Tracking Without SupervisionCode1
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture SearchCode1
ProContEXT: Exploring Progressive Context Transformer for TrackingCode1
NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor TrackletsCode1
NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object TrackingCode1
Ocean: Object-aware Anchor-free TrackingCode1
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object TrackingCode1
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D ModelsCode1
CATER: A diagnostic dataset for Compositional Actions and TEmporal ReasoningCode1
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.