SOTAVerified

Video Object Detection

Video object detection is the task of detecting objects from a video as opposed to images.

( Image credit: Learning Motion Priors for Efficient Video Object Detection )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 147 papers

TitleStatusHype
QueryProp: Object Query Propagation for High-Performance Video Object DetectionCode0
Flow-Guided Feature Aggregation for Video Object DetectionCode0
Do Image Classifiers Generalize Across Time?Code0
RN-VID: A Feature Fusion Architecture for Video Object DetectionCode0
Road User Detection in VideosCode0
A Delay Metric for Video Object Detection: What Average Precision Fails to TellCode0
Seq-NMS for Video Object DetectionCode0
Sequence Level Semantics Aggregation for Video Object DetectionCode0
Identity-Consistent Aggregation for Video Object DetectionCode0
Joint Representation of Temporal Image Sequences and Object Motion for Video Object DetectionCode0
Learning Where to Focus for Efficient Video Object DetectionCode0
STF: Spatio-Temporal Fusion Module for Improving Video Object DetectionCode0
Representation Recycling for Streaming Video AnalysisCode0
Context R-CNN: Long Term Temporal Context for Per-Camera Object DetectionCode0
Looking Fast and Slow: Memory-Guided Mobile Video Object DetectionCode0
Temporal RoI Align for Video Object RecognitionCode0
Transferable Adversarial Attacks for Image and Video Object DetectionCode0
Mobile Video Object Detection with Temporally-Aware Feature MapsCode0
Video object detection for privacy-preserving patient monitoring in intensive careCode0
Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In CricketCode0
Video Object Detection with an Aligned Spatial-Temporal MemoryCode0
Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in VideoCode0
Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object DetectionCode0
0-1 laws for pattern occurrences in phylogenetic trees and networks—0
YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.