{"total":66,"rows":[{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78,"area":null},{"id":"2205.05979","title":"MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection","created":"2022-05-12","cited_by_count":65,"area":null},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40,"area":null},{"id":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37,"area":null},{"id":"2110.12638","title":"Deep Learning for UAV-based Object Detection and Tracking: A Survey","created":"2021-10-25","cited_by_count":33,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","created":"2022-09-06","cited_by_count":17,"area":null},{"id":"2207.10959","title":"QueryProp: Object Query Propagation for High-Performance Video Object Detection","created":"2022-07-22","cited_by_count":12,"area":null},{"id":"2303.11003","title":"Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization","created":"2023-03-20","cited_by_count":12,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2106.15315","title":"Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics","created":"2021-06-21","cited_by_count":10,"area":null},{"id":"2309.04302","title":"Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes","created":"2023-09-08","cited_by_count":9,"area":null},{"id":"2311.00987","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2210.02368","title":"Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection","created":"2022-10-05","cited_by_count":8,"area":null},{"id":"2303.15416","title":"3D Video Object Detection with Learnable Object-Centric Global Optimization","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2102.13493","title":"ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation","created":"2021-02-26","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2210.06008","title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2103.14529","title":"Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation","created":"2021-03-25","cited_by_count":5,"area":null},{"id":"2106.05665","title":"Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2210.00588","title":"DFA: Dynamic Feature Aggregation for Efficient Video Object Detection","created":"2022-10-02","cited_by_count":5,"area":null},{"id":"2301.01917","title":"Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Information","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2402.09241","title":"Efficient One-stage Video Object Detection by Exploiting Temporal Consistency","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2103.11017","title":"TDIOT: Target-driven Inference for Deep Video Object Tracking","created":"2021-03-19","cited_by_count":4,"area":null},{"id":"2109.06148","title":"DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2208.08315","title":"Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2104.12106","title":"Temp-Frustum Net: 3D Object Detection with Temporal Fusion","created":"2021-04-25","cited_by_count":3,"area":null},{"id":"2109.05078","title":"A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos","created":"2021-09-10","cited_by_count":3,"area":null},{"id":"2304.10622","title":"Enhancing object detection robustness: A synthetic and natural perturbation approach","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2106.10766","title":"Learning to Track Object Position through Occlusion","created":"2021-06-20","cited_by_count":2,"area":null},{"id":"2206.11459","title":"Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline","created":"2022-06-23","cited_by_count":2,"area":null},{"id":"2208.11315","title":"Comparison of Object Detection Algorithms for Street-level Objects","created":"2022-08-24","cited_by_count":2,"area":null},{"id":"2309.01391","title":"SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2402.07642","title":"A Flow-based Credibility Metric for Safety-critical Pedestrian Detection","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2111.08867","title":"TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video","created":"2021-11-17","cited_by_count":1,"area":null},{"id":"2303.01219","title":"A Coarse to Fine Framework for Object Detection in High Resolution Image","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2312.14492","title":"Context Enhanced Transformer for Single Image Object Detection","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2401.12729","title":"Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2405.18857","title":"SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2410.13616","title":"Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2410.16057","title":"Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotations","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2412.04915","title":"Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection","created":"2024-12-06","cited_by_count":1,"area":null},{"id":"2502.12415","title":"Gaseous Object Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2102.05275","title":"A Generic Object Re-identification System for Short Videos","created":"2021-02-10","cited_by_count":0,"area":null},{"id":"2105.08253","title":"Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach","created":"2021-05-18","cited_by_count":0,"area":null},{"id":"2106.12966","title":"Class agnostic moving target detection by color and location prediction of moving area","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2110.09881","title":"HM-Net: A Regression Network for Object Center Detection and Tracking on Wide Area Motion Imagery","created":"2021-10-19","cited_by_count":0,"area":null},{"id":"2111.13233","title":"Look at here : Utilizing supervision to attend subtle key regions","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2204.13492","title":"Representation Recycling for Streaming Video Analysis","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2205.02371","title":"A Bayesian Detect to Track System for Robust Visual Object Tracking and Semi-Supervised Model Learning","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2211.11077","title":"Unifying Tracking and Image-Video Object Detection","created":"2022-11-20","cited_by_count":0,"area":null},{"id":"2211.15505","title":"Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2212.08415","title":"Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2301.07921","title":"Spatio-Temporal Context Modeling for Road Obstacle Detection","created":"2023-01-19","cited_by_count":0,"area":null},{"id":"2303.11291","title":"Mobiprox: Supporting Dynamic Approximate Computing on Mobiles","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2307.10039","title":"Deteksi Sampah di Permukaan dan Dalam Perairan pada Objek Video dengan Metode Robust and Efficient Post-Processing dan Tubelet-Level Bounding Box Linking","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2311.08557","title":"Low-light Pedestrian Detection in Visible and Infrared Image Feeds: Issues and Challenges","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2402.10752","title":"STF: Spatio-Temporal Fusion Module for Improving Video Object Detection","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2509.11323","title":"Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2601.14677","title":"A comprehensive overview of deep learning models for object detection from videos/images","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2605.17584","title":"VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.15112","title":"Learn Temporal Consistency For Robust Satellite Video Detector","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2609.29648","title":"Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}