Seq-NMS for Video Object Detection
arXiv:1602.08465
Abstract
Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip. Recently, there have been major advances for doing object detection in a single image. These methods typically contain three phases: (i) object proposal generation (ii) object classification and (iii) post-processing. We propose a modification of the post-processing phase that uses high-scoring object detections from nearby frames to boost scores of weaker detections within the same clip. We show that our method obtains superior results to state-of-the-art single image object detection techniques. Our method placed 3rd in the video object detection (VID) task of the ImageNet Large Scale Visual Recognition Challenge 2015 (ILSVRC2015).
Technical Report for Imagenet VID Competition 2015
References in corpus (1)
Cited by in corpus (61)
- A Survey of Deep Learning-based Object Detection
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Deep Learning for UAV-based Object Detection and Tracking: A Survey
- STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
- Flow-Guided Feature Aggregation for Video Object Detection
- NoScope: Optimizing Neural Network Queries over Video at Scale
- Mobile Video Object Detection with Temporally-Aware Feature Maps
- AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling
- Sequence Level Semantics Aggregation for Video Object Detection
- Memory Enhanced Global-Local Aggregation for Video Object Detection
- Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
- Relation Distillation Networks for Video Object Detection
- Impression Network for Video Object Detection
- Dual Semantic Fusion Network for Video Object Detection
- Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
- Recent Advances in Deep Learning for Object Detection
- A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos
- Progressive Sparse Local Attention for Video object detection
- Video Relation Detection with Trajectory-aware Multi-modal Features
- On The Stability of Video Detection and Tracking
- ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
- CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation
- RetinaTrack: Online Single Stage Joint Detection and Tracking
- Learning to Estimate Without Bias
- Detection and Tracking Meet Drones Challenge
- Video Instance Segmentation
- Real-Time Face & Eye Tracking and Blink Detection using Event Cameras
- Optimizing Video Object Detection via a Scale-Time Lattice
- Learning Where to Focus for Efficient Video Object Detection
- ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
- Object Detection in Video with Spatial-temporal Context Aggregation
- Learning Video Instance Segmentation with Recurrent Graph Neural Networks
- Fast Object Detection in Compressed Video
- Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
- Object Detection in Videos by High Quality Object Linking
- Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
- End-to-End Video Object Detection with Spatial-Temporal Transformers
- Towards High Performance Video Object Detection
- Geometry-Aware Video Object Detection for Static Cameras
- Object-aware Feature Aggregation for Video Object Detection
- Crossover Learning for Fast Online Video Instance Segmentation
- TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video
- Automated Rip Current Detection with Region based Convolutional Neural Networks
- Detect or Track: Towards Cost-Effective Video Object Detection/Tracking
- Performance of object recognition in wearable videos
- Learning to Track Object Position through Occlusion
- Temporally Identity-Aware SSD with Attentional LSTM
- Moving Target Defense for Deep Visual Sensing against Adversarial Examples
- 3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation
- Plug & Play Convolutional Regression Tracker for Video Object Detection
- SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection
- Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending
- A stepped sampling method for video detection using LSTM
- Object Detection in the Context of Mobile Augmented Reality
- DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
- 3D Object Detection and Tracking Based on Streaming Data
- Single Shot Video Object Detector
- Long Short-Term Relation Networks for Video Action Detection
- Feature Flow: In-network Feature Flow Estimation for Video Object Detection
- Temporal RoI Align for Video Object Recognition